Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

TBPN asked me how Zapier keeps AI from drowning in data. Short answer: we built it a brain. Three layers: 1. Company-level source of truth (strategy, values, ICP). Curated by me and a handful of senior leaders 2. Team-level context that cascades down 3. Individual context, private to each... show more

Wade Foster

25,153 subscribers

35,638 views • 3 months ago •via X (Twitter)

Education Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Your AI is only as smart as the context it runs on. Have you built your shared enterprise brain yet? At Databricks Data+AI Summit, I spoke with Prukalpa ✨, co-founder and co-CEO of Atlan, to go deeper on the AI Context Layer in practice. The concept of a shared enterprise brain resonated with me. It is a foundation that every AI agent draws from, learns from, and contributes back to. "The future of organizations are going to be the fastest learning organizations." - Prukalpa ✨ Sankar, co-founder and co-CEO of Atlan Watch the full interview on YouTube: Check out the live demo by Atlan on Building Context for Your AI Agents - #EnterpriseAI #ContextLayer #Data #AI #AtlanPartner Matthias Heidrich

Your AI is only as smart as the context it runs on. Have you built your shared enterprise brain yet? At Databricks Data+AI Summit, I spoke with Prukalpa ✨, co-founder and co-CEO of Atlan, to go deeper on the AI Context Layer in practice. The concept of a shared enterprise brain resonated with me. It is a foundation that every AI agent draws from, learns from, and contributes back to. "The future of organizations are going to be the fastest learning organizations." - Prukalpa ✨ Sankar, co-founder and co-CEO of Atlan Watch the full interview on YouTube: Check out the live demo by Atlan on Building Context for Your AI Agents - #EnterpriseAI #ContextLayer #Data #AI #AtlanPartner Matthias Heidrich

Helen Yu

10,953 views • 27 days ago

Your engineering team is about to snap. And your AI coding agent is making it worse. Introducing CodeRabbit Agent for Slack 🎉 A second brain for engineering teams. Because your tribal knowledge lives in Slack threads nobody can find. At CodeRabbit, we review millions of PRs every week and know how ace engineering teams operate on the planet. The same three things slow every team we see: - Context and decisions that live elsewhere. - Lack of a team-level durable knowledge base - And a trust layer that gives a safety net to your teams Built for Agentic SDLC workflows, CodeRabbit Agent for Slack solves all three problems in one shot while enabling teams to collaborate in real-time with the Agent. CodeRabbit Agent is Slack-native and builds your team’s operating context from every thread, every decision, every conversation your team has ever had. Make your team’s context compound!

Your engineering team is about to snap. And your AI coding agent is making it worse. Introducing CodeRabbit Agent for Slack 🎉 A second brain for engineering teams. Because your tribal knowledge lives in Slack threads nobody can find. At CodeRabbit, we review millions of PRs every week and know how ace engineering teams operate on the planet. The same three things slow every team we see: - Context and decisions that live elsewhere. - Lack of a team-level durable knowledge base - And a trust layer that gives a safety net to your teams Built for Agentic SDLC workflows, CodeRabbit Agent for Slack solves all three problems in one shot while enabling teams to collaborate in real-time with the Agent. CodeRabbit Agent is Slack-native and builds your team’s operating context from every thread, every decision, every conversation your team has ever had. Make your team’s context compound!

Harjot Gill

4,774,714 views • 3 months ago

A few days ago I asked if anyone was still interested in decentralized AI. Turns out... yeah! So here's lecture 1: Decentralized AI From Scratch We build a peer-to-peer AI from scratch in about 50 lines of Python. It runs on your laptop, answers your friends' WhatsApp messages using your local data, and begins to address the privacy / prompt-injection problem through user-specific context management.

A few days ago I asked if anyone was still interested in decentralized AI. Turns out... yeah! So here's lecture 1: Decentralized AI From Scratch We build a peer-to-peer AI from scratch in about 50 lines of Python. It runs on your laptop, answers your friends' WhatsApp messages using your local data, and begins to address the privacy / prompt-injection problem through user-specific context management.

⿻ Andrew Trask

25,889 views • 3 months ago

The new company brain. Context is the soul of your company, I learned today. Since I wrote a book, “Age of Context,” years ago I see that context is what we now call our private data. That data should be stored in a way to let AI agents and humans get more and more use out of it. This is precisely what PromptQL does and here Tanmai Gopal goes deep on how it now is a company brain, or, rather, a wiki that everyone updates and uses.

The new company brain. Context is the soul of your company, I learned today. Since I wrote a book, “Age of Context,” years ago I see that context is what we now call our private data. That data should be stored in a way to let AI agents and humans get more and more use out of it. This is precisely what PromptQL does and here Tanmai Gopal goes deep on how it now is a company brain, or, rather, a wiki that everyone updates and uses.

Robert Scoble

18,271 views • 1 month ago

IN NEWS: Attio raises $52M series B led by GV. Nicolas Sharp on AI in CRM: "LLMs work great when they have lots of context and you need to feed them that. One of the first things we worked on was this data model and being able to instantly ingest emails, calendars, product data, etc." "We have a thesis that code is becoming the new no-code. Software becomes so much more malleable because code is so much easier to generate."

IN NEWS: Attio raises $52M series B led by GV. Nicolas Sharp on AI in CRM: "LLMs work great when they have lots of context and you need to feed them that. One of the first things we worked on was this data model and being able to instantly ingest emails, calendars, product data, etc." "We have a thesis that code is becoming the new no-code. Software becomes so much more malleable because code is so much easier to generate."

TBPN

16,200 views • 11 months ago

IN NEWS: Infisical closes $16M in funding, led by Elad Gil We asked co-founder Vlad Matsiiako to break down the thesis: "Creating a uniform source of secrets and enterprise access helps us build an AI brain." "AIs are running faster and smarter, but that depends on quick access to secrets and data bases." "Right now a lot of this is provisioned manually. We want to make this autonomous."

IN NEWS: Infisical closes $16M in funding, led by Elad Gil We asked co-founder Vlad Matsiiako to break down the thesis: "Creating a uniform source of secrets and enterprise access helps us build an AI brain." "AIs are running faster and smarter, but that depends on quick access to secrets and data bases." "Right now a lot of this is provisioned manually. We want to make this autonomous."

TBPN

10,488 views • 1 year ago

A great executive assistant is a superpower for CEOs. An AI-powered EA is something else entirely. Cortney Hickey, Executive Business Partner to Wade Foster at Zapier has leaned in HARD to AI + automations to drive operational efficiency, leadership alignment, and cultural clarity across the company. In this week's How I AI, she shows us some of her tricks, including: - a meeting prep agent that makes sure she + the CEO are 100% ready for any meeting - an AI "meeting coach" that ensures the exec team is staying true to their principles and commitments - her pre-exec doc review system that makes sure anyone in the company can get CEO-level feedback...before meeting with the CEO This is one of the most practical and aspirational episodes we've had so far. Cortney is an AI star. As always, big thanks to our sponsors! 💼 WorkOS Make your app enterprise-ready today 🤑 Brex The intelligent finance platform built for founders

A great executive assistant is a superpower for CEOs. An AI-powered EA is something else entirely. Cortney Hickey, Executive Business Partner to Wade Foster at Zapier has leaned in HARD to AI + automations to drive operational efficiency, leadership alignment, and cultural clarity across the company. In this week's How I AI, she shows us some of her tricks, including: - a meeting prep agent that makes sure she + the CEO are 100% ready for any meeting - an AI "meeting coach" that ensures the exec team is staying true to their principles and commitments - her pre-exec doc review system that makes sure anyone in the company can get CEO-level feedback...before meeting with the CEO This is one of the most practical and aspirational episodes we've had so far. Cortney is an AI star. As always, big thanks to our sponsors! 💼 WorkOS Make your app enterprise-ready today 🤑 Brex The intelligent finance platform built for founders

claire vo 🖤

16,022 views • 7 months ago

"Everyone talks about humanoids, but most of the applications that can be automated in the next 2-3 years do not require legs." - Dylan Patel "If I go to a factory, the floor is a flat slab of concrete. I don't need to spend all this weight and power on legs when I could just throw wheels on it." "Hands are incredible, and we aren't even close to human-level hands physically or AI-wise." "Imagine cutting down the costs of humanoid robots to 1/10th by replacing legs with wheels, and having three gripper fingers instead of fully formed hands."

"Everyone talks about humanoids, but most of the applications that can be automated in the next 2-3 years do not require legs." - Dylan Patel "If I go to a factory, the floor is a flat slab of concrete. I don't need to spend all this weight and power on legs when I could just throw wheels on it." "Hands are incredible, and we aren't even close to human-level hands physically or AI-wise." "Imagine cutting down the costs of humanoid robots to 1/10th by replacing legs with wheels, and having three gripper fingers instead of fully formed hands."

TBPN

16,666 views • 1 year ago

We asked Steven Pang what he's working on (Orbit). "We built a precise modulator of the vestibular system, which is in your inner ear." "It's like making high-level API calls to regulate your heart or breathing rate." "The vestibular system evolved so early on in the evolutionary chain that it's entangled with a bunch of deep brain regions." "We started by sending signals to it. It makes brain stimulation a lot easier and allows you to do important things, like sleeping better or beating Ozempic without all the side effects."

We asked Steven Pang what he's working on (Orbit). "We built a precise modulator of the vestibular system, which is in your inner ear." "It's like making high-level API calls to regulate your heart or breathing rate." "The vestibular system evolved so early on in the evolutionary chain that it's entangled with a bunch of deep brain regions." "We started by sending signals to it. It makes brain stimulation a lot easier and allows you to do important things, like sleeping better or beating Ozempic without all the side effects."

TBPN

16,905 views • 1 year ago

A few weeks ago I put out a call for CEOs that are *actually* using AI, not just sending AI memos. Ofc Wade Foster (CEO Zapier) was the first to raise his hand. Wade is truly a AI-native CEO, and in this week's ep he shows us: - how to reverse engineer company culture from Granola transcripts - his Zapier interview rubric agent that gives structured feedback on every candidate - and how to use Grok (YES, grok!) to source talent If you're looking for non-technical, leadership focused use cases for AI - this is a must watch. This episode is brought to you by our amazing sponsor 🧠🤑 Brex - The intelligent finance platform built for founders Watch it here:

A few weeks ago I put out a call for CEOs that are actually using AI, not just sending AI memos. Ofc Wade Foster (CEO Zapier) was the first to raise his hand. Wade is truly a AI-native CEO, and in this week's ep he shows us: - how to reverse engineer company culture from Granola transcripts - his Zapier interview rubric agent that gives structured feedback on every candidate - and how to use Grok (YES, grok!) to source talent If you're looking for non-technical, leadership focused use cases for AI - this is a must watch. This episode is brought to you by our amazing sponsor 🧠🤑 Brex - The intelligent finance platform built for founders Watch it here:

claire vo 🖤

53,012 views • 6 months ago

Tired: Writing PRDs by hand Wired: Writing PRDs with AI Inspired: letting AI reply to all PRD comments left by your coworkers Dennis Yang takes AI product management to the nth degree in this week's episode of How I AI, showing us how he: - uses Cursor for ALL his product work (yes, including commenting back to his team) - maxes out the notion and jira MCPs to automate work across his team's source of truth - prototypes AI products using cursor as the foundation This one is a 11 out of 10 for any PM trying to take their AI use to the next level and inspired me in a bunch of ways. And yes, his colleagues know all about it 😎 As always, a BIG thanks to our wonderful sponsors: ⚡️ Zapier - the most connected AI orchestration platform 🤑 Brex - the intelligent finance platform built for founders

Tired: Writing PRDs by hand Wired: Writing PRDs with AI Inspired: letting AI reply to all PRD comments left by your coworkers Dennis Yang takes AI product management to the nth degree in this week's episode of How I AI, showing us how he: - uses Cursor for ALL his product work (yes, including commenting back to his team) - maxes out the notion and jira MCPs to automate work across his team's source of truth - prototypes AI products using cursor as the foundation This one is a 11 out of 10 for any PM trying to take their AI use to the next level and inspired me in a bunch of ways. And yes, his colleagues know all about it 😎 As always, a BIG thanks to our wonderful sponsors: ⚡️ Zapier - the most connected AI orchestration platform 🤑 Brex - the intelligent finance platform built for founders

claire vo 🖤

45,455 views • 9 months ago

Last week $TEAM outlined a new AI bull case for SaaS, as a source of context to generate better, faster, cheaper AI outcomes. Atlassian demod how Claude Code by itself underperformed an identical instance of Claude Code, on an identical prompt, when the other instance had access to their Teamwork Graph (TWG) which has access to past project files, messages, documents, code bases, employee data, and system integrations (slack, outlook, etc). The added context pointed Claude to the right information to solve the task faster, whereas the instance without context thought more, read more, hallucinated, and got the task incorrect after spending 2x more tokens and running an extra minute. Since token spend is quickly becoming many multiples of traditional software cost for coding use cases (Jira at $10-12/seat vs Anthropic spend per seat in the several hundreds a month), Atlassian makes a compelling case that context pays for itself many times over by helping customers to get more value out of their expensive AI tokens. $MSFT easily has the strongest advantage as a source of differentiated context. Video worth watching.

Last week $TEAM outlined a new AI bull case for SaaS, as a source of context to generate better, faster, cheaper AI outcomes. Atlassian demod how Claude Code by itself underperformed an identical instance of Claude Code, on an identical prompt, when the other instance had access to their Teamwork Graph (TWG) which has access to past project files, messages, documents, code bases, employee data, and system integrations (slack, outlook, etc). The added context pointed Claude to the right information to solve the task faster, whereas the instance without context thought more, read more, hallucinated, and got the task incorrect after spending 2x more tokens and running an extra minute. Since token spend is quickly becoming many multiples of traditional software cost for coding use cases (Jira at $10-12/seat vs Anthropic spend per seat in the several hundreds a month), Atlassian makes a compelling case that context pays for itself many times over by helping customers to get more value out of their expensive AI tokens. $MSFT easily has the strongest advantage as a source of differentiated context. Video worth watching.

SouthernValue

31,196 views • 2 months ago

"What happens when we can access each other's AI memory in enterprises?" scott belsky, investor/founder of Behance: "If I was working as an intern for years, and the context window is accessible to the enterprise, can the enterprise (keep prompting) and asking me what I'd think or do, after I leave?" "Every company right now is trying to build this AI memory for each of its products and users. A lot of them are building connectors to form a collective memory." "In the social/consumer world, imagine your girlfriend saying she wants access to your context window or memory." "There are all kinds of weird questions and implications that arise from this."

"What happens when we can access each other's AI memory in enterprises?" scott belsky, investor/founder of Behance: "If I was working as an intern for years, and the context window is accessible to the enterprise, can the enterprise (keep prompting) and asking me what I'd think or do, after I leave?" "Every company right now is trying to build this AI memory for each of its products and users. A lot of them are building connectors to form a collective memory." "In the social/consumer world, imagine your girlfriend saying she wants access to your context window or memory." "There are all kinds of weird questions and implications that arise from this."

TBPN

44,908 views • 1 year ago

A 14-year-old from China built three separate AI brains connected to Claude Code - and each one grows every day on its own. One brain for code, one for projects, one for everything else in his life. 600+ conversations on one topic in a single node - everything linked, everything accessible in one request without copying between tabs. But the main thing isn't storage. If Claude Code made a mistake and he corrected it once - the system remembered. That same mistake never happened again. No re-explaining context, no starting from zero - Claude already knows how he thinks. Instead of one giant messy file- a stack of smaller brains passing context to each other. Brain to brain to brain - just stacking intelligence while his classmates do homework by hand.

A 14-year-old from China built three separate AI brains connected to Claude Code - and each one grows every day on its own. One brain for code, one for projects, one for everything else in his life. 600+ conversations on one topic in a single node - everything linked, everything accessible in one request without copying between tabs. But the main thing isn't storage. If Claude Code made a mistake and he corrected it once - the system remembered. That same mistake never happened again. No re-explaining context, no starting from zero - Claude already knows how he thinks. Instead of one giant messy file- a stack of smaller brains passing context to each other. Brain to brain to brain - just stacking intelligence while his classmates do homework by hand.

Noisy

22,622 views • 2 months ago

We asked Walden (Co-Founder of Cognition) about building a truly AI-native company. “At a minimum, we can’t be hiring people whose whole aspiration is to write code that Devin will do in 1–2 years.” "A lot of companies at our stage, they have like an internal tools team to maintain all the different services that engineers internally use." "And we can just staff that team with Devins, and then basically have engineers just sending requests to those Devins for how to do that work."

We asked Walden (Co-Founder of Cognition) about building a truly AI-native company. “At a minimum, we can’t be hiring people whose whole aspiration is to write code that Devin will do in 1–2 years.” "A lot of companies at our stage, they have like an internal tools team to maintain all the different services that engineers internally use." "And we can just staff that team with Devins, and then basically have engineers just sending requests to those Devins for how to do that work."

TBPN

15,304 views • 1 year ago

Ilya Sutskever explains why AI will do 100% the work that human can do within few years. "Slowly but surely, or maybe not so slowly, AI will keep getting better. The day will come when AI will do all of our, all the things that we can do, not just some of them, but all of them. Anything which I can learn, anything which any one of you can learn, the AI could do as well. How do we know this, by the way? How can I be so sure? How can I be so sure of that? The reason is that all of us have a brain, and the brain is a biological computer. That's why we have a brain; the brain is a biological computer. So why can't the digital computer, a digital brain, do the same things? This is the one-sentence summary for why AI will be able to do all those things: because we have a brain, and the brain is a biological computer." --- Full Video on 'University of Toronto' YT Channel (link in comment)

Ilya Sutskever explains why AI will do 100% the work that human can do within few years. "Slowly but surely, or maybe not so slowly, AI will keep getting better. The day will come when AI will do all of our, all the things that we can do, not just some of them, but all of them. Anything which I can learn, anything which any one of you can learn, the AI could do as well. How do we know this, by the way? How can I be so sure? How can I be so sure of that? The reason is that all of us have a brain, and the brain is a biological computer. That's why we have a brain; the brain is a biological computer. So why can't the digital computer, a digital brain, do the same things? This is the one-sentence summary for why AI will be able to do all those things: because we have a brain, and the brain is a biological computer." --- Full Video on 'University of Toronto' YT Channel (link in comment)

Rohan Paul

334,691 views • 10 months ago

Demo alert: What if your company wiki was automatically written and updated by LLMs? Jim Fisher built a demo of this for Granola using all the meetings we've shared internally. Observations so far: it's incredibly up to date (no more stale docs!) and it requires zero effort. Not having a human author feels... different. When it's missing context on something (ie when something happens but we don't talk about it in a meeting) I want to add it manually to the wiki, but then that'll disappear the next time the page gets regenerated... Generally, makes me bullish on workflows where humans feed tons of unstructured data (easiest of which to create is conversations) to an AI, and then AI organizes + structures it on the fly.

Demo alert: What if your company wiki was automatically written and updated by LLMs? Jim Fisher built a demo of this for Granola using all the meetings we've shared internally. Observations so far: it's incredibly up to date (no more stale docs!) and it requires zero effort. Not having a human author feels... different. When it's missing context on something (ie when something happens but we don't talk about it in a meeting) I want to add it manually to the wiki, but then that'll disappear the next time the page gets regenerated... Generally, makes me bullish on workflows where humans feed tons of unstructured data (easiest of which to create is conversations) to an AI, and then AI organizes + structures it on the fly.

Chris Pedregal

15,213 views • 1 year ago

The reason your AI gives generic answers isn't the model. It's that your company's knowledge lives in 12 different tools and your agent can't see any of it. So here's how to build a context database your agents can actually use: 1) Pull it in: - Slack, email, meetings, docs, tickets - Auto-collected on a schedule into one place. 2) Clean it up. - An agent files what matters and drops the noise, so your brain doesn't bloat. 3) Store it as memory. - Folders of files your agents read from and write back to as they learn. 4) Point your agents at it. - Now they draft, build, and ship with full context instead of guessing. Same model. Same agent. The difference is whether it can understand your company or not. Build the database once. Everything downstream gets smarter.

The reason your AI gives generic answers isn't the model. It's that your company's knowledge lives in 12 different tools and your agent can't see any of it. So here's how to build a context database your agents can actually use: 1) Pull it in: - Slack, email, meetings, docs, tickets - Auto-collected on a schedule into one place. 2) Clean it up. - An agent files what matters and drops the noise, so your brain doesn't bloat. 3) Store it as memory. - Folders of files your agents read from and write back to as they learn. 4) Point your agents at it. - Now they draft, build, and ship with full context instead of guessing. Same model. Same agent. The difference is whether it can understand your company or not. Build the database once. Everything downstream gets smarter.

The Startup Ideas Podcast (SIP) 🧃

13,486 views • 1 month ago

Appreciate you Charles for having me on today! We covered: • $AMD emerging as the second source of the AI economy • My two favorite emerging market names for 2026: $MELI & $JMIA • $MU at the center of the next AI spend cycle as AI becomes memory-first • $NVDA laying out the blueprint for the operating system of the AI economy • $META & $AMZN winning in AI through distribution, data, and workflow control • $EOSE as a winner from AI data centers creating extreme load swings that long-duration zinc storage is built to handle

Appreciate you Charles for having me on today! We covered: • $AMD emerging as the second source of the AI economy • My two favorite emerging market names for 2026: $MELI & $JMIA • $MU at the center of the next AI spend cycle as AI becomes memory-first • $NVDA laying out the blueprint for the operating system of the AI economy • $META & $AMZN winning in AI through distribution, data, and workflow control • $EOSE as a winner from AI data centers creating extreme load swings that long-duration zinc storage is built to handle

Shay Boloor

250,124 views • 6 months ago

Our new short course, Knowledge Graphs for RAG, is now available! Knowledge graphs are a data structure that is great at capturing complex relationships between data of multiple types. By enabling more sophisticated retrieval of text than similarity search alone, knowledge graphs can improve the context you pass to the LLM and the performance of your RAG applications. In this course, taught by Andreas Kollegger of Neo4j, you’ll - Explore how knowledge graphs work by building a graph of public financial documents from scratch - Learn to write queries that retrieve text and data from the graph and use it to enhance the context you pass to an LLM chatbot - Combine a knowledge graph with a question-answer chain to build better RAG-powered chat systems Sign up here!

Our new short course, Knowledge Graphs for RAG, is now available! Knowledge graphs are a data structure that is great at capturing complex relationships between data of multiple types. By enabling more sophisticated retrieval of text than similarity search alone, knowledge graphs can improve the context you pass to the LLM and the performance of your RAG applications. In this course, taught by Andreas Kollegger of Neo4j, you’ll - Explore how knowledge graphs work by building a graph of public financial documents from scratch - Learn to write queries that retrieve text and data from the graph and use it to enhance the context you pass to an LLM chatbot - Combine a knowledge graph with a question-answer chain to build better RAG-powered chat systems Sign up here!

Andrew Ng

244,329 views • 2 years ago