Kun Chen

Where they publish

• Newsletter Kun's Field Notes Field notes on agentic engineering and solo building. Has a feed.

  Practical essays on building software with coding agents, and on leaving a big-tech job to build solo. Over 4,000 subscribers.

  Open blog.kunchenguid.com

  Recent

  • I distilled myself, and you should too 9 Sept 2026 You can also distill others. Full guide below.
  • Your AGENTS.md is a Neural Net 23 Aug 2026 And here’s how to properly train it with gradient descent
  • Kun's Pi Agent Config 1 Aug 2026 Minimal, practical, and elegant

  Show 8 more

  • Evaluating the Effectiveness of Programming Languages for Agents 10 Jun 2026 And how to pick the best one
  • Everyone Should Have an OPINIONS.md 5 May 2026 A game changer that wasn't possible without agents
  • The Month After Leaving Big Tech 4 May 2026 What it feels like to quit your job and go solo
  • How I built a starry night in TUI 28 Apr 2026 Twinkling stars, a moon strip, with a hand-rolled ANSI diff renderer
  • Org-Bench: Let’s Simulate the Org Charts Meme with Agents and See Who Wins 22 Apr 2026 And prepare to have your mind blown.
  • Making a Polished TUI Demo Video Without a Video Editor 21 Apr 2026 Recording, mocking, and polishing a terminal demo with off-the-shelf tools
  • How I Built a Reproducible Mac Setup with Nix 5 Apr 2026 A pragmatic setup that lets me get any new Mac into working shape in seconds instead of spending a weekend reinstalling everything.
  • Zero to One — Handbook for Entrepreneurial Engineers 2 Apr 2026 Ever since I was a teenager, my coding adventure has always centered around one question - I have great ideas. How do I turn them into reality? This article aims to give some answers to this question.

  Link verified 8 Sept 2026. Recent items update automatically from the channel.

• x.com @kunchenguid Where most of their writing on agentic engineering actually happens.

  Short posts and threads on coding agents, developer tooling and what building solo with AI looks like day to day. Their most active channel.

  Open x.com

  Recent

  • be very careful if you find yourself simply passing messages to and from your agents e.g. people ask you a question on slack, and you simply ask an agent and pass its response back - it should be obvious that your job can be automated in that case instead, you should try and build an agent (or sometimes just skills) that can reliably answer similar questions moving forward and remove yourself from the loop your value then becomes improving said agents and skills, and your impact can easily scale and manifest even when you sleep don’t be automated. be the automator 22 Oct 2026
  • see - if eMudhra was chinese, they would never have picked number 4 as their private key 22 Oct 2026
  • poll result on why people haven't adopted personal agents i suspect all the other 3 reasons are solvable, but looks like most people simply don't see real need for having an agent handle their personal life is consumer-facing personal agent all a bubble? 21 Oct 2026

  Show 17 more

  • it’s interesting how anthropic has the best model yet slowest to market with a personal agent that shows no clear differentiation why do you think that’s the case? 21 Oct 2026
  • interesting read walking through a practical example of building a reasonably polished app with ~1hr of human time not sure how i feel about “shotgun prompting” though! what i like to do is “ramble prompting” with voice 😄 21 Oct 2026
  • Derek was my former manager, VP of eng at both MSFT and Atlassian one of the most technical, forward thinking, hands-on eng leaders I’ve had the pleasure to work with great to see him sharing on X and definitely recommend as a high quality connection! 21 Oct 2026
  • wait.. what? permanent prompt caching for subscription users i suspect it’s not truly keeping the cache forever, but instead they know the probability of resuming an old conversation is close to zero so they’ll just eat the pricing difference when it happens 21 Oct 2026
  • interesting data from my most recent 2000 real tasks all of these tasks' outcome got accepted by me, so consider them all successful. when a model didn't give me good results, i would get it to do more iterations until it succeeded the main caveat is the "plan" bucket - if i didn't like a model's plan, i would sometimes just abandon it and it wouldn't show up here. sometimes i also explicitly ask astra / fable for difficult plans. so take the plan row with a grain of salt. the other rows are mostly randomized and fair reasoning effort was set at xhigh for plan, medium for others explaining th… 21 Oct 2026
  • i just discovered my 9y old son and his friends all think AI = low effort = bad they can tell a picture is AI generated, and they don't care how good it looks - "that's just AI" they prefer to hand-draw much worse looking cards to each other and they love it 20 Oct 2026
  • part 4 of "software is taking off" through recent discussions i realized many people saying "software is dead" were actually thinking about software engineering as a profession so.. is software engineering dead? when i was a kid, my mom was an accountant. when i was doing my homework in the evenings, I would hear the sound of her using abacus. it was very loud and noisy over the years, the sound of pushing abacus became punching calculators, then typing on keyboards, and eventually making phone calls. she just retired a few years ago, as a director of an accounting team if you thought of the… 20 Oct 2026
  • more and more products are straight blocking access from cloud data centers because they are 99%+ agents at this rate, owning a local machine with a residential IP might become one of the things that prove you are a human 20 Oct 2026
  • something i’m very curious about if you tried personal agents but it didn’t stick with you, what was the main reason? (comment if it’s some other reasons) 20 Oct 2026
  • i got slightly surprised by this so sharing in case it’s helpful - after unifying your X subscription, your Grok Bot is no longer running on its own quota like before! it’s now sharing the same weekly quota as coding this is actually a good thing - previously the grok bot quota was a bit tight and now it draws from the larger pool - but you’ll need to plan for this or otherwise may end up like me and used up all the quota for coding and got surprised why grok bot stopped working my plan is to start using grok bot as the ONLY interface for my X subscription quota. i will no longer use my X sub… 19 Oct 2026
  • sharing a very high value loop i run everyday at 3am "audit my development work in the last 24h, identify bottlenecks that slowed down my velocity, and propose improvements" it feels great to see your work gets smoother every day 19 Oct 2026
  • ironically, LLMs themselves have NOT internalized the bitter lesson when using LLMs to write LLM powered systems, they keep building rigid knowledge with deterministic code, and don’t know where to cut the line of writing prompts instead 19 Oct 2026
  • agents just enabled a new type of work life balance work - kick off 10 agents life - get coffee and breakfast work - come back to answer their questions, make decisions, and kick off more agents life - workout work - come back... life - play video games 19 Oct 2026
  • a lot of the shortcomings we are seeing with coding agents today ultimately boil down to limitations in post training why agents don’t write good tests by default? why do they spit out a ton of useless comments? why do vibe coded codebases all turn into a mess without human steering and intervention? because in current RLVR pipelines, we reward task resolution. as long as the agents wrote code that could pass predefined hidden tests, that’s a success whether the architecture is clean, whether the code is easy to maintain and evolve, whether the comments are actually helpful in future work, wh… 18 Oct 2026
  • this is a great write up. i’ve answered many people similarly - don’t fall in love with tools and activities. the world changes and they go away put your passion on solving problems using whatever tools that are the most effective and you’ll never be “replaced” 18 Oct 2026
  • part 3 of "software is taking off" there's a profound misconception that led to people saying "software is dead": they think software = code if software = code, and anyone's agent can write said code as needed, then of course it'll be hard to sell software but most of the valuable software we use today is not just a pile of code! good software is often the glue behind a network. your agent can vibe code a clone of X, instagram, uber all you want - but you won't even use it yourself, because the people you care about aren't there good software is often the tip of an infrastructure iceberg. can… 17 Oct 2026
  • interesting write-up from ceo of e2b but let me rephrase the title honestly for you - "Your sandboxes are dead. My sandboxes are great!" 17 Oct 2026

  Link verified 8 Sept 2026. Recent items update automatically from the channel.

• YouTube Kun Chen Screen-recorded walkthroughs of their agentic dev setup. Has a feed.

  Videos on their agentic engineering workflow and dev environment, aimed at other developers trying to build with coding agents.

  Open youtube.com

  Recent

  • High Throughput Agentic Engineering with Kun 13 Sept 2026
  • L8 Principal Building a Full Stack App with Agentic Engineering 27 Jul 2026
  • Dad and Son Vibe Code an RPG Game 13 Jul 2026

  Show 12 more

  • Kun's Agentic Dev Environment From Scratch 5 Jul 2026
  • L8 Principal's Agentic Engineering Workflow 20 Jun 2026
  • Short How small teams with AI move fast 6 Jun 2026
  • Short The circular ai money game 5 Jun 2026
  • Short Why middle management is getting hit 5 Jun 2026
  • Short Interest rate and layoffs 5 Jun 2026
  • Short LLM tokens aren't productivity 4 Jun 2026
  • ex-Meta Principal Explains the AI Token Game 3 Jun 2026
  • AI Tech Layoffs Explained by ex-Meta Principal Engineer 21 May 2026
  • First Month After Quitting My Big Tech Job as L8 Principal 17 May 2026
  • Don't Get Laid Off by AI (From a Lead Principal Engineer) 22 Oct 2023
  • Short Do you understand diffusion of responsibility? 26 Feb 2023

  Link verified 8 Sept 2026. Recent items update automatically from the channel.

• GitHub kunchenguid Their code, including /kun and other agent-tooling projects.

  Seventy-six public repositories, mostly small tools for working with coding agents -- CLIs, dotfiles, agent configs.

  Open github.com

  Recent

  • eddies-wallet — A virtual allowance and financial learning app for families. 22 Oct 2026
  • firstmate — Talk to one agent. Ship with a crew. 22 Oct 2026
  • no-mistakes — git push no-mistakes 22 Oct 2026

  Show 17 more

  • baby-menu — A menu bar app that can become anything you ask it to be. 22 Oct 2026
  • lavish-axi — HTML is the new markdown. Lavish is the new editor for your HTML artifacts. 22 Oct 2026
  • quota-axi — Allow your agents to see your LLM subscription quota windows. 22 Oct 2026
  • kun — Think and build like a principal engineer. Leverage Kun's experience, knowledge, tools, workflows, and skills to help you get shit done. 22 Oct 2026
  • homebrew-tap 22 Oct 2026
  • pi-launcher — A signed macOS launcher for your Pi agent. 22 Oct 2026
  • axi — Design principles for agent ergonomics. Higher accuracy with lower token cost than both MCP and regular CLI. 21 Oct 2026
  • backpass — You don't write AGENTS.md. You train it with gradient descent. 21 Oct 2026
  • treehouse — Manage worktrees without managing worktrees. 21 Oct 2026
  • gh-axi — GitHub CLI for agents — designed with AXI (Agent eXperience Interface). 18 Oct 2026
  • chrome-devtools-axi — The most agent-ergonomic browser automation 17 Oct 2026
  • New repoinfinitary-evidence-test-public — Harmless examples for Infinitary pull request attachment verification. 16 Oct 2026
  • gh-axi-adhoc-sandbox — Fixed sandbox for gh-axi adhoc e2e (no createRepository in the daily path) 15 Oct 2026
  • compact-adviser — "Work appears completed or recorded. Run /compact to save tokens." 9 Oct 2026
  • gnhf — Before I go to bed, I tell my agents: good night, have fun 3 Oct 2026
  • autopreso — Realtime speech to presentation. Let the whiteboard whiteboard itself. 25 Sept 2026
  • tasks-axi — Agent-ergonomic CLI for task/backlog management with pluggable backends (markdown, sqlite, remote trackers) 22 Sept 2026

  Link verified 8 Sept 2026. Recent items update automatically from the channel.