Every single customer told Jacqueline Cheong (@JacquelineSYC19) they didn’t want the feature. She built it anyway. Six months later, 40% of them had turned it on. She’s the co-founder and CEO of @artie_labs, which moves data between databases in real time: the unglamorous plumbing that lets AI agents reason over what’s happening now, not what happened yesterday. We got into: •Building the feature customers said they didn’t want •Founding a company with your spouse (and why she’s loud about it) •Why her whole team sees the revenue and burn numbers •Why she stopped watching the metric and started watching the inputs •Why real-time data is the layer AI agents actually need 𝐓𝐈𝐌𝐄𝐒𝐓𝐀𝐌𝐏𝐒 (00:00) Transamerica, and Why This Spot (02:00) What Artie Actually Does (05:00) Why Real-Time Data Is Hard (08:00) The AI Agent Angle (12:00) The History Table Everyone Said No To (18:00) Founding a Company With Your Husband (24:00) Radical Transparency With the Team (30:00) The “Working With Me” Doc (34:00) Focus on Inputs, Not the Score (38:00) The Wedding Cake Metaphor This is a @Composio “Agents at Work” podcast, where I chat with founders building the next leap of AI. Follow for more :)

How time flies. I've been @Composio 8 months now building out our content engine and podcast: interviewing founders about what they're building. Season 3 starts soon and it'll be different. Every episode is one company, one department, filmed inside. Less "what do you think about AI," more what does it actually do here daily. I'll be asking questions like: -How much of your product is built by your own agent -What you automated and had to take back -What roles you stopped hiring for -What you'd do first at a slower company If you're a company in San Francisco (or Toronto;)) and you'd let a camera in, DM ME! Episode 1 is a works in progress right now;)

What have people in SF built with Astra? (GPT-6 Community Night edition🌌) I got accepted to attend the @OpenAI GPT-6 Community Night out of 40,000 people who applied! Not only did I get to meet Sam Altman but I also learned what builders are creating with Astra:) Someone's building... "The first ever shitty cloud for shitty apps." A wine-collection tracker. A DIY hardware note-taker wired up in Blender. A "second brain" pulling in every X bookmark and YouTube video, 9 months deep. An action short pulled off a phone and auto-edited in DaVinci Resolve. Got to talk to some incredible people doing this: @katedeyneka (@reelful), @jsmarr (@Shopify), @danizeres (@OpenAI), @ZergGirl (@Replit), @scasa1 (@Target), @wongmjane, @theo, @iHarnoorSingh (@AssemblyAI) and more. Full reel ↓

What have people in SF built with Astra? (GPT-6 Community Night edition🌌) I got accepted to attend the @OpenAI GPT-6 Community Night out of 40,000 people who applied! Not only did I get to meet Sam Altman but I also learned what builders are creating with Astra:) Someone's building... "The first ever shitty cloud for shitty apps." A wine-collection tracker. A DIY hardware note-taker wired up in Blender. A "second brain" pulling in every X bookmark and YouTube video, 9 months deep. An action short pulled off a phone and auto-edited in DaVinci Resolve. Got to talk to some incredible people doing this: @katedeyneka (@reelful), @jsmarr (@Shopify), @danizeres (@OpenAI), @ZergGirl (@Replit), @scasa1 (@Target), @wongmjane, @theo, @iHarnoorSingh (@AssemblyAI) and more. Full reel ↓

@OpenAI GPT-6 Community Night Meeting Recap :) -met and talked with @sama for the first ever time -met and talked with my podcast inspiration @ti_morse for the first ever time -interviewed a few people asking them “what’s the coolest thing you’ve built with astra” -got to see a lot of other cool people like @katedeyneka from @reelful, @jsmarr from @Shopify, @danizeres from @OpenAI, @ZergGirl from @Replit, @scasa1 from @Target, @wongmjane, @theo !! alsoo i got complimented on my shirt and how it matched the theme, it wasn’t even intentional hehe 🥹

@OpenAI GPT-6 Community Night Meeting Recap :) -met and talked with @sama for the first ever time -met and talked with my podcast inspiration @ti_morse for the first ever time -interviewed a few people asking them “what’s the coolest thing you’ve built with astra” -got to see a lot of other cool people like @katedeyneka from @reelful, @jsmarr from @Shopify, @danizeres from @OpenAI, @ZergGirl from @Replit, @scasa1 from @Target, @wongmjane, @theo !! alsoo i got complimented on my shirt and how it matched the theme, it wasn’t even intentional hehe 🥹

how to not fall for phishing attacks: 0. remember you can't be hacked just by clicking on links you can only be hacked if you actively enter your password and 2FA code in places you're not supposed to 1. always read the URL you click on the url in the the current phishing messages is postdmca-x. com do you think anyone from X will use that random domain? they'll only use the official domain. if you read the URL you basically avoid 99.99% hack attempts. 2. never enter your real password in any form if you still feel convinced, just submit with a wrong password if it still "logs you in", you know you just saved your ass from a hacking attempt why? because a phishing form will always accept any password input as successful, because it doesn't really know the correct password only the real server knows your actual password and will give you an "incorrect password" error

I GOT MY ACCOUNT BACK. For about 36 hours my account was sending phishing DMs to a lot of you. If you got one, IM SORRY, IGNORE. If you clicked it and entered anything, change your password now and turn on a passkey!! How it happened: same DM, from someone I had no reason to doubt. That's the whole attack. It looked SO LEGIT. Two things I'd do differently: check the domain before typing a password anywhere, and use a passkey! I HAVE ONE NOW. Thank you to everyone who messaged me, reported the DMs, and warned their own networks. That's what got it shut down. Back to regular programming. Now my account is extra secured :D BRB gonna send an apology message to everyone the scammer messaged in my DMs (there's alot:,))

I GOT MY ACCOUNT BACK. For about 36 hours my account was sending phishing DMs to a lot of you. If you got one, IM SORRY, IGNORE. If you clicked it and entered anything, change your password now and turn on a passkey!! How it happened: same DM, from someone I had no reason to doubt. That's the whole attack. It looked SO LEGIT. Two things I'd do differently: check the domain before typing a password anywhere, and use a passkey! I HAVE ONE NOW. Thank you to everyone who messaged me, reported the DMs, and warned their own networks. That's what got it shut down. Back to regular programming. Now my account is extra secured :D BRB gonna send an apology message to everyone the scammer messaged in my DMs (there's alot:,))

Every company has the same problem says @ashwingop. One team learns something. Nobody else finds out. The lesson gets relearned six months later by someone else. "How do you make sure that if one part of the company learns about something, everybody else learns it too? So you don't relearn experiences. You move faster. You move as a single unit." That's what @sentra_app is building: organization memory. A company brain. Full convo below.

How do you introduce AI to a child who has already interacted with it but has no idea it's not a person? @Ashwingop's daughter started talking at @ChatGPT the same way she talks to her grandparents on the phone. She couldn't tell the difference. Full convo below

Instinct is the AI assistant every VC is chasing. Its founder, @noahrshinn, co-wrote Reflexion, one of the earliest agentic frameworks with MIT's @ashwingop. Noah chose to build agents for individuals. Ashwin quietly went the other way and founded Sentra to bring memory to enterprise agents. @sentra_app is now the company brain of a $12B public company-- 18,000 employees, and the CXOs start their day on it. Nothing like it exists in public. I sat down with Ashwin at Land's End in San Francisco before any of this was revealed. We got into: •Why memory is not a knowledge base •Why organizational memory is easier to build than individual memory •Why he thinks the AI race is nowhere near over •Who's actually accountable when AI gets something wrong •What worries him about his daughter growing up unable to tell AI from a person 𝐓𝐈𝐌𝐄𝐒𝐓𝐀𝐌𝐏𝐒 (00:00) Meet Ashwin at Land's End (00:48) What Sentra Builds (03:53) Why Agents Need Memory (06:44) Memory vs. Knowledge Base (08:38) Why Org Memory Works (13:02) Who's Accountable When AI Gets It Wrong (15:36) Humans Becoming AI (18:52) The AI Race Is Not Over (29:43) Choosing the Right Team (36:10) The AI Transition and Perspective (39:34) Kids Growing Up With AI (46:09) Agency as the Edge

My conversation with @jerryjliu0. He's building @llama_index: document infrastructure for AI agents, the layer underneath everything models need to work. Did you know he's the guy whose tool half the industry used for RAG? Then he called RAG a hack, two years before the field agreed. Here's the problem he's pointing at: 90% of the world's information is locked inside PDFs, PowerPoints, and Word documents. The models are already smarter than humans. But until an agent can read and reason over all that, it just sits still. RAG was the hack everyone reached for to bridge that gap: chunk, embed, retrieve, done. The easiest thing that kind of worked, so people could ship demos. Anything complex, and it falls apart. We got into: •Why RAG has no first principles, and what's replacing it •Why context, not intelligence, is the real bottleneck now •Why even MCP doesn't fully solve context •How you get agents to follow a company's culture, not just its instructions •What he'd build if he started LlamaIndex today 𝐓𝐈𝐌𝐄𝐒𝐓𝐀𝐌𝐏𝐒 (00:00) The Context Bottleneck (02:00) One Commit, One Tweet: The Origin (05:00) Feeding GPT-3 Your Private Data, Pre-RAG (08:00) From Quora to Uber's Self-Driving Lab (11:00) Meeting His Co-Founder at Uber ATG (14:00) Document Infrastructure for AI Agents (18:00) "RAG Is a Hack" — What He Meant (22:00) Why Production Search Is Still Unsolved (24:00) How a Research Background Changes How You Build (33:00) The Open Problem: Context Across Sources (38:00) Specs, Cultural Context, and Underspecified Tasks (40:00) What He'd Build Differently Today

Michael Blau (@blauyourmind) went from the investment team at @a16z Crypto to CTO at Royal, working with is brother. Something he learned was... "A great team with a bad idea will always beat a great idea with a bad team. The great team can figure it out, pivot, build something new. Our ideas don't matter, we just need the best, most flexible people around us." And if he wasn't in tech? He'd have his own parlor magic show on the Las Vegas Strip. He's been doing card tricks since he was 12. And that dream isn't going anywhere. What would you be doing if you weren't in tech? Full convo below.

"That's interesting" is founder speak for "I don't care." @Calcsam showed up to Next Conf three weeks into building @Mastra. Talked to 11 or 12 people. Heard "oh, that's interesting" over and over again. By 1:30 PM they'd had enough. Walked to a bar two miles away and asked themselves: "What did we f*** up?" "Don't just accept someone who says 'yeah, it's great.' You gotta dig deeper. When someone said 'oh, that's interesting' we knew they actually weren't that interested." The best feedback is rarely the feedback you get. It's the feedback you pull out. Full convo below.

At 22, Dan Romero (@dwr) thought Bitcoin was stupid. Then he joined @Coinbase. Now Dan is GTM at @Tempo and is one of the clearest voices explaining where stablecoins matter: •Cross-border payments: new companies are building entirely on stablecoin rails because they're internet-native and work across any country •Marketplace payouts: @DoorDash is piloting paying restaurants after every single delivery, even on weekends "What's gonna make a real difference is the fact that stablecoins create tangible consumer and business benefit. Getting paid faster is something everyone can understand." Full convo below.