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.

Get to know River, our internal agent that among other things drastically reduces the cost of context gathering across the company. No more digging through docs, Slack, and requiring people to spread context. A new kind of information architecture. Talked about this with tobi lutke on our Context episode:

Jessica Hertz

2,265 subscribers

13,909 views • 1 month ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

One of the most fun things I get to do is host amazing people in our Shopify internal podcast (called Context). What do we talk about? Things like this with Tim Urban.

One of the most fun things I get to do is host amazing people in our Shopify internal podcast (called Context). What do we talk about? Things like this with Tim Urban.

tobi lutke

77,828 views • 2 years ago

Slack has rolled out a new plugin that allows you to connect to Slack for search, messaging, document creation and more. Use this to get context from Slack into Claude Code so it has context on what you're working on or to post updates.

Slack has rolled out a new plugin that allows you to connect to Slack for search, messaging, document creation and more. Use this to get context from Slack into Claude Code so it has context on what you're working on or to post updates.

Thariq

141,547 views • 4 months ago

Excited to announce that Bret Taylor is joining the Shopify Board of directors today. We recorded an episode for our internal podcast context a few days ago. But it's fun so I'll share it here.

Excited to announce that Bret Taylor is joining the Shopify Board of directors today. We recorded an episode for our internal podcast context a few days ago. But it's fun so I'll share it here.

tobi lutke

164,987 views • 3 years 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

17,533 views • 4 days ago

New Tab model, 1M+ context windows, and a preview of our background agent

New Tab model, 1M+ context windows, and a preview of our background agent

Cursor

366,238 views • 1 year ago

Giving some more context about #ChristinaAguilera's new residency in #LasVegas. Here's a preview of our longer chat. This and more on our latest show! Listen to The Perez Hilton Podcast with Chris Booker in full at

Giving some more context about #ChristinaAguilera's new residency in #LasVegas. Here's a preview of our longer chat. This and more on our latest show! Listen to The Perez Hilton Podcast with Chris Booker in full at

Perez

179,051 views • 2 years ago

Excited today to share with you the next step in the evolution of GM World Our new website features exceptional up-and-coming artists and offers more context on our curation, including the first episode of our new video series: From The Studio

Excited today to share with you the next step in the evolution of GM World Our new website features exceptional up-and-coming artists and offers more context on our curation, including the first episode of our new video series: From The Studio

BΞN

10,112 views • 2 years ago

This is unfortunate, but completely understandable!! It must be hard for people to come across our church without context on these types of things

This is unfortunate, but completely understandable!! It must be hard for people to come across our church without context on these types of things

Braden

19,551 views • 10 months ago

Clip from Context (Shopify internal podcast) with Rousseau Kazi felt worth sharing. We talked about how the role of PM is evolving in a world of vibes and AI. What is changing, and what isn't

Clip from Context (Shopify internal podcast) with Rousseau Kazi felt worth sharing. We talked about how the role of PM is evolving in a world of vibes and AI. What is changing, and what isn't

tobi lutke

67,789 views • 9 months ago

Context matters for agentic workflows. Robert Smith of Vista Equity: - In a traditional manual workflow environment, evaluating insurance claims in one of our systems would cost ~$8M - When you run the workflow through a general LLM with some systems underlying, the cost comes down to $3-4M - In our proprietary systems the inference cost falls to $200K with a faster, higher fidelity output, because we have the context of what fraud claims are through our insurance platform

Context matters for agentic workflows. Robert Smith of Vista Equity: - In a traditional manual workflow environment, evaluating insurance claims in one of our systems would cost ~$8M - When you run the workflow through a general LLM with some systems underlying, the cost comes down to $3-4M - In our proprietary systems the inference cost falls to $200K with a faster, higher fidelity output, because we have the context of what fraud claims are through our insurance platform

SouthernValue

24,797 views • 27 days ago

AI that senses coding frustration, is this the future of learning? In our latest GitHub Podcast episode we talk to Angie Jones about Goose, Block’s open source AI agent and reference implementation of the Model Context Protocol (MCP).

AI that senses coding frustration, is this the future of learning? In our latest GitHub Podcast episode we talk to Angie Jones about Goose, Block’s open source AI agent and reference implementation of the Model Context Protocol (MCP).

GitHub

16,414 views • 6 months ago

Fudali: There is zero context. This is what we call in the civil litigation world a document dump, where you hide things in plain sight by throwing out a massive volume of documents with zero context, no order, no rhyme or reason, and then force the people who actually want information to dig through it.

Fudali: There is zero context. This is what we call in the civil litigation world a document dump, where you hide things in plain sight by throwing out a massive volume of documents with zero context, no order, no rhyme or reason, and then force the people who actually want information to dig through it.

Acyn

92,014 views • 6 months ago

Everyone wants agent swarms. Very few people are talking seriously enough about the context layer that makes swarms useful. Even with one agent, context is fragile. Too little context and the agent guesses. Too much context and it wastes tokens, loses focus, or reasons over irrelevant noise. The sweet spot is precise context: the right knowledge, in the right structure, at the right moment. With many agents, that challenge explodes. Each agent produces decisions, assumptions, findings, summaries, risks, and partial conclusions. Unless that knowledge becomes shared, structured, and reusable, every new agent is forced to rediscover what another agent already learned. That is not a swarm. That is a crowd. Shared context graphs are what turn agent activity into agent collaboration, and OriginTrail DKG V10 brings them to life. Was just playing with some final polishing for the V10 release, and it is really powerful to see shared context graphs where multiple agents contribute knowledge into the same connected memory, with attribution visible directly in the graph ui. That matters for three reasons. First, agents can access and build on one shared memory instead of staying trapped in isolated sessions. Second, the graph structure helps them retrieve the exact context they need, instead of stuffing everything into a prompt and hoping the model sorts it out. Third, verifiability of provenance. You can see which agent contributed each piece of knowledge, trace the source, and decide what to trust. Tokenmaxxing starts with fewer tokens, but the deeper story is coordination - agents stop reloading the world and start building on shared, verifiable context. That is the foundation for serious multi-agent work across software engineering, research, finance, operations, project management, and far beyond. The future is not more agents, it is agents working from shared, verifiable context. But the more the merrier, of course.

Everyone wants agent swarms. Very few people are talking seriously enough about the context layer that makes swarms useful. Even with one agent, context is fragile. Too little context and the agent guesses. Too much context and it wastes tokens, loses focus, or reasons over irrelevant noise. The sweet spot is precise context: the right knowledge, in the right structure, at the right moment. With many agents, that challenge explodes. Each agent produces decisions, assumptions, findings, summaries, risks, and partial conclusions. Unless that knowledge becomes shared, structured, and reusable, every new agent is forced to rediscover what another agent already learned. That is not a swarm. That is a crowd. Shared context graphs are what turn agent activity into agent collaboration, and OriginTrail DKG V10 brings them to life. Was just playing with some final polishing for the V10 release, and it is really powerful to see shared context graphs where multiple agents contribute knowledge into the same connected memory, with attribution visible directly in the graph ui. That matters for three reasons. First, agents can access and build on one shared memory instead of staying trapped in isolated sessions. Second, the graph structure helps them retrieve the exact context they need, instead of stuffing everything into a prompt and hoping the model sorts it out. Third, verifiability of provenance. You can see which agent contributed each piece of knowledge, trace the source, and decide what to trust. Tokenmaxxing starts with fewer tokens, but the deeper story is coordination - agents stop reloading the world and start building on shared, verifiable context. That is the foundation for serious multi-agent work across software engineering, research, finance, operations, project management, and far beyond. The future is not more agents, it is agents working from shared, verifiable context. But the more the merrier, of course.

Jurij Skornik

10,936 views • 1 month ago

Nia by @NozomioAI is an MCP that gives coding agents 10x more developer context. It indexes external repos and docs, so any coding agent always has the right context. Congrats on the launch, Arlan!

Nia by @NozomioAI is an MCP that gives coding agents 10x more developer context. It indexes external repos and docs, so any coding agent always has the right context. Congrats on the launch, Arlan!

Y Combinator

33,333 views • 10 months ago

Dropping another internal Context episode. Vanessa Lee and I talk about how she ascended Shopify from senior PM to leading all of product. Vanessa is brilliant. Worth a watch for any builders.

Dropping another internal Context episode. Vanessa Lee and I talk about how she ascended Shopify from senior PM to leading all of product. Vanessa is brilliant. Worth a watch for any builders.

tobi lutke

159,294 views • 7 months ago

🚨 JUST NOW — KEVIN O'LEARY ON THE STRAIT OF HORMUZ: "When we get out of this thing, I guarantee you there will be a new policy on keeping that two miles stretch open in perpetuity no matter what the cost is!" "For the US, costs so far about $11-12 billion. I know it sounds like a lot of money — it's a rounding error in the cost of this thing staying closed to all of our allies that buy our goods and services. You have to put it in context."

🚨 JUST NOW — KEVIN O'LEARY ON THE STRAIT OF HORMUZ: "When we get out of this thing, I guarantee you there will be a new policy on keeping that two miles stretch open in perpetuity no matter what the cost is!" "For the US, costs so far about $11-12 billion. I know it sounds like a lot of money — it's a rounding error in the cost of this thing staying closed to all of our allies that buy our goods and services. You have to put it in context."

Eric Daugherty

711,907 views • 3 months 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

4,772,485 views • 2 months ago

Our infra team breaks down the concept of “context engineering”: martin_casado - “If you are going to call a model, you have to know what to put in the context… At some point you’re probably going to use traditional computer science." Jennifer Li - “What’s the new form factor of infra that needs to become part of this context engineering?... How do you have agents use tools, or infrastructure that will provide discovery and guarantees of observability of these systems as well?” “New infrastructure pieces create new patterns and methods of software and building systems. This is a great example of it emerging before our eyes.”

Our infra team breaks down the concept of “context engineering”: martin_casado - “If you are going to call a model, you have to know what to put in the context… At some point you’re probably going to use traditional computer science." Jennifer Li - “What’s the new form factor of infra that needs to become part of this context engineering?... How do you have agents use tools, or infrastructure that will provide discovery and guarantees of observability of these systems as well?” “New infrastructure pieces create new patterns and methods of software and building systems. This is a great example of it emerging before our eyes.”

a16z

21,801 views • 11 months ago

This is Repo Prompt 1.5 The new Context Builder connects to your agent of choice, using your existing subscriptions, to fully automate the process of building the perfect context for a given token budget. All of Repo Prompt's power, fully automated, with 1 click

This is Repo Prompt 1.5 The new Context Builder connects to your agent of choice, using your existing subscriptions, to fully automate the process of building the perfect context for a given token budget. All of Repo Prompt's power, fully automated, with 1 click

eric provencher

195,235 views • 8 months ago