Daniel Gilbert (@dangilbert) header
Daniel Gilbert (@dangilbert) profile picture

CEO @Brainlabs Scaled from 1→1,000 people Author of Don't Be a Midwit 📘 Sharing how we became AI-native (real demos & lessons) @ShowMeYourAI

USA
Joined October 2011
banned my Claude form EVER telling me "go to settings and..." 😂 if it can do the step itself, it does the step. the only things it hands back are the bits that are physically mine, like a login or a 2FA code
1
219
a year ago shoppers coming from AI were 9% LESS likely to buy on US retail sites. now they convert 90% better 🤯 and Adobe expects AI traffic to nearly double on Black Friday. AI is either talking about your brand or ignoring it, and this is the worst quarter to be ignored... check out the Brainlabs AI visibility page
1
129
exactly why everything at Brainlabs lives in @NotionHQ... AI is only as good as what it knows.
saas runs on software, so everyone is building a software factory the hardest part of building agents is the context (or knowledge that they have) if youre building agents, you should be building a knowledge factory
2
1
7
3,158
you an spot AI-made designs in about 2 seconds... em dashed, those double slashes, an arrow on every button and that BLACK background 😂 Liz, our CMO, shows how she gets Claude to build something that actually looks designed, and it starts before she even writes anything.
2
3
205
agree.... for most of what you're doing the gap between them barely MATTERS now the person using it matters way more
Google, OpenAI & Anthropic are at the stage where, unless you frequently switch between them or actively test them, you are probably very happy with the series of releases in the past two months. Even the model releases that are not as strong represent large capability gains
136
Fable 5.2 vs Opus 5.5... The New Stack ran both and got the same scores, w Fable costing almost 4x as much 🤑 even Anthropic says start on Opus. Save Fable for those massive builds if you’re using it for real work, what’s the one job where it’s actually been worth the extra?
2
213
this is so underrated...saying "i don't know this yet" out loud is what lets everyone else start asking questions. an honest leader beats one who's faking it every time
The best thing a leader can do rn is admitting what they don’t know. Just had a training w a @cxodev client and the senior leader that brought us in was transparent abt their AI use: “I’m not doing any of this stuff. But I want to.” Gave everyone permission to ask & learn.
158
agents aren't magic it's just a more efficient way of interfacing with lots of different software on one platform. that's all it is 🤷‍♂️
1
286
100% this... there's plenty of GOOD AI output out there if all you're getting back is slop, that's a judgement problem. and that's your problem
A new faux pas I’m seeing: dismissing a teammate’s well-structured, probably decent agentic output as “AI slop” because you don’t want to read it. If a teammate (or agent) has skillfully prompted and carefully edited something to solve a problem or communicate with the business, it isn’t automatic slop just because AI generated it. There’s often good stuff in there... if it’s long or you're multi-tasking, feed it to your agent. Don’t overuse the term "AI slop" for any AI output. Save it for the actual sloppity slop, ya know?
1
251
Daniel Gilbert retweeted
Introducing eve 1.0 Build production agents.
eve is generally available with v1.0. • Build agents on your own harness • Ship multi-tenant, multiplayer agents • Govern & trace sessions with Agent Runs • Render agent UIs via Next.js, Nuxt & more Read the blog → vercel.com/blog/eve-is-now-g…
48
62
13
1,091
144,415
another reason we love @NotionHQ ... it's not tied to ONE LLM the model's the bit you can swap. your context & your JUDGEMENT are the bits you can't full episode in the comments
1
4
330
Spot on! mean or nice doesn’t matter.... it’s a machine I don’t need it to apologise. I need it to EXPLAIN why the output was bad
Unfortunately, the meaner you are to your AI, the better the work you get back. I hope it doesn’t remember any of this.
206
starting a new project? state the end goal FIRST.... the ideal version then work back from it. AI can’t make good calls if it doesn’t know what it’s building people think it’s magic and comes up with everything. it’s not. it can’t read your mind... that part’s still on YOU
233
step 38 is the one that matters 😂 every job writes back to the brain.... building it is easy, getting it to keep LEARNING is what I bang on about every week.
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.
148
ever wondered where these AI agents actually even live? wish it was more magical than it is😂 Watch our CTO Ben Vincent explain it with one diagram!!! Full episode on the YouTube channel below
1
1
4
364
agents are like cars: more dangerous when operated incorrectly.... you still need a DRIVER. use AI with bad judgment and you’ll crash. use it well and you go a lot further 🏎️💨
1
276