Project: Sway The People!

Description

Sway The People! is a political simulation game for Linux, Windows and macOS. It is an Electron-based project, written in TypeScript.

I started developing it on July of 2026, and released the 1.0.0 version on August 11th, 2026.

In the game, players run a political campaign for leader of a fictional nation, against 3 other candidates, with events, debates, and public opinion in general being driven by LLM models. The premise of the game is to make the campaign (and the nation itself) as custom as possible, with the player being able to create their own policies and speeches in free text, and everything else in the game adjusting itself to that through generative AI models. While some parts use more traditional evaluation mechanics, the idea is for the bulk of the gameplay to be guided by LLMs.

While I enjoyed playing several campaigns, the game is mostly an exploration of how generative AI, and LLMs in particular, can be embedded in games to enable new experiences.

Context

The development of Sway The People! happened at the convergence of three threads: me experimenting with vibecoding, Anthropic's Fable 5 release and my interest in applying generative AI to games. I will describe each one here.

Vibecoding

After using generative AI for several purposes since early 2023, and starting to use coding agents around 2025, this year I am exploring development flows that use generative AI in even more pervasive forms. One of the furthest down the spectrum (and trendiest one) is vibecoding, in which the developer avoid as much as possible looking at the generated code, and drives the development just by talking with a coding agent and accepting whatever it produces - if something does not seem right, the developer just asks the agent to change it again. For Sway The People!, I decided to try this flow: I focused only on the requirements and the overall vision for the project, while delegating all the code concerns to the agent. I will go into more details about my flow further down in this post, in the highlights section. Suffice to say, I think I was able to achieve the vision I had for the project, but I had to follow a more organized and thoughtful approach than most vibecoder-gurus preach about. Despite the success, I still prefer the AI-assisted Engineering approach, in which coding agents are used to speed up the development, but the developer still remains very involved with the final code.

Fable 5

The second thread was the release of Fable 5. Earlier this year, Anthropic announced it had created a model representing a whole new class of intelligence, called Mythos, which it declined to release to the general public; instead, on June 9th of 2026, it released Fable 5, a version of the same model with additional safety measures. What followed was quite a saga: just three days after launch, the US government put export controls on the model and Anthropic suspended all access to it, only restoring it globally on July 1st. On top of that, Anthropic had said from the start that Fable would only be temporarily included in the usage limits of subscription plans, requiring separately billed usage credits afterwards... but the cutoff date kept getting pushed forward (it moved from June 23rd to July 8th, then July 13th, then July 20th), until Anthropic finally announced, two days before the last deadline, that the model would remain a standard part of the higher subscription tiers indefinitely. During those weeks of uncertainty, many people (myself included) rushed to experiment with the capabilities of the model while it was still accessible. Sway The People!, developed through July and August, was one of my main "Fable projects": I used the model for everything in it, precisely to explore what this new class of intelligence could do, expecting all the while that it would become unavailable to me at any moment. Which, fortunately, ended up not happening!

Generative AI embedded in games

The final piece of context has to do with my own interest. I have been following the generative AI boom since early 2023, and I have always had a huge interest in games - as a matter of fact, most personal projects I had before starting to explore AI Engineering were small games. So, it is very natural to merge both trends (I did a little bit of this with LicLacMoe, though that was a very tongue-in-cheek type of project). Now that I have a good understanding of, and experience with, AI Engineering, I feel ready to start experimenting more seriously with games that have generative AI embedded into them. I am very interested in how these models (both for language and image) can expand the set of experiences that games can offer. Especially, it seems to me that they allow for extremely customized experiences, to a level that could not even be dreamt before. Sway The People! was the first experiment on this line, and I already have several other ideas in mind that I expect to explore in the following months.

Highlights

Foundational guiding documents

As I mentioned before, for Sway The People! I decided to go the full vibecoding route, delegating all coding related concerns to the AI agents. In order for this to work without becoming a hellish mess, I chose to set the stage by using the AI agent to generate a few guiding documents beforehand. These documents steer all future work (and are updated whenever needed), ensuring a minimal level of consistency in the project. I used a PRD (Product Requirements Document), a Technical Requirements document and an MVP scope document.

My flow was as follows: I started with a dump of all my ideas for the project into a notes file. This initial file was really a brainstorm: very loosely structured, written with no care for grammar or syntax, and all over the place. I then started a session with an AI coding agent (Fable, through Claude Code), which I used throughout until the guiding documents were finished. I first asked it to read the notes and ask any questions it had to clarify any points, before writing the PRD - this document would only contain product definitions, without any technical decisions or assumption. It took a few back and forth messages until it was ready, and then we moved on to the Technical Requirements document - here would be where all the important technical decisions live, including things like which programming language, which frameworks, and so on. It also took a few messages to be ready. Finally, I asked it to work with me to define the MVP scope for the initial version.

Overall I think this flow worked out fine, and gave better results that what I usually get by jumping straight into asking for a project with some specific features. The documents I described were not the only ones, but they were the new ones I used for this specific mode: I also worked with the agent to create an AGENTS.md, a README.md and an ARCHITECTURE.md files to document all the relevant info and contribution guidelines (both for AI and human agents).

Fable 5 performance

I used Anthropic's model Fable 5 for everything in the development of Sway The People!. Part of the project was experimenting and understanding the capabilities of this model, as it was said to bring a new class of intelligence in comparison with the other frontier-level models (mostly Anthropic's Opus and OpenAI's GTP 5). I found the claims to be mostly accurate: working with Fable really feels substantially different than working with any other model. The thing that most impressed me was its ability to make autonomous decisions that were, by and large, spot on. While working with other models, whenever they would reach a point where something was not very precisely specified and had to make a decision by themselves, I would more often than not have to trace back and course correct it. With Fable, however, I almost always could just let it pick a path forward and run with it, only a few times having to ask it to change something.

Pacing dictated by LLM inference speed

A peculiar aspect of the resulting game is its pacing, especially when using local models. Although I already expected any game that relies on running LLMs locally to have a slow progression, actually playing the result made it very clear that these types of games have to be designed with plenty of waiting time in mind.

The timing will definitely vary a lot based on the hardware of the player and the chosen model. I have a fairly good computer (at least by 2024's standards, when I bought it) with 16GB of VRAM plus 64GB of RAM, and mostly played with models in the 20B-30B range. For me, each creation would take a couple of minutes, making each day take anything between 10 and 30 minutes to play (depending on if it had events, influencer content creation, debates, etc.). Running the game with an 8B model made the pace dramatically faster. Different hardware, as well, should change this by a large factor. This variability seems to me one of the most complex considerations for any game aiming to use local LLMs as the main driver.

Regardless of the variability, the fact that generations always take some time (even the hosted ones) means several structural support things need to be built around them in the game. One such things I had to use in Sway The People! is a generation queue, which makes sure that generations happen asynchronously, sequentially and their results are smoothly integrated back into the game once they are complete. I consider the asynchronous aspect to be mandatory for any game using current generative AI tech in its core, otherwise the game will hang for a prohibitively long time and the user experience will be horrible. Making the generations sequential is also mandatory for most local setups (current customer hardware struggles to supply inference on even a single request at a time, let alone multiple), though it can be optional when using hosted options. And making sure that the results are smoothly integrated into the game is the most tricky one of them all, but it is absolutely essential to keep the user experience fluid. I might consolidate my thoughts about these new architectural concerns intrinsic to generative AI native games on a future blog post, and I will surely keep updating my understanding of them as I develop more projects like this one.

For me, the pacing worked very well. I am used to having several different things going on at the same time and alternating my attention between them, so I played the campaigns as a "background game", making some decisions and then turning to something else for several minutes before coming back to play the "next turn". But I admit I am probably part of a very small slice of the population that would find games with this pacing fun!

Sandbox and customization

The central idea behind using LLMs for the gameplay was to make each campaign extremely custom, in the sense that it would react to the player's choices and words in a way that is not possible with traditional coding. I am fairly confident to say that the final result proved the point.

I ran some really wild campaigns, choosing policies that ranged from fairly conventional to completely unsuited for a nation-wide program. Each time, the game reacted appropriately, even accurately raising the difficulty to an impossible level when the agenda would make no sense for a political campaign. So much so, that I had to put some arbitrary balancing constraints on the initial public opinion, so that even crazy ideas would have a minimal chance of winning the campaign based on the player's performance.

I think the influencers mechanic was particularly nice in this aspect: being able to read how each character would mold the party's agenda in a way to communicate with their particular audience really drove home how unique the new capabilities that LLMs bring for interactive entertainment are.

AI Usage statement

Outside of the software engineering and startup-pilled bubble, the current sentiment with regards to Artificial Intelligence in society is extremely negative. Especially in games, the public opinion is overwhelmingly that AI is a cheap way for companies to extract more profit while providing a lower quality product.

Due to this, I chose to write an AI usage statement for the project. In this statement, I describe why and how I believe AI can be used to provide new and unique experiences in games, and the way I used it while developing Sway The People!. I argue that not only AI makes unproven game genres more viable, but also that it can make each player's experience more unique and customized (as I talk about a few sections above in this post). I understand that the way in which large companies use AI, as a cheap way to quickly produce mediocre assets and cut off personnel costs, leads to a drop in quality and a worse ecosystem state overall, but I also believe that there are other ways in which AI can be used, which are much more beneficial for everyone. By building positive examples of such usages, hopefully we can build a better alternative and steer this technology into a better path.

I expect to include something similar in future projects, at least for the near future.

Other game genres

After having built Sway The People! as a proof of concept for using LLMs as a core mechanic for a game, I look forward to explore the same idea with other genres. While I like the idea of political sims, and enjoyed playing this game in particular, it is not really a genre I play very often. I chose it mostly because of the obvious appeal to use free text during debates and policy definitions (and also the fact that we are on an election year here in Brazil, so it is being talked about all the time).

I already have several ideas for other games using the same approach, or expanding it. All of them in different genres. I expect to be able to finish at least one more project within the year, and maybe a couple for next year. I will, of course, write about them in this blog once I release their first versions.

Future Expansions

I do not plan to expand Sway The People! much further, as I would like to move on to new projects that apply generative AI on other game genres. However, there are a couple of things I still want to implement, and some other ideas that I will leave queued up in case I decide to come back to it in the future.

Nations

The main improvement I want to make is on nations. In the MVP of the game, for every campaign a totally new nation was created by the AI model based on the chosen agendas. There were two problems with this: first, that campaigns were not replayable, if the player wanted to try to run another campaign on the same setting they would need to save at the very start of the campaign and later load that save to replay the entire campaign; and second, that nation creation is probably the most time-consuming part of the entire game, so before even starting to play the player was stuck for about half an hour waiting for the setting to be created.

For the initial release (version 1.0.0), I implemented default nations. Now the player can choose one of 3 pre-defined nations when starting a campaign, so that both of the problems mentioned before disappear. The player can also still choose to have the AI generate the entire nation if they desire, but that is a choice rather than the only possibility.

I want to implement three features related to nations (two of each I am almost certain to do before moving on from the project, the third one I am not sure yet if I will do or keep for a later time): saving the current nation during a campaign, so that the player can replay a setting they really liked; loading custom nations, so that the player can use a saved nation to start a new campaign on (which also has the nice side-effect of allowing for sharing custom nations between players); and finally, an in-game nation editor, so that the player can manually set all parameters of the nation. Saving and loading should be relatively simple features, so I intend to do them in the near future. The in-game editor is a more complex one, so I am still debating whether to implement it or keep it on hold (as long as the load nation feature is available, players can just edit the nation files to handcraft anything they like, anyway).

Campaign lengths

Currently, the game has a fixed length of 14 days for all campaigns. While I discussed briefly with Fable 5 about which length to use for the MVP, this was mostly a dummy value so that I could focus on the rest of the development. I think overall it works pretty well, though I did no research to figure out how common this length in real countries, nor did any comprehensive playtesting to determine if it is the optimal choice.

My idea is to make the length of the campaign a choice when starting a new one, just like games such as the Civilization series usually let you choose to play a short, medium, large or marathon-style session. I will probably settle for something like 14 days for a short campaign, 30 as the medium length and 90 for an epic campaign.

The main concern here is checking whether any balancing needs to be adjusted in all the public opinion calculations in order to make all campaign lengths fun. I think events and debates should not have much problem, as they can both improve and degrade the player's candidate popularity, and opponents also have their own fluctuations; but the influencer system might need to be adjusted, as their impact is always a straight bonus which might become overwhelmingly decisive on longer campaigns.

Media assets

Finally, in order to make the game an actually enjoyable experience for more people instead of a proof of concept, I would need to include media assets: music, images, animations, etc. The simplest route would be to either license or build assets and include them in new releases of the game. I might do this for a few ones: for instance, even during development I inteded to make the background image for the debate screen an actual debate stage (I even had the image to use), but I just never got to it and did not feel it was missing when playing. For simple things like that, I might still include assets.

My long term vision, however, is to also explore how image generation can be embedded into games (as I briefly explored in Chargen), much like Sway The People! already does with text generation. Once I start exploring this, I might circle back to this game and implement it here, for instance by procedurally generating image avatars for councilors, candidates, influencers, etc., or maps for nations with their regions clearly visible. I think it could add a lot of fun to the game. But I don't feel that the current state of the technology and customer hardware available is sufficient to make this feasible yet. My previous experiences trying to have an application that depends on having both an LLM and an image generation model running at the same time in the local machine does not give me much confidence that even people with generally good computers would be able to run it efficiently, and I do not know of any image generation hosted service that allows for a generous amount of free generations each day, like OpenRouter does for text generation. So this is mostly something for maybe 3 to 5 years in the future.

Setup

I developed Sway The People! intending it to be a portfolio project. For such projects, I have a set of minimal criteria I always use. Here is how it complies with those criteria, and in which ways it differs:

I use Github Actions to generate new releases for Sway The People!. Here I made a small update from my previous approach: in all previous portfolio projects, I always configured the workflow to generate the release when code was pushed to the main branch, this reflected my experience in the industry for a long time and worked fine for me through many years. However, it was somewhat clunky in the sense that I always had to keep the main branch stable and do all the development in a separate dev branch, which is overkill for a single developer project, and involved a lot of ritual around the main branch, while also having to rely on arcane commit message conventions to manage versioning increments. For Sway The People!, I changed it so that the release workflow happens triggered by a push to a version tag. This simplifies the process significantly: the version is always obvious from the tag itself, and the main branch is freed from any ritual, better reflecting the state of development.

I have a changelog file and a file with guidelines about contributing, beyond the usual readme file as documentation. This is in addition to all the vibecoding-related documents (PRD, Technical Requirements, etc.) I mentioned before.

I also included automated tests for everything except the UI code. In previous portfolio projects, I always made sure to keep a high test coverage, and favored using TDD (Test-Driven Development) while developing the projects. Since in Sway The People! my approach was to delegate all coding to the AI agent, instead of using TDD I worked together with the agent to include instructions on AGENTS.md, ARCHITECTURE.md, and all other relevant documents, guiding any contributor (AI or human) to extensively use tests for any new development. I think this worked pretty well. Despite not having directly checked the total coverage, I found very few bugs while playtesting (much less than I would have expected from a project of this scope), and while watching the logs as the agent worked I saw that several times it caught errors and bugs on its implementation by running automated tests, fixing them before completing the task. I do not know yet if this is a characteristic of Fable 5, or if other models of different intelligence classes would also achieve the same.

Links

Source code: Github

Executable: Releases

Monthly Recap - 2026-07 July

After a long while, in July I was able to once again have a very productive month with my personal projects. This years has been incredibly challenging with all the recent changes in the software industry and the uncertainties that come with them, so most of my efforts had to be shifted to compensate for that in my day job. This month, though, I was able to dedicate more time to my own things, here is a short summary of what I accomplished.

Achievements

Several new blog posts

One of the areas I had not been able to touch for several months had been this blog. While I have been trying to always write at least a monthly recap post, describing everything I have been working on during the month, the last time I had written one had been about January. This month I covered the gap, and wrote the recap of what I did every month, up until June. Thankfully I keep quite well-organized notes about everything I work on, so it was not that hard to figure out what went in which month.

Beyond this, I also wrote two more blog posts, one describing my experience with opencode and the other with my analysis of volume 34 of Thoughtworks' Technology Radar. I had been meaning to do both for a long time. The first one I wanted to write because it goes off the beaten path of Claude Code, Codex, etc. I really think opencode brings a promise of cheap experimentation that is very much worth talking about. The second one is an exercise I have been meaning to do ever since I started this blog, which is to share my thoughts about the main discussions happening in the software engineering world. I had already written some posts summarizing my experience in conferences, but never went deep into any major report. The Technology Radar is one that I read every single edition for the past 5 or 6 years, so it was a very natural first choice. And I intend to continue doing so with future editions.

Finished studying Fundamentals Of Software Engineering

I picked up Fundamentals Of Software Engineering as part of my personal studies habit midway through last year, as I was switching teams to work on a new product. I thought it would be a great opportunity to get a stronger theoretical grounding on software architecture, as I would be once again witnessing one emerge. While it was a very bumpy road from then until now, I think studying this book was mostly a positive experience, and while I did not learn a whole lot from it, it helped me organize my thoughts and categorize several ideas and concepts.

First pre-release of new portfolio project

July also saw the first pre-release of my new portfolio project. My last such project was LicLacMoe, which I released in early 2025 (more than a year ago). My plan since 2023 has been to release at a minimum one new portfolio project a year, and ideally two per year. With this new project coming up, I remain on track with the plan for the third year in a row. Although the project can already be found in my GitHub profile, I do not want to talk too much about it yet, as I still intend to improve it before making the first official / major version release. Once I do, I will write a dedicated blog post for it, and include a mention in the respective monthly recap post.

Plans for next month

Start next career book studies

Since I finished Fundamentals Of Software Engineering on July, I am now ready to pick up the next book to study on the career track of my personal studies habit. I am evaluating the ones I had in my backlog in order to pick up the one that makes the most sense right now. By August I should have finished choosing and started studying the next one.

First full release of new portfolio project

As I mentioned before, I have a brand new portfolio project coming up. While the version 0.0.1 is already available, I should soon have the first major version, 1.0.0 ready to release. In August I expect to make this release and write up a blog post about the project, as I have done previously for each recent portfolio project.

Thoughtworks - Technology Radar 34

Intro

Twice a year, Thoughtworks publishes its Technology Radar, an opinionated guide to the current technology landscape. It organizes notable technologies and practices (which they call blips) into four quadrants: Techniques, Tools, Platforms, and Languages & Frameworks; and four rings that express how confident they are in recommending each one, from "Adopt" down to what used to be called "Hold". I have been following the Radar for several years now, and reading each new edition has become something of a ritual for me. Volume 34 came out in April of 2026, but this time I was only able to read it in July, so parts of it already felt slightly outdated... which says as much about the current pace of the industry as it does about my reading backlog. Here are my thoughts on this edition.

General Comments

The first thing that caught my attention was a change to the Radar itself: the "Hold" ring has been renamed to "Caution". I dislike this change. It feels like an unnecessary cave in to the current hype machine, which insists that everything new must be flawless and that pointing out problems is bad for business. Being able to take a stand and argue against certain things, when one has strong arguments, is important for any serious conversation about technology, and softening the language of the ring that exists precisely for that purpose seems like a step in the wrong direction.

The distribution of blips across the rings tells an interesting story. There are 62 blips on Assess and 30 on Trial, against only 17 on Adopt and 9 on Caution. That overwhelming concentration in the middle rings feels very symptomatic of the times we are living in: there is an explosion of new things appearing, and it is necessary to at least keep track of most of them, while investing time to go deep into only a few. It is also striking how few blips landed on Caution - eight of the nine are Techniques, one is a Tool, and there are none at all in Platforms or Languages & Frameworks. The Platforms quadrant, in fact, has zero blips in both Adopt and Caution: everything in it sits in the middle, still being evaluated, with nothing yet considered either safe enough to fully recommend or problematic enough to warn against.

All four themes of this edition are related to AI: "The challenge of evaluating technology in an agentic world", "Retaining principles, relinquishing patterns", "Securing permission-hungry agents" and "Putting coding agents on a leash". It is the second time that this is the case, in previous editions there used to always be at least one theme dedicated to something else, as an effort to keep a broader view of the ecosystem. The four themes seem to form two couples: the first two are about how we humans are changing to adapt to this new model of working, while the last two are about the technical side of embedding generative AI models within a useful "exoskeleton" that is both effective and safe.

Highlights

OpenClaw is the only tool placed under Caution, and to me it is a clear portrait of the current state of AI hype. It made a huge impact when it was first released, and just a few weeks later it was already far less talked about... by now, it is rarely mentioned at all. I was always skeptical about the "hyper-personal AI assistant" category itself, as I see little value in delegating relevant choices of my life to an artificial intelligence. But beyond my personal preferences, the trajectory of OpenClaw illustrates the broader pattern: there is a huge push towards adopting every new thing that appears, without any clear success story that has proved itself over sufficient circumstances.

The agentic coding tools, on the other hand, are where the consolidation is most visible. Cursor reached Adopt, and it was one of the first agentic IDEs I tried, early on. I had an overall good experience with it, though not a very remarkable one. It holds the distinction of being the only agentic coding tool with which I hit a token budget limit while coding (the only other time that happened was with Claude Code, and that was because I was testing Fable, a model with a more restrictive budget). Since the limit appeared unexpectedly, midway through development, I switched to Windsurf and never went back: overall, I preferred working with Windsurf. On Assess, Pi is one I find very promising: I have seen some very interesting proof of concept projects using the Pi SDK as a framework on top of which entire TypeScript systems are built, UI and backend included. It seems like a great candidate to bridge the gap between AI agents and traditional applications, enabling truly agentic applications, and I am very interested in testing it soon. Also on Assess is OpenCode, which became a true milestone in my routine - it is now my tool of choice for simpler or more exploratory tasks, and I wrote a dedicated post about it recently. And finally, Claude Code reached Adopt, having indeed become the industry standard for agentic AI coding: I have been using it extensively, reserving it for the complex tasks that demand state-of-the-art intelligence.

Small language models appearing on Assess caught my attention for a different reason. By "small", the Radar means models of 3B parameters and below, which sits just outside the range I most commonly explore in my personal open source projects - JenAI, LLP and Chargen are built to work with models in the 8B to 70B range. Adding the frontier models I use for development, there is now a whole spectrum of model sizes, each serving its own purpose. I like to think this shows we are starting to reach some level of maturity in employing AI for actual use cases, moving beyond mere experimentation: choosing the right size of model for the job is the kind of engineering decision that only becomes relevant once the technology is being put to real work.

Curated shared instructions for software teams reaching Adopt was particularly satisfying to see. As an InnerSource champion, I have been talking within my company about how AGENTS.md and similar instruction guidelines for agents are now an important and integral part of any project, and how they enable more effective collaboration even from outside contributors. I have given a series of talks about this in internal events already, and I plan to at least write a blog post on the topic soon.

Codebase cognitive debt, placed under Caution, names one of my main concerns with the current shift to AI-assisted software engineering. I have developed software across the whole spectrum that goes from full vibe-coding (just ask the AI and go with whatever it produces, without even looking at the code) to purely human-written code, and I have had successful results at every point of it. But the characteristics of those successes are different, and being distant from the code still does not feel as reliable and sustainable as being hands-on. A big part of being proficient at developing a software system lies in the mental map one has of it, and not being actively engaged in writing the code erodes that map very quickly. This fundamentally changes the process of software engineering. When humans write all of the code, the more you work on a system, the better you become at working on it, because your mental map keeps expanding. When humans stop looking at the code, the relationship inverts: the more you work on the system, the less proficient you become, as the code evolves in ways you can no longer clearly picture. There is no turning back, and the current push in the industry is for humans to be as far out of the loop as possible in order to gain development speed. But we have not lived with this model long enough to have clear success stories that have stood the test of time and proved it sustainable... and until we have those stories, I remain cautiously skeptical.

Things Tested And To Test

Beyond the highlights, several other blips crossed paths with my own explorations. Among the things I have already tested are LangGraph (which I have used as my default choice of AI agents framework - the Radar moved it out of Adopt and into Trial, as there are newer alternatives that can compete with it now), Google's Agent Development Kit (ADK) (which I used briefly when assessing different agent frameworks, and enjoyed more than other alternatives I also tried such as CrewAI, as it maps better to a software engineering mindset - the Radar's main criticism is that it is still pre-GA) and HTML Tools (the first time I see this explicitly named, but an approach I have been following for a while: whenever I ask a coding agent for a report, I ask for the findings consolidated in a nicely stylized standalone HTML page, which reads much better than the default markdown).

On the list of things I want to test are Mastra (a TypeScript-native open source framework for building AI applications and agents), team of coding agents (a technique I have only limited experience with so far), code intelligence as agentic tooling (I have not yet explored much of the Language Server Protocol as a way for LLMs to work more efficiently, but it is high on my list) and mutation testing (an idea I have known for years and was always skeptical about for human-written code, but as a "test-the-test" approach for AI-generated test suites, which realistically no one will fully review, it finally starts making sense to me).

Closing Thoughts

Stepping back, the picture this edition paints matches what I see in my daily work. Kent Beck describes the life of a product in three phases, his "3X" model: Explore, when you cheaply try many things in search of what works; Expand, when something has caught on and you scale it while removing bottlenecks; and Extract, when the ground is stable enough to optimize for efficiency. The AI-dominated landscape of this Radar feels like an industry moving from Explore into Expand: the explosion of new things being created continues (hence the crowded Assess and Trial rings), consolidation is beginning around a few winners (hence Claude Code and Cursor on Adopt), but there is still no concrete success story that has stood the test of time... which is precisely why so much of the Radar remains in the middle rings, and why I keep some healthy skepticism about the most aggressive promises being made.

The next edition of the Technology Radar should be released around October or November of this year. I intend to once again read it (hopefully closer to the release date this time) and share my thoughts here on the blog.

Exploring opencode

I started using opencode around May of 2026, and it truly felt like a milestone in incorporating AI into my daily routine. I mentioned in my May monthly recap that I intended to write a dedicated post about the experience, this is that post.

Some context first. I started using AI coding agents (or harnesses, as I prefer to call them) around August of 2025, with Cline on VSCode, and then moved on to Claude Code in January of 2026. In both cases this happened at work, for purely professional purposes, coding and other software engineering tasks. It was only when I began experimenting with these tools on my personal computer, for a much broader range of tasks, that I eventually discovered opencode. It was a spark that changed a lot of how I think about and use harnesses, for a few reasons.

What Sets It Apart

Install And Start Using

The first thing that struck me is how simple the setup is. With every other harness I have used or looked into (Cline, Claude Code, Codex, etc.), there is a whole ritual before you can do anything: create an account, choose a subscription plan, log in through the tool, and so on. With opencode, you install it and start using it. That is the entire onboarding. It sounds like a small thing, but it completely changes the feeling of picking up the tool for the first time.

Free Access To Reasonably Good Models

The second reason is that opencode currently offers free access to reasonably good models, without any severe limits. The obvious caveat: it is impossible to know for how long this will be sustainable, and opencode might well start limiting usage or requiring a paid subscription in the future. The slightly less obvious caveat: every session needs to be treated as likely shared with the companies that created the model, as the simplest benefit a company can get from giving access to their models for free is data for future training... so, best not to share any personal or sensitive information. Regardless, right now it makes opencode a perfect tool for experimentation.

By lowering the cost of exploration to basically zero, it allows everyone to try the harness for all sorts of things, not just coding. These tools have access to terminal commands, beyond reading files and accessing the web - which means that anything that can be done on a computer can be explored through AI with them. And a huge amount of our society runs on computers, so the potential is enormous. To give a few examples of things I have done: searching for a public, free web radio station from any country (Argentine rock forever!) and playing it directly through the terminal, looking up lyrics and other info about new music I found, and debugging and fixing a broken game installation by letting the agent look at the actual configuration files. Without the burden of knowing you have a certain limit of tokens to spend, you feel free to explore all sorts of random things that an AI agent might do with a computer.

I am even considering making opencode the very first thing I install, the next time I setup a brand new OS installation (likely Linux, as it is my default OS). I find it intriguing to think what an AI-based distro would look like, though I would not want to go to the extreme yet. In my mind just being able to bootstrap the OS with opencode, and then using it to install everything else that I need (as it would have access to the package manager of the distro) by just talking with the computer feels really cool.

Open And Provider-Agnostic

The third reason is that opencode is a fully detached, open source agentic harness that can work with models from several providers. Most tools in this category fail at least one of these criteria: they are IDE-first (Cline), closed source, or tied to the provider that created them (Claude Code with Anthropic, Codex with OpenAI). Pi is an alternative that is also detached, open source and provider-agnostic, but it is far less complete when it comes to features and capabilities.

Being provider-agnostic also means opencode can be used with local models. So even if the free access to hosted models disappears in the future, it will still be possible to run it for free with local ones. That is a kind of insurance that no closed, single-provider tool can offer.

Limitations

Despite all the positive aspects, there are some limitations as well:

Model Quality

While the free hosted models are good, they do not reach the same level of quality as frontier models. For more complex or nuanced tasks, they often do not achieve the best results. This can be worked around with more guidance and handholding from the user, but it takes more work. For the absolute best quality, proprietary models (which usually work better with their own company's harness) are still the way to go.

Context Management

Context management is often a problem. Most of the free models offered have a context size of at most 128k tokens, which gets consumed very quickly - the tool seems to be quite aggressive about how much it puts into the context. It does perform automatic summarization when it gets close to filling the available context, which is good, but more often than not the summarization loses some information that is essential to the task at hand. In practice, this means the quality of the results degrades very quickly, making opencode not very suitable for long-running tasks.

Closing Thoughts

For me, the real significance of opencode is not any single feature, but what the combination enables: a tool that anyone can install and immediately start using to explore what AI agents can do with a computer, at no cost. The frontier of quality still belongs to the proprietary models and their harnesses, and the limitations around context are real. But as a gateway for experimentation, and as an open, provider-agnostic foundation that will keep working regardless of what any single company decides, it has earned a permanent place in my toolbox. I expect to keep exploring what these agents can do well beyond coding, and I am sure some of those experiments will end up here on the blog.

Monthly Recap - 2026-06 June

After two very intense months of working overtime in April and May, June finally saw things gradually getting back to a more sustainable pace. I chose to take it easy and not use all of the newly available free time for personal work though, as I felt like I was very close to getting burnt out if I maintained the same rhythm. I hope that taking a few weeks now, mid way through the year, to rest and re-energize will allow me to have a very productive and purposeful second half of 2026. Here's a quick summary of what went on in June for me.

Achievements

Personal Studies Progress

My personal studies habit got quite messy over the last year, and I have not done a great job of describing what I have been doing in the last few monthly recaps, so I will take a short moment to put everything back on track here. At about the middle of last year (2025), it became clear that the software development ecosystem was finally locking in to embed AI in its core loop. While I had been exploring the field for about a couple of years already by then, I felt the need to build a more comprehensive and grounded understanding of the possibilities and implications of this shift - so, I picked up two books on the topic to study (AI Engineering and Beyond Vibe Coding).

At the time, I was already studying two other books. This, coupled with a transition to a new team (and organization) within my company, with a whole new tech stack, proved to be too much change in too compressed a timeframe, and so I went through a couple of not very productive months just struggling with too many things to do and progressing too little on each of them. Early this year, I organized myself to address this, and reduced the amount of books I was working through at a time. So, as I mentioned in previous recaps, I finished them one by one, the last one being AI Engineering.

In June I finally reached the stage in which I could move on to pick new books to study. The first one has been Nexus, by Yuval Harari - I have been a huge fan of his work for more than a decade now, having deeply enjoyed Sapiens and Homo Deus, so naturally I wanted to go through the rest of his work. So far, it has been totally worth it, and I will share more of my thoughts once I finish it.

Electron

While I have developed several tools and apps to be used on desktop environments in the past, they have always been restricted to one of three stacks: simple Python apps with TKinter (one of the first programming languages I learned, always feels very comfortable to go back to), Java apps leveraging Swing for the UI (Java being my main professional programming language for cloud and microservices systems, it was always tempting to accept an old and rusty visual presentation in order to do what I consider myself to be best at) or straight out web apps based on HTML and JavaScript running on localhost (made for better visual presentation while still allowing me to leverage over a decade of experience writing cloud systems, but was a very clunky distribution model).

After learning about the open source Pi coding agent, and seeing some creative usage of it embedded in applications through its TypeScript SDK, I got really interested in exploring its ability to embed AI agents within applications. So I used this as an opportunity to finally do something I've been meaning to for several years now: learn Electron. This will allow me to create desktop apps with agentic capabilities, something that gets me really excited. And also, by using Electron I believe I will be able to continue leveraging my knowledge of web frontend technologies while having a much better distribution model for desktop apps.

I went through Stephen Grider's Udemy Electron course to do this, and it was a really great short introduction. Throughout the years, I have taken several of his courses, and his style always resonated a lot with me. The combination of going very deep into the fundamentals of what is going on and getting that understanding, plus having a preference for code-along sessions instead of just showing the final result is an incredibly effective teaching style. Based on my previous experiences I expected this course to do the trick, and it definitely did.

Plans for next month

For July, the main things I expect to achieve are starting the next career-related book in my personal studies (the ideal number for me is 2, one for career and one for hobbies - currently I am working only on Nexus) and continue building personal applications that explore agentic capabilities woven into specific workflows. I am definitely focusing on Electron + Pi at the moment, but I will also try to build a few experiments with LangChain, as that seems to be the standard that the market is converging on for now.

Monthly Recap - 2026-05 May

May continued the intense overtime push of April, but having been operating in this manner for a while, I was able to get more things done even with little free time. Here is a quick summary.

Achievements

Finished AI Engineering book

After restarting AI Engineering, by Chip Huyen, in April, I was able to finish it this month. This is one of the most highly regarded books in this new field, and for good reason. It covers the full lifecycle of AI systems - from data engineering and model selection to deployment, monitoring, and responsible AI practices in production. While I already had some practical experience with several of these topics from building JenAI and other personal projects, the book helped me contextualize and structure that knowledge in a way I had not been able to before. I am glad I was able to finally complete it, and although it goes in depth on some areas that I normally do not touch (such as model training and fine tuning), I feel like this will be a reference I come back to often.

Started using opencode

This month I also started using opencode, an open-source AI-powered coding assistant. I intend to write a dedicated post about this, as I found the experience really intriguing. For now, it suffices to say that agentic coding assistants in general really feel like the next step for AI. Not the end state, but a significant (and positive) advancement in the capabilities that this technology bring to the table. I already used Claude Code to a good extent, but having an open source alternative, which has flexibility to work with several models from different providers, and comes out of the box with free options, democratizes the access to a whole new level. Really excited to explore the implications of this!

Started AI Engineering Track Udemy course

To complement the book studies, I also started the AI Engineering Track on Udemy. This is a more hands-on, practical course with a stronger emphasis on implementation and tooling. I have just started working through it, and my plan is to go through it systematically over the next few months.

Monthly Recap - 2026-04 April

April was a month with very little spare time for me. A huge rush to wrap up the work for the mid-year event of my company meant that every developer worked double shifts during this period. The bright part is that this time I was able to keep up my personal studies habit - although not much else. Here's a quick summary.

Achievements

Restarted AI Engineering

Last year I started studying AI Engineering, by Chip Huyen. This is one of the most highly regarded book in this new field, with some of the most prominent people in software engineering giving it high praise. Due to the several competing priorities along the way, though, I had to stop studying it for several months. Having just finished Beyond Vibe Coding in March, this month I was finally able to restart it. Maintaining consistency with this habit has been a focus for me this year, and I am very glad I was able to stick with it this month, despite the challenges.

Downpoints

Overtime

As I mentioned before, April was a very difficult month with regards to work-life balance. Of course, having to put some extra effort at specific times when the company needs is part of being a professional, but I hope this does not become the new normal for us.

Monthly Recap - 2026-03 March

March was a month of wrapping up ongoing work and exploring new horizons. After a couple of months getting my feet wet with different AI productivity ideas, I was able to finish studying a book I picked up specifically about this topic, as well as presenting a hands-on session at an internal developer conference in my company. Here is a quick summary.

Achievements

InnerSource synergy with agentic AI presentation

This month I had the opportunity to present at an SAP's internal developer conference. It was my second time presenting at this event in a row. I talked about how the InnerSource philosophy and techniques can have a positive synergy with agentic AI software engineering. I think there is a lot of unexplored territory in terms of how we can engineer collaboration in a way that optimizes the value provided by AI and human agents. It was a great experience to share my thoughts and to connect with other developers within the company.

Finished studying Beyond Vibe Coding

I finished studying Beyond Vibe Coding, a book by Addy Osmani about the evolution of software development with generative AI. It goes way beyond the superficial "AI writes code for you" narrative and dives into practical strategies for integrating LLMs into the development workflow in a sustainable and effective way. It covers topics such as prompt engineering patterns, context management, and how to structure projects to leverage AI without losing control of the codebase. While I think it suffers a bit from the pragmatics of this format for the current context (AI tools evolve way too fast for a book cycle - books shine in consolidating the best practices about things that have been around for a while, but for AI it seems that articles are able to cope with the pace of change better), I found it to be a very practical read and will definitely apply some of its insights going forward.

Monthly Recap - 2026-02 February

February was a month for exploration. With the increasing work load at my day job, I used most of my free time to learn and try out a few new things. As expected, all of them related to AI. Here is a quick summary.

Achievements

Productivity tools

While I continue to use JenAI on a daily basis, it remains (by design) a very limited tool. In order to leverage the benefits of AI more widely, I started developing a few more personal productivity tools. The gaps from JenAI that these cover are a simplified persistence model, more intuitive UI and more sophisticated context management. I have also created a few automations to run AI tasks on schedule. As of now, I have no plans to make either of these open source, as they are more exploratory and specific to my work flow.

ComfyUI

Another area of AI that I had not touched for a long while is image generation. While I played around with Stable Diffusion in its early days, and covered image generation on Chargen, it is not something I do regularly. In February I took some time to update myself on newer tools for this, and did a few lessons about ComfyUI. It seemed to me to do a better job of offering enhanced capabilities around the raw image generation models than the other tools I know about, and I look forward to work more with it.

Finished Rich Dad Poor Dad

On a more personal level, I finished studying Rich Dad Poor Dad as part of my personal studies habit. This took longer that I expected, as I started the book roughly in the middle of 2025, but had to interrupt the studies several times along the way. As someone who had never invested before, I really enjoyed the book and found it to be an excellent introduction to the topic.

Monthly Recap - 2026-01 January

January is always a month for planning. This year, I have a really ambitious roadmap, with several times more goals than I take on average. It will be challenging to meet them, but I am very excited about the prospect of having a more active year!

Achievements

Started AI Projects

One of my goals this year is to start leveraging AI more widely in my work. While I have been studying it and building some projects around generative AI tools, I want to incorporate it more in my everyday activities.

Not only I plan to use AI to get more work done, I am also determined to create a lot more systems that use AI creatively. I do not want to share the details yet, but I will surely write about them as the year goes. I already started with some, and the results have been very inspiring!

Released JenAI v1.8.0

I have been building JenAI since 2024, and despite its simplicity it is still a tool that is very much present in my routine. This month, I released a new version (v1.8.0) adding database support for both Postgres and SQLite. JenAI always had an emphasis on local environments, and one aspect of this was its usage of the filesystem as the only persistence option - while I remain fully commited to keep it local-only, supporting the usage of a database (which still has to be local, anyway) allows for more easily integrating complex features, such as AI-initiated chats and embedding JenAI as the underlying engine for a broader AI system (a future project of mine).

Downpoints

Personal studies lacking

Having difficulties to find time for personal studies was a recurrent theme last year - unfortunately this year started in a similar way. I am not too concerned about this, because I had very good reasons to divert my time to other projects and I have a strong plan on how to get back to this soon, but it still was a negative aspect of the month.

Plans for next month

More AI Engineering studies

Last year I started studying AI Engineering books alongside the classic career and hobby studies I do. This did not end well, as I was overwhelmed with tasks and almost never got the time to do them all. So for February I plan to retake these studies, and come up with a better plan on how to address all the needs in a healthy and sustainable manner.

Year In Review - 2025

2025 was a very busy year, marked by constant changes and several ups-and-downs. While I have been writing monthly recap blog posts for quite some time now, my plans to write an yearly review were left behind last year - I intented the first one to be about 2024, but only now I am able to catch up and write a first attempt at summarizing the year. I will try to be consistent with this, and follow up with one for 2026, 2027, and so on.

Highlights

I will not go deep into the details of each achievement, as that would lead to a very long post and the content would likely be redundant with other posts I did during the year. So, I will just arpeggiate them with a brief description.

Here were the main highlights of the year for me, grouped by their relevant categories:

Personal studies

As a direct consequence of participating in several technical book clubs at work, I took on a personal habit of picking books to study by myself, with the same level of attention that I give when attending a book club. I have been doing this since 2021 (so about four and a half years by now), and it has been an amazing source of personal growth for me. I aim to put around 30 minutes every working day in studying either a career-related book, or a hobby-related book.

This year, however, I was very inconsistent with how much time I was able to put into this. A mixture of going back to working on-site most days of the week, applying and moving to a new team inside my company and buying and moving into a new home meant that I was most often not doing these studies than doing them. Nevertheless, I was still able to go through a few books, here they are:

Studied The Captain Class

Great book about leadership, I started it in late December of 2024 and was able to finish early this year. I saw a lot of the Scrum Master role reflected in the Captain role that the book talks about, and was able to take several lessons about how I could be a more effective Scrum Master. I read this as part of career studies.

Studied Building Successful Communities of Practice

Short but useful book, which I picked up because I wanted to start some groups inside my old team as a forum for bringing improvements to what is a very, very old and static mindset. I ended up getting a position in a different team before I was able to stablish too many things, but I did set up a Code Quality forum that as far as I know is still going strong, so it served its purpose. I read this as part of career studies.

Studied The Prompt Report

Paper about prompt engineering, useful because I have been steadily trying to get more involved with AI Engineering these past few years (yes, before the crazy push we have right now for everyone to become an AI Engineer). I read this as part of career studies.

Started studying Fundamentals Of Software Architecture

Longer book which is an introductory-level presentation of Software Architecture as a field, with its responsibilities, history and peculiarities. I started it roughly in the middle of the year, but was not able to finish yet. So far it has been interesting, although nothing ground-breaking and seems pretty biased at times. I read this as part of career studies.

Started studying Rich Dad Poor Dad

The only hobby studies book I picked this year. I started reading it around August, and wasn't able to finish within the year. However, that should count in favor of the book, because it led me to start investing for the first time, and for several months all my personal time was spent in studying about different types of investment and structuring my finances. This book was really life-changing for me. While I have read several criticism of the book, and I do not agree with everything said in it (in fact, my personal interests and investment profile is very different than that of the author, and I would never want to make the same investments that he does), I still found the content very inspiring and educational. You do not need to blindly follow everything a book says to get value out of it. I read this as part of hobby studies.

Started studying AI Engineering

While I usually separate my studies in either career or hobby, the accelerating pace of AI led me to try a new approach this year. I started adding a technical book as well into the mix, effectively making it three categories. This did not go as well as I expected, I ended up having way too many tasks with less free time, and started skipping the studies for weeks at a time. In 2026, I plan to restrict it to at most 2 categories again. Regardless, the first technical book I picked up was AI Engineering, which is a foundational book for the most hyped type of development of our current times. I have not yet finished it, and so far it has been instructive but not particularly engaging. I read this as part of technical studies.

Started studying Beyond Vibe Coding

The second technical studies book I picked up was Beyond Vibe Coding, which tries to give some guidance of how to effectively incorporate AI development tools into solid engineering practices. This has been more useful than the AI Engineering book I mentioned previously, but it does have the feel of an extended blog post. It is unclear if the content in it will still be relevant 2 or 3 years from now. Nevertheless, I intend to finish it in 2026. I read this as part of technical studies.

Portfolio projects

I like to keep a portfolio of representative projects in my Github profile. These are not only public and open source, but also display, as much as possible, the engineering practices that I value: automated tests, automated CI/CD pipeline, good documentation, etc.

Each year I try to develop at least 1 new project, but I also keep releasing new version of older ones when I have anything I want to add to them. Most of the new projects are focused on exploring how to incorporate LLMs and other generative AI tools into software systems as more than mere chatbots.

Here are the relevant developments of 2025:

Several new versions of JenAI

JenAI was my first portfolio project around generative AI tools, and is basically a terminal chatbot (I have written a blog post about it). I use it extensively for personal purposes, and have built quite a bit of tooling around it for myself. It is intended to be a personal tool, so I have no plans of putting effort into making it generally useful to a large audience, despite being very fond of the project.

In 2025, I released two patches for it: v1.7.2 and v1.7.3, both to improve the sanitization of strings so that it doesn't break when exotic characters are used in the conversation.

Developed LLP (Local Language Practice)

Local Language Practice (LLP) is a system to practice languages through a roleplay chat with LLMs (I have also written a blog post about this one). This was my main project for the year, and it is around a topic that I really want to explore further in the near to medium future: generative AI applied to education. It is a project I have used quite a bit for real learning, but not as much as I wanted because I have had very little time to invest in studying languages this year, unfortunately.

I released the first version in April of 2025 (v1.0.0), and two more versions later in the year (v1.1.0 and v1.1.1).

Developed LicLacMoe

LicLacMoe was more of a fun project, one in which you can play tic-tac-toe against an LLM (as per usual, I have a blog post about this one as well). I like to think of it as "the most useless application of LLMs you will likely ever see". Despite the obvious silliness, it was also an interesting study about how to use LLMs for specific tasks, instead of a generic chat interface. It also allowed to verify the (admittedly obvious) fact that reasoning models are better at playing games with logical rules than vanilla models.

I also released three versions of this one in 2025, all of them in May (v1.0.0, v1.0.1 and v1.1.0).

Finished 4 first steps into AI Engineering projects

Back in 2024 I had started a series of four projects I called "First Steps Into AI Engineering" (guess what? I also have a blog post about this). These consisted of JenAI, Chargen, LLP and LicLacMoe. In 2025 I was able to complete the last two, and wrap up the series. This series was very useful for me to learn how to build systems around generative AI tools (not only LLMs, but also image generation ones), something that is likely to become the baseline of contemporary software development.

Created programming language learning projects curriculum

Late in the year, after moving to a new team that was using Go as the primary programming language (and having no prior experience or knowledge about Go at all), I saw myself having to very quickly learn a new language and tech stack, with the all-too-helpful but way-too-helpful assistance of AI coding tools. While I was able to very quickly become productive, I felt like I didn't understand very well the code I was shipping, and that annoyed me. So I set out to create a curriculum of projects for myself that covers most of the basic concepts I have used in my career, the purpose of which being that if you implement all the projects it contains in a particular language, you should feel very comfortable developing software in that language. I am currently applying it to Go, and so far it has been proving itself as useful as I intended it to be. (Of course, I have a blog post about that).

Developed Catcher Server project

In the end of the year I also developed the Catcher Server project (and wrote a blog post about it). It is somewhat of a break with the large line of AI-related projects I have been implementing in the past two years, but I think it is a nice little tool that already proved useful to me a few times. I also used it as an opportunity to apply full vibe coding in building something a little more complex than simple scripts - applying this to a simple and low risk project was very good to build experience for more challenging ones in the future.

Professional

I also had a quite busy year at work, being involved in a series of initiatives, moving to a new position and winning a few prizes.

Open Source Champion

I have been an Open Source Champion within my company since late 2024. However, the first months were mostly onboarding and ramping up in the topic and the role. In 2025 I was finally able to really make some meaningful contributions in this role. Beyond just Open Source, I have also been heavily involved in the topic of Innersource (applying Open Source concepts and techniques in the context of a private company). As part of this role, I presented the topic at internal developer conferences of the company, organized hackathon-style events and delivered workshops as part of some of our internal development curriculums.

Innoweeks as Dev Lead and MVP

At my company we have a month-long event called Innoweeks, in which we get together with customers to build an MVP that solves a real business project in a burst of short iterations. I had participated in 2019 and 2024, and I did so again in 2025. This year, I was the dev lead for the team, and received the MVP prize for my team at the end of the event.

Won third place prize at Innovation in my location

I work at one of the biggest locations my company has - we have over 3000 full time employees here. Which means we get to do a lot of cool events and initiatives based here. In 2025, the location offered prizes to the people who got involved the most in boosting innovation at the company. The way it worked was that each participation in innovation events or activities would give the participant a certain number of points along the year, and the people who won the most points at the end of the year would win. I was very honored and happy to be in the podium for this, I was the third person who contributed the most among the 3000+ employees we have.

Moved to a new team

I rejoined my company in 2024, but I did so in a team that was really not a good fit for me - it was responsible for a very old monolithic system and still operated with waterfall methodology, both of which I am strongly opposed to. After I concluded the one year that the company demands you stay in a position before applying to another one, I applied to join a new team working in building the platform that the company runs on. While I am enjoying the current technology stack, and our technical scope, much more than the previous one, unfortunately the new team also has several leadership and organization issues that I am trying to improve, little by little. But overall I am much happier now than last year.

Learned Go programming language

With the move to the new team, I also had to pick up the technology stack the team was using. In this case, it was mostly the Go programming language, with Kubernetes as the runtime. I am already quite familiar with Kubernetes, but I had never worked with Go before. So that was an opportunity to learn the language, and add another tool to my toolkit.

Monthly Recap - 2025-12 December

December was a very nice wrap up for the year, in which I could get a lot more done than in previous months. Big changes, lots of catching up, and an overall bump in productivity. While not everything is yet perfect, it certainly helped to improve morale.

Achievements

Back to personal studies

First off, after a long stretch (almost half an year!) without being able to focus on personal studies, I was finally able to get back to it. While I am not entirely back to my normal pace, I made a lot of progress in both books I am working through, and put some time into it most weeks. I am almost finishing Rich Dad, Poor Dad now.

Blog posts

I was also able to set aside some time during the holidays to write several blog posts I had been planning to. These were all based on projects I undertook in the last three months of the year, but that I was too busy to document.

Here they are:

• Projects Curriculum For Learning Programming Languages
• Learning Golang
• Project: Catcher Server

Attending TDC

December is usually the month in which The Developers' Conference (TDC) has its Porto Alegre edition. This year was no different, and fortunately I was once again able to attend it in person. This is the third year in a row that I do this, and it is always one of my favorite times of the year.

Just like last year, this edition was smaller than the normal version of the event. While last year it followed the "AI Summit" format (which I highly dislike), this time it used the "TDC Experience" format, which I found better than the AI one, but still not as good as the full version. The event took place in a different venue from the classic Uniritter campus - while I liked the space (inside the Barra Shopping), I felt it had a less distinct atmosphere. Nevertheless, this time I was able to attend it together with other colleagues from my company and even my team, so it was overall a great and pleasurable experience.

The talks themselves focused more on seeing AI through a more mature and seasoned perspective, keeping the high expectations while starting to recognize and analyse several of the possible pitfalls it offers. I think this shows the "growing up" of the software development ecosystem with regards to this technology, and I only wished my company was at this stage as well - unfortunately, we are only now getting into the "starry-eyed adolescent" phase, a good 3 years behind the whole world.

Downpoints

While there were no major negative points this month, I do feel I am not yet fully back to speed, after all the chaos of changing jobs and moving to a new place. There are several days in which I still get stuck with some minor problem to solve and can do no useful work. Thankfully, these have been getting rarer lately.

Plans for next month

January is usually a month to plan things and set up new routines. The only thing I am mostly convinced I will be focusing on for next year is improving AI skills, so I expect to already get started with some of that. But mostly it will be coming up with a solid plan for 2026.

Monthly Recap - 2025-11 November

After several chaotic months, in November things finally started to settle down a little. While it was still far from my normal, I was able to put some time working on things I wanted to do, and had some nice achievements. Here's a quick summary.

Achievements

Programming language learning projects

For a long time I wanted to create a personal curriculum of projects to develop in order to become proficient in any new programming language. Having gone through the process of learning Go during the second half of this year led me to finally do this. I created a list of ten projects which get progressively more complex and cover most of the essential programming concepts. I have made this personal curriculum open source on Github, and wrote a blog post about it.

Go learning projects started

I immediately started applying the previously mentioned curriculum to my learning of Go. I am slowly working through it, and so far the experience has been really great. I can already feel the benefits, as I feel way more confident developing software in Go now than when I started. I am keeping the projects in private repositories on Github, as for now I do not see the value in making them public - this might change in the future.

Catcher server project

This month I also published another new open source project, catcher-server. It is a simple Python web server that logs to the console information about any request it receives, useful for debugging and validating applications that make outbound requests. The need for something like this came when I was working with microservices and a very new platform which does not have full observability capabilities yet - while I could look for existing alternatives, I thought the scope was perfect to have some fun and vibe code plus open source a simple project. The combination worked pretty well! I have also written a blog post about it.

Downpoints

Personal studies blocked again

While November allowed me to dedicate some time to work on personal projects, it was not yet enough to fully get back with personal studies. It has been a rough year, and I have been blocked on this front for several months already.

Plans for next month

Get back to personal studies

I expect December to continue the trend of things getting less chaotic, and with that to have more time to focus. One of the main things I expect to get back on track is my personal studies habit, as it has suffered tremendously already this year.

Project: Catcher Server

Every now and then, while building and gluing together different pieces of a system, I run into the need for exactly one thing: a tool that will tell me, in the most direct way possible, what a given service is sending out as an HTTP request. No frills, no mystery, no surprises... just give me everything, and don't ask questions.

This is precisely the itch that catcher-server was built to scratch. It's a minimal open source HTTP server designed with only one job in mind: to receive any HTTP request, on any endpoint, and log clearly to the console its method, endpoint, and payload. You throw requests at it, it logs them. That's all there is to it.

Why did I build it?

The motivation came from real needs in my day-to-day work. I was working with a new platform at my job, dealing with limited deployment and observability capabilities. When you are working in such an environment, the quickest way to validate and debug what is happening is often to set things up locally. So, rather than guessing at what my services were really sending, or trying to wade through partial logging and indirect clues, I wanted something that would display the complete truth about outgoing requests, with zero ceremony.

You might reasonably ask why not look into one of the many alternatives out there. The answer is simple: I wanted something I could run locally, that would be mine, with zero licensing or learning curve to think about. Just something I could launch instantly, trust, and forget.

Vibe Coding

There's another reason why I consider this project relevant. It is a great example of a good use for vibe coding. Catcher-server is not a polished product for broad public consumption, but rather a practical and friendly tool, spun up to fulfill a personal/internal need. Projects like these are perfect for a more relaxed, collaborative coding session, especially when working with AI tools to speed up the boring parts. I see vibe coding as an ally for prototypes, utilities, and experiments - fast, fun, and effective in their scope, even if not suited for rigorous software that needs to last forever.

Under The Hood

True to its spirit, catcher-server is built on Python with Flask. That's it: no frameworks or engines beyond what is needed. The idea was to keep everything as simple as possible. No clever tricks or fancy abstractions, just a straight line from incoming HTTP requests to the console log.

Use Cases

While I personally used catcher-server for a microservices project, the intention is broader: it's meant for debugging, testing or observing outgoing HTTP requests from any project. If you want to get the real payload, headers, or query params from your code, without distractions, catcher-server is here for you. It isn't opinionated, and it isn't limited to any domain. Point your requests at it, and it will always catch them!

Conclusion

Catcher-server is the kind of tool I like to have at hand: minimal setup, instant feedback, and the freedom to use and adapt it however I want. It's not going to change the world, but it just might prevent some early gray hairs!

Links

Source code: Github

Learning Golang

This year marked a significant shift in my professional journey as I transitioned to a new team, where Go stands as the primary programming language. As someone who hadn't previously engaged with Go, these past months have been a deeply immersive learning experience. In this post I will briefly share some of my thoughts about this process.

It's particularly pertinent to consider this journey amidst the current, somewhat chaotic, integration of AI into every facet of software development. It offers a valuable opportunity to pause and reflect on what it truly means to acquire new skills in an era where some people claim AI makes all skills obsolete.

My Learning Trajectory 

My approach to learning any new subject, especially a programming language, typically involves a structured path. While often a single video course suffices, I added a few more steps in this case. I began with the official language tutorial, followed by a full video course, and, finally, embarked on a series of personal projects to solidify my understanding.

Official Tutorial 

The initial step involved working through the tutorials on the official Go programming language website. This proved effective for environment setup and familiarizing myself with the core code-build-run cycle. My exploration here was primarily foundational, extending only slightly beyond the "Hello World" scope.

Udemy Course 

After gaining a basic grasp of project bootstrapping, I sought a more in-depth, structured resource. For years, Udemy has been my go-to platform for professional development in software. Thankfully, I found out that Maximilian Schwarzmüller offered a "The Complete Guide" course covering the language. Having completed several of his courses previously, I had high confidence in the quality, and I wasn't disappointed. Though perhaps less comprehensive than some of his other offerings, it provided a robust foundation in the language's fundamental concepts and constructs.

Projects 

While a thorough video course usually equips me sufficiently, in this instance, I felt the need for more. This followed from a confluence of factors: Go not being my immediate choice for personal applications, its less-than-intuitive aspects, and the workplace emphasis on AI-generated code over manual development. All of this motivated me to deepen my learning through practical application.

That is when I created a list of 10 application projects to develop in the language, which would progressively make me exercise more and more complex concepts. I have wanted to create such a "curriculum" for a long time now, so this was the perfect opportunity to do so. I tried to frame the projects in a way that could be used for almost any language, and put the list in a public Github repository. I also wrote a blog post about it.

Challenges 

AI

Artificial Intelligence undeniably offers substantial productivity gains in our field. However, the prevailing directive from upper management to uncritically deploy AI-generated code introduces significant challenges, particularly concerning knowledge acquisition and retention.

When your only incentive is to push out as much code as possible, as quickly as possible, it is easy to not put the effort (and time) into learning new things. If it seems to mostly work most of the times for the things you already know, you end up assuming it will also work when you do not know enough to make a judgement on what it is producing. But the catch here is in the "most" and "mostly" part: there are very significant and problematic cases in which you need to use your judgement to override something the AI made. If you are using AI to ship something in a language you do not know, you are not able to do that.

My approach has been to use AI as dictated while at work, and while creating things for personal use that I already know deeply how they work. But to avoid as much as possible relying on it while I am learning something new - I try to write all new code by myself, researching when I do not know how to do something, and only resorting to generated code when I am at an absolute loss. I then use generative AI models to analyse and evaluate my final implementation, asking it to give tips about best practices and where I could improve. I believe this approach not only preserves the learning benefits of a pre-AI era but also augments them, maximizing the value derived from this new technology. It is a shame that it is so hard to communicate this to the highest level of management at companies, these days.

Overlapping 

Another challenge I found is the fact that I do not see myself using Go for my personal projects. The language seems to overlap a lot with other languages (mostly Java, also some Python and JavaScript) that I already master and that work perfectly fine for me. I feel like I have to put conscious effort to choose Go as the main language for any new project I might start, and I am not sure how sustainable this is in the long run.

Thoughts So Far 

Overall, I find Go a pleasant language to work with and considerably simpler to learn than I anticipated. While it is definitely not my favorite language (not by a long shot), and I don't foresee continued investment in it beyond my current professional requirements, it effectively serves its purpose, generating optimized executables with minimal overhead.

Error Handling Code Everywhere

One aspect of the language that I find slightly weird is how much error handling code it needs. I do not know if this is just a skill/experience issue, but having seen code for fairly seasoned Go developers I am inclined to conclude that it really is intrinsic to the language. It feels like half of every Go source code file I read consists of "if err != nil".

While I do appreciate the safety that this might bring to programs, it still makes the code feel slightly uglier than in other languages, to me.

Dependency management

The only other point that I find disconcerting is Go's dependency management mechanism. Coming from a Java and JavaScript background, I am used to having solid, unambiguous and strict manners of declaring and managing your dependencies. Go's approach feels very idiosyncratic and flaky, and at least once per month I have very experienced Go developers telling me to run some arcane command to "just fix your vendoring" without being able to explain what the command is actually doing.

Projects Curriculum For Learning Programming Languages

While learning the Go programming language, I did something I have been wanting to do for a long time and created a short "curriculum" of projects to develop when learning a new language. The idea of this curriculum is to progressively expand one's understanding of how to do several common programming tasks in the desired language, and should be agnostic enough to work for almost any language.

I made this list public in a Github repository, and in this post I will briefly describe the reasoning behind it and introduce the initial set of projects.

Reasoning 

For many developers, embracing new programming languages is an intrinsic part of the professional journey. While some may comfortably settle into a familiar stack, the evolving technological landscape often rewards those who frequently broaden their linguistic horizons.

While it is possible to become reasonably proficient by fumbling your way around, especially if you already know a very similar language, the results are better when you apply deliberate effort to the learning journey. A mixture of understanding the concepts and getting your hands dirty creating something with the language works the best. This curriculum covers only the second part, you should first have taken a short course or read the basic tutorials of the language to get the concepts and theory.

My initial list has 10 projects, starting from the simplest behavior possible (logging some text to the console) and ending with an application to fully manage a resource. Along the way, it exercises programming constructs, interaction with the filesystem and exposing a service through HTTP requests.

By following this sequence and implementing each project, one can acquire a robust intuition for tackling the vast majority of tasks encountered in any language. This gives the confidence to then use the new language effectively for any project requirement.

A Note On Perspective 

This list is heavily shaped by my own experience, as someone who has mostly developed for the cloud and desktop, and with a backend focus. It might not cover several things that are important for frontend, mobile and AI/ML development.

The Projects

I created a public Github repository with the list of projects, and I intend to enrich their descriptions and refine the list as insights emerge from using it.

Here is the initial list, with a short description of what each project contributes:

1. Hello World

Classic first program in any language, just print out the message "Hello World" to the console. This makes you understand how to set up, build and run a project in this language.

2. Current day and time greeting

Print to the console a short greeting informing the current day and time. This allows you to learn how to use the standard library of the language, move away from hardcoded values to start using variables, and string formatting.

3. Guess the number game (CLI)

Simple game in which the application chooses a number between 1 and 100 and the user has to guess it in 7 or less attempts. This introduces handling user input, conditionals and loops.

4. Note taking (CLI, local filesystem)

Start a CLI that reads user input until a certain pattern is entered (such as /exit or similar), then saves all the text entered to a file named with the current date and time to a standard folder - optionally, offer a "view" mode in which the notes already saved are displayed. Focus here is learning how to interact with the filesystem and an initial mode of persistence.

5. To-do app (CLI, database/sqlite)

Application that allows users to create tasks and mark them as done from the terminal. Learn how to interact with databases in the language, a good first option usually being sqlite.

6. Hello World (GUI)

Same as the first project, but now displaying "Hello World" in a graphical interface. This project makes you learn the very basics of creating an UI in the language. Depending on the language, this (and the next two projects) might not be relevant, or be redundant - in a language usually applied in a stack that is graphical by nature, the CLI version of these projects will already teach how to create graphical interfaces.

7. Guess the number game (GUI)

Same as the third project, but now with a graphical interface. Most important learnings here being how to receiver user input in a GUI and how your custom logic interacts with the UI rendering loop (often requires basic multithreading understanding). Depending on the language, might not be relevant or be redundant.

8. To-do app (GUI)

Same as the fifth project, but now with a more sophisticated user experience to edit tasks. The main benefit I see for this project is to give a holistic understanding of a complex end-to-end scenario, going from an user interface all the way to a database and back - after finishing this project it should feel like you can comfortably use this language to solve real-world problems in a user-friendly way.

9. Quotes app (REST)

Web application that returns famous quotes from certain people (can be hardcoded) through HTTP requests, preferably applying the read-only parts of REST. This project allows you to learn how to run a web server in this language, and use your custom logic to respond to requests. I do not see the need to also implement the client part for this project, but frontend-focused developers might see the benefit.

10. Album manager app (REST)

Web application that fully manage an "album" resource - allowing the creation, edition, listing and viewing of musical albums. The challenge with this project is implementing the full management of a resource, including its nested entities (an Album has an Artist, a list of Musics, etc.) and database persistence. It serves as a capstone - if you are able to do this, you should feel confident to say you are proficient in the language. Most entry-level jobs would have very similar (if not lesser) expectations, and if you reached this stage it should be very easy for you to go after any subsequent knowledge as the need arises.