Nelson (@az8TLab) header
Nelson (@az8TLab) profile picture

"az8T lab" does AI-assisted, research-informed software engineering

Joined March 2026
Photo by Nelson (@az8TLab)Photo by Nelson (@az8TLab)Photo by Nelson (@az8TLab)Photo by Nelson (@az8TLab)Photo by Nelson (@az8TLab)
What does #buildinpublic mean ? It's basically a popular public-faced journaling initiative focusing on relevant development phases of (startup) projects founders think worth sharing traces of. The past months, I kept pointlessly posting about developing mine : until today
3
2
8
264
countless days later > after having started 'building in public' 🖼️ here's another "boring" snapshots from Contour's latest update : 1/5 < Home > page content restructured > in order to align to critical improvements linked to the related items shown 2/5 new curated blog articles (yet, oldest are shown) 3 to 4/5 the platform gravitates heavily around social networking with like-minded individuals, defining why the < Community > dimension of Contour isn't just an aspect, just as its opt-in collaborative @openscience framework 5/5 what "code learning and training (social-network) platform informed by brain science" truly means (...) today added one less in my life, busy delivering something as deep. side note: The platform's user interface will be completely transformed upon release! The pre-release will optionally remain remembered as that (for registered users), however, there's still no fixed release date due to the nature of the remaining work to complete alone featuring AI agents. Thank you very much @X for enabling builders like me to introduce their content and gather around similar people from around the #world 👋
2
3
51
building in public is not necessarily worth trying to, nor is the "vibe coding" hype, nonetheless, 🫨 I've spent a while experimenting with AI-assisted coding , until finally understanding that : Since my contents ephemeral introduction at @X, a handful users dared to like and share my posts, I'd like to thank them again, especially who followed so far. One of them even commented, curious to learn my worse learned lesson ATM (...) it's what inspired this post: my take on a useful lesson in resume, isn’t to “add precise scripts” as the post "fixing bugs" nearly alluded to. It’s instead a repeatable way to reason about engineering work: ➡️ identify a failure, ➡️ find where the existing safeguards do or don’t catch it, ➡️ add the smallest durable protection,➡️ then test that protection against the failure. Much like a mindset put into practice as a solo builder, the more my repo became larger and complicated to follow, the more I cumulated mistakes after errors, yet, I still had to find a way to prevent this from perpetuating itself. I kept investigating, iterating with coding agents, effectively working my way out of this failing setting, and despite no new identifiable internal error being surfaced by the "compiler", one day, I decided to ask my coding assistant to thoroughly review an expert blog article about optimizing codebases foundations. Surprisingly, to this day, the assistant still estimate that the strongest foundation pre-existed the review: likewise, the project reached a phase where it didn’t rely only on telling qualified programmers or coding agents what to do. What instead has been elaborated is a map of where code lives, project-specific instructions, and automated checks in CI. Those checks can catch problems even when an agent or developer forgets a rule. This particular combination of guidance plus automatic enforcement (safeguards) is believed to be stronger than a mere "standardized checklist" by itself. From there, I drove the next round (manual Tesla car mode, lol, how can't i crash w/o licence) by looking for ways mistakes could whatsoever get through, finding the blog articles in question before debating about them with my agents, as a result, we agreed upon adding: ➡️ Checks for pages not connected to the app, also for duplicate routes or components; ➡️ clearer instructions to find and update existing code before creating a parallel version; ➡️ tests to catch stale pages; ➡️ and a command to locate all files related to a feature. This matters because agents and people can both misunderstand a large codebase or miss an existing implementation. General-purpose AI coding tools > don’t automatically know a project’s specific rules or build lasting checks for them, because this remains at every shipping author's responsibility; someone has to identify risks and make protection part of the project. I by the way also favored targeted changes over adding process for its own sake: the existing CI could enforce the new checks, so extra tooling like a separate pre-commit system wasn’t needed, anyway.
3
5
300
Nelson retweeted
please stop putting dynamic context on line 1 of your system prompt!!! prompt caching reads top down, so you invalidate the cache on every single turn. keep static instructions at the top and shove volatile state to the very end. saves like 90% on api costs
1
1
2
91
First of all, thanks people for helping me reach "+80 followers", I appreciate the milestone, and remain open to connections! 🍾🎉 Now ladies and gentlemens, in a world premiere, Contour's latest feature: < Code N-Back > Closely inspired from the original N-back, a long-used laboratory task where people reliably get better at it with practice, studies disagree on whether that practice improves anything beyond tasks like it, and nobody so far, Contour included, is known to have studied an N-back made of lines of code. What we practise here basically is > "telling very similar lines of code apart" while holding a few in mind. Each round we hand in is saved to its own record, shown per level on the Dashboard. A round counts as practice for the day, and so for users streak, when they catch at least 4 of its 6 matches and press Match on no more than 3 other lines. If a look-alike catches users out (made to gently "fool/stress-test" users memory confidence after each incremental training session), the snippet it came from comes back in Review the next day as a recall card. The lines follow users practice progression depth tier and start from snippets you have already rebuilt in < the Reorder puzzle >, which will be introduced in the next post. It's an experimental cognitive task: nothing here biases users sensitive calibration measures, their depth or their (structured) course progress.
2
84
#buildinpublic < the Reorder code puzzle > is part of Contour's latest 'code perception training' tasks. Rules are simple: The lines of a short snippet are shuffled and users put them back in order by dragging a line by its handle <> using the arrow keys on the handle <> or pressing the up and down buttons. After each check; users are told which lines are in the right place, and you can try as often as you like. With the memory option on, the code is shown first and then hidden, so users rebuild it from memory; above the "Beginner level" that option also mixes in one or two look-alike lines that were never in the code (..) for users to leave out.🤓 Its a lighter step than predicting code from scratch, so the 'Explore' (tab) offers it > once code is on screen note: my bad @X algorithms, I deleted this post before editing and reposting it in less than 24h; please, don't shadowban me for "AI slop".
1
24
< Predict >🎯Contour's beloved training task. For users with pre-existing programming experience who want to stay atop of their skill: a prediction is typed (sped up for the video), then the compare view shows where it differed from the real code, then the “Feedback on this round” step. note: This is the surface description of the feature. The calibration engine and so forth aren't emphasized, yet, despite bearing close dependency to this feature when users use it with registered accounts.
1
7
🚨 Paying $20 Pro, $100 Max, and $200 Ultra coders: update to Claude Code v2.1.326 right now. → /update-config overhead drops 86% from 93K to 13K tokens → Fixes stale settings keeping auto mode's usage-billed classifier active → Stops session recaps firing on billed turns One weekly quota catch: opusplan compaction now runs on Opus, so compaction itself costs more.
45
26
2
805
96,149
🏗️building "Contour" in public has made something clearer : fixing a bug 🔎starts with finding the code that actually owns the feature. It’s figuring out which code > actually owns the feature you’re trying to change (...) I kept finding myself in the same loop, so, anecdotically, I applied a custom repo tool: npm run map:feature <keyword>. It searches client/, server/, and shared/, then groups matching files by directory. The idea truly came off increased codebase complexity, which routinely triggered repeated repair loops; with changes that seemed not to take effect, or with the risk of editing an old or duplicate implementation instead of the active one. To be precise, this is not a visual dependency map! Right now, it just automates a faster way to answer: “Where does this feature actually appear in the source ?” That alone has been useful👍
🤖 Made with AI
1
4
130
There's many code search and architecture tools accessible. What I am exploring is < a repo-specific map > that would let a developer (or an agent) see a feature’s verified connections and likely change impact before editing. The current command only finds matching files, but the thing I’m more interested in exploring is what comes next. A feature-oriented map that can show the evidence behind a relationship: UI → route → server logic → shared contract → data → tests …and let you inspect those connections before changing anything. This may be useful for qualified humans, and potentially very useful for coding agents too.
4
45