One of the main reasons AI delivery fails:
Teams apply software-delivery methods to AI delivery.
Agile assumes the thing can be built. The uncertainty is what to build.
With AI, six weeks can get you one result: it doesn’t work.
That changes the whole operating model.
Founders: be careful when someone says they love your product but keeps putting off the next meeting. So much for all the ‘love your product’ BS 🙄
Ask them when they would want to start using it. If there is no urgency, find out what would need to change before you build more for them.
A Ferrari is 10X faster than you on a racetrack, but you're infinitely faster than it crossing a jungle. The problem with the fast takeoff crowd in AI is that they think the world is a racetrack, when in fact it's more like a jungle.
1/ AI demos are so stupid sometimes! You usually see the run that worked. You need to know what happens across different runs before you trust it with real work.
2/ Give the agent the same task a few times and keep the results, including the ugly ones. If you only look at the best run, you have no idea how much supervision the job will need.
3/ Then try it on tasks that differ from your examples. If it needs someone to correct it every time, factor that into the workflow before promising anyone an autonomous agent.
Founders should be careful with a potential customer asking for a feature. It’s not the same as a commitment to buy!
Before spending weeks building it, ask straight out if they’ll commit to buy if the new feature is in. Don’t be afraid to ask for a clear commitment.
When an agent gets stuck, giving it more attempts can get expensive pretty quickly. Especially if it keeps repeating the same approach expecting a different result... Give it a way to stop and ask for help instead
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.
I just had one of my AI agents telling me that a problem was just “fixed!” That was great... until I ran it and got the exact same error 😖
Word of advice: Give your agents a way to test the fix before telling you it is done.
Remember one critical thing about AI delivery:
sometimes finding out an idea doesn’t work is a good day. Sure, it would have been more fun if it worked... but finding that out before promising the whole thing saves a lot of pain 🤷♂️
Sales 101 is listening. If you’re selling a new product, the best advice anyone can get is to pay attention to how people describe the problem in their own words.
Obviously it’s tempting to jump straight into your amazing AI demo, but you might end up explaining a solution to a problem they do not think they have 🤷♂️
AI agents can easily mistake a completed run for a successful one. That should worry both builders and users…
The agent can finish every step and still misunderstand what you wanted.
Rather, give it a clear way to check the result before trusting it with bigger tasks.
Self-hosted Claude Managed Agents is now in private beta.
You can host the agent harness, sandboxes, and session history, in your own cloud or on-premises, and choose where requests to Claude are sent.
1/ AI delivery estimates get dangerous (and even a bit stupid) when you put a fixed date on something you haven’t tested yet. The team can do everything right and still the outcome can be that it’s just not gonna work.
2/ I would separate the work to find that out from the commitment to deliver the full solution. Agree on what you are testing and what would be good enough before you start.
3/ And once you have the results, you can have a much more useful conversation about the timeline and the cost. And if it doesn’t work well enough, another sprint is likely not going to fix it 🤷♂️