Franti Huamán (@frantisan) header
Franti Huamán (@frantisan) profile picture

I make things

Lima, Perú
Joined April 2007
Photo by Franti Huamán (@frantisan)Photo by Franti Huamán (@frantisan)Photo by Franti Huamán (@frantisan)Photo by Franti Huamán (@frantisan)Photo by Franti Huamán (@frantisan)Photo by Franti Huamán (@frantisan)Photo by Franti Huamán (@frantisan)Photo by Franti Huamán (@frantisan)Photo by Franti Huamán (@frantisan)Photo by Franti Huamán (@frantisan)
Franti Huamán retweeted
Making the most AI pilled company is the whole game: 1. make a second brain. one folder of markdown files on how you think, write and decide (obsidian) 2. talk to it. voice notes all day (wispr), and an agent files every fact, story and decision 3. make a company brain. customers, calls, numbers, pricing, playbooks, past decisions and why you made them 4. record every call and meeting (granola). the transcripts go straight into the brain 5. keep a facts file. true things about you and the company that agents are allowed to say. this kills made-up claims 6. keep a voice file. your 50 best posts, 20 you hate, and the words you never use 7. put all of it in git (github) so every change has a history 8. write one instruction file at the top (CLAUDE.md or AGENTS.md). read these files before any task, never overwrite, always date 9. give agents memory across sessions so they stop starting from zero (claude-mem, mem0) 10. pipe every data source into one warehouse your agents can query (airbyte → clickhouse). ads, analytics, CRM, payments 11. feed it data nobody else has. it's the only part a competitor can't download the skills 12. don't start from zero. install the good ones first (anthropics/skills, obra/superpowers, mattpocock/skills, addyosmani/agent-skills) 13. grab the marketing ones too (coreyhaines31/marketingskills, cody schneider's graphed skills for static ads and UGC, boringmarketing dot com skills) 14. map every workflow in the company and rank them by money made or saved 15. do each one once while talking out loud, and record it 16. have an agent turn the recording into a skill. when to use it, the steps, the checks, the mistakes to avoid 17. one skill per job. small and boring beats one giant prompt 18. connect your tools with MCPs so agents can act and not only advise (gmail, slack, stripe, linear, notion, posthog, supabase) 19. give agents a browser (browser-use, vercel agent-browser, claude in chrome) 20. give agents a computer of their own for the tools with no API (vercel agent-desktop, orgo) 21. give your best skills away in public. it's the new lead magnet the agents 22. run an orchestrator that never turns off (grok bot, openclaw, hermes). it manages one agent per project, and each of those runs its own sub-agents 23. use coding agents for the building (claude code, codex, cursor, t3, antigravity) 24. wrap them in a harness so they plan, test and remember (ECC, superpowers) 25. manage the whole fleet in one place (paperclip). every agent gets a job, a budget and a log 26. put the skills on triggers (n8n, scheduled tasks). daily, weekly, on every new lead, on every cancellation 27. route your models (openrouter). the expensive one plans and checks (fable 5.2, gemini 4 carbon), the cheap ones do the volume 28. cut the token bill. shorter outputs, smaller tool results (caveman) 29. run a local model for the data that can't leave your machine (gemma 4) 30. track cost per job. if a job costs more than it earns, fix it or kill it the factory 31. build the line. spec agent → builder agents in parallel (git worktrees) → test agent → reviewer agent → deploy (vercel, railway) 32. design goes through the same line (paper MCP), and a skill strips out anything that looks AI made (unslop) 33. every annoying task in the company becomes an internal tool by the end of the day 34. every customer request becomes a pull request before a human reads it (tstack for the PR workflow) 35. reviewer agents with a named bar. "would the best team in the world ship this?" reject until the answer is yes 36. keep 50 real cases with the right answer. rerun them every time a new model drops and switch to the winner 37. humans approve, own the outcome and talk to customers. that's the 10% you keep the loop 38. every finished job writes back to the brain. what worked, what failed, what to stop doing 39. support tickets, analytics and social comments flow in every night 40. every friday an agent rewrites the playbooks from the week's results, and you approve the diff 41. every month, rank everything by profit per human hour. kill one thing and double one thing the growth 42. research with agents before you spend a dollar (perplexity API, last30days skill) 43. outbound runs itself. find the leads, enrich, verify, send (apollo, million verifier, instantly, phantombuster) 44. send prospects finished work in place of a pitch 45. ads run on a loop. an agent writes the creative, publishes through the facebook ads API, kills the losers and scales the winners 46. agents make the creative too. images (nano banana), video (heygen, fal), voice (elevenlabs), music (lyria 3.5, suno) 47. turn every finished job into content. the story, the number, the prompt 48. every customer makes the brain smarter for the next one. that's your network effect 49. once it works, point it at a new niche. same agents, new context The models are the same for everyone but your context is the only part that's yours. Acquire as much of it as you can, as fast as you can. Build loops like this. This is the whole game, happy playing.
507
345
118
5,223
578,233
Franti Huamán retweeted
I got this cold email today about what I'd teach kids interested in web development and programming. I figured I'd share my full response here in case it helps others: — Learning to create software today is a glass half full / half empty situation. You can be optimistic or pessimistic. It is strange and transformative that we no longer write most code by hand. AI has completely changed how software is built. I expect this to change even more dramatically in the coming years, as entirely new programming languages¹ are invented² and adopted. One person might look at this and be pessimistic: what will these computer scientists and programmers do, as AI continues to become superhuman in its intelligence? But the wiser of the bunch will realize there is much to be optimistic about. Those with the agency³ to create and explore their wildest ideas have unlimited power. There has quite frankly never been a better time in the history of humanity to have good ideas⁴. So my advice for those building at summer camps is simple. You have to hone and craft your "idea machine". You are going to have lots of bad ideas, but you'll get better at coming up with ideas and refining your taste so you can recognize and act on great ideas sooner. People at summer camps will spend less time reading CS tutorials and more time thinking about the fun or interesting things they want to exist in the world. My favorite way of teaching and getting people interested in software is to first help them build something they are excited about. When they hit roadblocks that require a deeper understanding of a CS concept or something related to web development, only then do we take the time to explain what it is and how it solves their problem. Starting this way, at least for me, seems to get people hooked faster than needing hours and hours of prereqs. There's more desire to spend time learning the fundamentals after having the "aha!" moment. It's worth checking out some skills⁵ designed to help encode the best practices for teaching and then plop that into a coding agent or your AI tool of choice and give it a task: teach me about how databases work (or similar). It's pretty great. It's also worth remembering that AI models today are the worst they will ever be. You need to learn how to be even more ambitious⁶ with what you ask them. Good luck! — ¹ nitter.gq/poteto/status/21198244… ² bend-lang.com ³ neelnanda.io/blog/44-agency ⁴ are.na/editorial/notes-on-ta… ⁵ github.com/mattpocock/skills… ⁶ felixrieseberg.com/how-to-be…
we are entering a renaissance in programming language and runtime research, and a golden age of software testing and verification it’s time to rewrite all software
76
93
17
1,326
67,291
Franti Huamán retweeted
I've changed how I work over the last few weeks. I now have one lead agent for each area of focus, running all the time, and a chief of staff agent that oversees them. Each lead manages its own sub-agents that write code, test it, chase reviews, and coordinate with team members. Everything I need to decide or review comes into one prioritized queue, a simple local web app. Each product review includes screenshots and a video demo of the feature. I clear the queue in batches, mostly by voice and keyboard shortcuts. The leads also bring back ideas I hadn't considered. Working from one queue, instead of switching between dozens of chats, has cut a lot of mental overhead. The system keeps learning my preferences and distilling my judgment into a "Brian brain," so its recommendations and first drafts get better before they reach me. The goal is fewer corrections per change. Every change still goes through the same human review and security checks. It is eliminating tasks, not human judgment. What an exciting time to push the frontier of productivity, especially as we build the economy for agents (agentic finance). We should all keep pushing in this direction.
874
480
434
10,299
1,661,594
Franti Huamán retweeted
Your coding agents should have a manager. That manager should be a coding agent. We’ve been quietly working this way since February. Here’s the setup we’ve arrived at. 1) Give each project a lead agent. It keeps the plan, remembers decisions, delegates work and knows what’s stuck. 2) Let it start other agents for specific tasks. They work in parallel, bring questions to the lead and report back. 3) Have agents show what they made. Screenshots, live pages, different options and what changed since the last round. 4) Put everything that needs your judgment in one queue. Point at what needs changing, give feedback or approve the work. Your response goes back to the agent. 5) Keep feedback open until it’s addressed. Test changes before they land, get a second opinion on merges and approve anything risky. I spend far more time looking at actual work now. The agents keep track of the rest.
I've changed how I work over the last few weeks. I now have one lead agent for each area of focus, running all the time, and a chief of staff agent that oversees them. Each lead manages its own sub-agents that write code, test it, chase reviews, and coordinate with team members. Everything I need to decide or review comes into one prioritized queue, a simple local web app. Each product review includes screenshots and a video demo of the feature. I clear the queue in batches, mostly by voice and keyboard shortcuts. The leads also bring back ideas I hadn't considered. Working from one queue, instead of switching between dozens of chats, has cut a lot of mental overhead. The system keeps learning my preferences and distilling my judgment into a "Brian brain," so its recommendations and first drafts get better before they reach me. The goal is fewer corrections per change. Every change still goes through the same human review and security checks. It is eliminating tasks, not human judgment. What an exciting time to push the frontier of productivity, especially as we build the economy for agents (agentic finance). We should all keep pushing in this direction.
118
22
11
395
49,038
Franti Huamán retweeted
The head of the philosophy department at Williams College downplays the pedagogical value of writing: “What if we are mistaken in treating writing as the highest cultivation of thought? The evidence that supports this belief is thin at best. Writing can be useful cognitive scaffolding for memory and self-regulated learning, but the notion that it is the best process for developing thinking skills is a fairly recent idea, traceable to the 1970s writing-across-the-curriculum movement.”
258
210
375
1,314
2,170,143
Franti Huamán retweeted
Cómo se puede contar algo tan humano de una manera tan guapa…
89
2,300
317
10,287
1,031,044
Franti Huamán retweeted
Noah's Ark resting place '100% confirmed' after 4,300 years as astonishing 'man-made' structure is detected buried deep underground trib.al/Swpjv1F
Readers added context they thought people might want to know
The '100%' is the Noah's Ark Scans team's own confidence in its reading of radar anomalies. Core drilling at Durupınar only began this week; lab results are expected in winter, and most geologists still classify the site as a natural rock formation. internewscast.com/news/noahs-ark… globenewswire.com/news-release/2…
422
2,255
459
14,484
4,618,774
🇺🇸🎓 ¡Te esperamos en la Feria EducationUSA 2026! Si estás pensando en estudiar en Estados Unidos, esta es tu oportunidad. 📅 14 de septiembre 🕠 5:30 p. m. – 8:30 p. m. 📌 Country Club Lima Hotel – San Isidro 🎟️ Ingreso gratuito previa inscripción: eventbrite.com/e/feria-educa…
41
147
6
630
50,791
Franti Huamán retweeted
Game theory explains why working harder inside a broken system is always the worst response to that system. That's because a system is never truly broken. It's just producing exactly the outcomes its own incentive structures were designed to produce, whether intentional or not. Working harder inside this system increases your output in the payoff matrix, but it simply won't change the actual structure of the system's matrix. Thus, the correct response is not more effort. Instead, you must aim to identify whose interests the current structure serves and position yourself in favor of those interests rather than against them. Change the game, or play the game that is actually being played. Either way, you must stop optimizing for the game you wish it to be and start acting realistically.
73
918
62
6,423
214,543
“When entering a marriage, one should ask the question: do you think you will be able to have good conversations with this woman right into old age? Everything else in marriage is transitory, but most of the time in interaction is spent in conversation.” — Friedrich Nietzsche
13
55
11
310
16,272
Franti Huamán retweeted
Siendo ARQUERO le reventó el travesaño e indirectamente se hizo una autoasistencia, tenes que cerrar las canchitas, los genios hacen eso
191
4,928
151
69,230
2,045,882
Franti Huamán retweeted
The obvious way to buy back your time is to pay someone to do something for you. Pay the mechanic to change your oil or a dry cleaner to press your suit. The less obvious way to buy back your time is to say no. Passing on a promotion might "buy" you more time with family. Declining the dinner invite might "pay" for the time you need to exercise. We buy back our time not only with the money we spend, but also with the opportunities we decline. The more clearly you know how you want to spend your days, the easier it becomes to say no to the requests that steal your hours.
432
34
3,847
177,586
Franti Huamán retweeted
Finish something. Anything. Stop researching, planning, and preparing to do the work and just do the work. It doesn’t matter how good or how bad it is. You don’t need to set the world on fire with your first try. You just need to prove to yourself that you have what it takes to produce something. There are no artists, athletes, entrepreneurs, or scientists who became great by half-finishing their work. Stop debating what you should make and just make something.
1,558
90
10,141
308,801
Franti Huamán retweeted
There is an African Proverb that I love: “A cat that dreams of becoming a lion must lose its appetite for rats.” Meaning: To achieve greatness, you must let go of old habits that could hold back your progress.
49
1,249
12
6,307
125,108
Franti Huamán retweeted
Understand. Don't memorize. Learn principles, not formulas.
152
2,586
79
15,367
360,570
Milton Friedman on how real reform happens: “You can’t reform any institution from inside because people don’t act against their own interest.” “The only way you reform institutions is by competition from the outside.”
17
264
24
1,152
21,867
Franti Huamán retweeted
Naval Ravikant on the right reasons to start a company “I really just wanted to be a founder,” Naval confesses with respect to the first few companies he started. “That desire kind of overrode everything… It was not a pure motivation.” Then his motivation shifted to money and power: “Nobody wants to talk about it, but [money and power] are fundamental drivers,” he admits. “I want to make money, and I want a company that has an influence. And that wasn’t that great of a motivation either.” Naval continues: “Now looking back in my career, I was most successful when I did projects because I was genuinely curious about them… Following my own intellectual curiosity gave me insight that led to good investments, startups, and outcomes.” Today Naval is in a position where he doesn’t have to do things for money or status, so he only works on products he wants to see exist: “What’s a beautiful thing I can make that wouldn’t exist if I didn’t put effort into it?” he asks himself. “And what people do I want to spend all my time around?” Naval reflects: “The truth is that when your material desires are somewhat met, you end up extremely bored… When you don’t have to hustle for a living, you’re like, ‘What do I do?’ You’ve lost your purpose in life. You can go meditate in a corner for a long time, but that gets boring too. You can go completely hedonistic, but that’s a death trap and just an empty lifestyle.” He continues: “What I want to do is self-actualize. I want to be the best version of myself. And what does the best version of myself mean? That means creating something. It’s better to create than to consume. It’s far more fulfilling to learn along the way and build… And I want to do it with friends — people that I really respect, admire, and enjoy spending time with… I wish I had that motivation and insight 20-30 years ago.” Source: @zfellows (Aug 2025)
11
44
3
315
28,345
Franti Huamán retweeted
La productividad no es hacer mas cosas. Es eliminar las que no importan. La mayoria de las empresas no fracasan por falta de actividad, fracasan por confundir movimiento con progreso. Una buena semana tiene pocos objetivos, responsables claros y decisiones rapidas. Todo lo demas es teatro corporativo.
6
59
6
264
8,553