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.

Agent Toolkit for AWS gives AI coding agents the tools, knowledge, and guardrails they need to work effectively with AWS services. Instead of relying on agents' general knowledge of AWS, which can be outdated or incomplete, it provides access to up-to-date documentation, best practices, and tested procedures that improve... show more

Amazon Web Services

2,236,730 subscribers

22,757 views • 3 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

21 Comments

SecureAI3 months ago

Good guardrail to start with — most agent mistakes on AWS trace back to stale or guessed knowledge. The next one, as coding agents move from suggesting to running things: authority. What an agent is allowed to touch in a live account, and with what spend and blast-radius limits. Up-to-date docs keep it correct. Scoped permissions keep a wrong call from becoming an expensive one.

Brooke Jamieson3 months ago

Please try out the agent toolkit and let me know what you think!

Andrew3 months ago

🫵Revenge is certain🚀

Inflectiv AI ⧉3 months ago

Standardizing cloud infrastructure deployment through the Model Context Protocol ensures that autonomous developers stop guessing static API endpoints.

Mcmamby 🦊3 months ago

Europe girl as Amazon spokesperson?

NAZZY3 months ago

AI agents just got a major upgrade on AWS ⚡☁️

Kazi Humayun Rashid(Tanveer)3 months ago

URGENT - Hackathon deadline June 30, 2026 at 6:00 AM BST. I need immediate human support. Please reset my payment attempt limit NOW so I can add my card. My card is valid, bank confirmed international transactions are enabled. The block happened on my VERY FIRST attempt.

🅱🆄🅲🅺🆂💲🇲🇾3 months ago

Perfect fur a starter

安叫兽|Bird🕊️ 🔶 BNB3 months ago

MCP 这块终于不用全靠模型记忆了

THC Humor 💹🧲3 months ago

The future belongs to agents that actually know the documentation

Milton Yan3 months ago

documentation and best practices cover the knowledge gap, but guardrails that stop the wrong API call in real-time are a different layer. knowing the correct way to configure an S3 bucket and not doing it anyway are different failure modes.

NAZZY3 months ago

Outdated knowledge is the problem… this is the fix 🧠☁️

NAZZY3 months ago

Better tools, better guardrails, better AWS workflows for AI agents 🤖🔥

EurosHub3 months ago

Equipping agents with curated procedures and live references mitigates outdated knowledge and accelerates deployment in production grade workloads.

AI Mastery Guide3 months ago

Giving agents up to date docs instead of relying on outdated training knowledge is exactly the gap that needed fixing

Cheryl Tibbs3 months ago

This is the real unlock. Agents guessing at your cloud setup is how you burn money and trust. Give them real tools, current docs, and guardrails and you go from a cute demo to something you can actually run in production. We build this way at EmergeStack and it matters.

NAZZY3 months ago

AWS Agent Toolkit brings real-time docs, best practices, and guardrails to AI coding agents ⚡🤖 Less guessing. More building. ☁️🔥

Subramanya N3 months ago

does it show the IAM diff before an agent runs a command, or only after failure?

KnowDirect3 months ago

I like the direction here. AI agents can move fast, but pairing that speed with AWS-specific guidance is what makes them actually useful.

Back LLM Radar｜Syl3 months ago

This is the right direction. Up-to-date docs + MCP tools reduce agent guesswork. The next guardrail is runtime evidence: tool version, IAM/resource diff, command log, allowed/blocked reason, and rollback path. Otherwise success rate improves, but governance remains hard.

Arzoo Ai3 months ago

Agent Toolkit for AWS helps AI agents stay updated with accurate docs, best practices, and secure workflows for better AWS development. 🚀

Related Videos

AI agents can now connect to real cloud devices🔥 agent-device now supports BrowserStack and AWS Device Farm. Test, inspect, and debug on real devices in cloud instead of stopping at local simulators. » agent-device connect browserstack » agent-device connect aws-device-farm

AI agents can now connect to real cloud devices🔥 agent-device now supports BrowserStack and AWS Device Farm. Test, inspect, and debug on real devices in cloud instead of stopping at local simulators. » agent-device connect browserstack » agent-device connect aws-device-farm

Michał Pierzchała

12,743 views • 3 months ago

This is probably the biggest news yet in software going headless, and will bring knowledge work agents to the masses. The new ChatGPT agents have access to any of the tools and data you want to work with, with complete coding and tool use available to them. Here's an example of a custom sales assistant agent uses Box as a knowledge source for accessing enterprise content securely to answer questions and generate new content on the fly. The workflows can obviously vastly far more complex as the agent can use any of the tools within Box available via MCP and CLI. This precisely what agents will start to look like for knowledge work. You'll be able to spin them up in the foreground or background to help augment work. Big opportunity right now for headless platforms, and for all the new builders and designers of these agents in the enterprise.

This is probably the biggest news yet in software going headless, and will bring knowledge work agents to the masses. The new ChatGPT agents have access to any of the tools and data you want to work with, with complete coding and tool use available to them. Here's an example of a custom sales assistant agent uses Box as a knowledge source for accessing enterprise content securely to answer questions and generate new content on the fly. The workflows can obviously vastly far more complex as the agent can use any of the tools within Box available via MCP and CLI. This precisely what agents will start to look like for knowledge work. You'll be able to spin them up in the foreground or background to help augment work. Big opportunity right now for headless platforms, and for all the new builders and designers of these agents in the enterprise.

Aaron Levie

420,133 views • 5 months ago

Meet AMD Skills: A growing catalog of agent skills that helps AI coding assistants work more effectively with AMD hardware and software. Compatible with coding agents including Cursor, Claude Code, OpenAI Codex, and Gemini CLI, AMD Skills provides the knowledge, scripts, and best practices developers need to build faster on AMD. Why try it? → Install in seconds with the Skills CLI → Learn AMD best practices and workflows → Build AI applications from client to cloud → Pick only the skills you need Get started: npx skills add amd/skills Explore the project, install a skill, and let us know what you'd like to see next:

Meet AMD Skills: A growing catalog of agent skills that helps AI coding assistants work more effectively with AMD hardware and software. Compatible with coding agents including Cursor, Claude Code, OpenAI Codex, and Gemini CLI, AMD Skills provides the knowledge, scripts, and best practices developers need to build faster on AMD. Why try it? → Install in seconds with the Skills CLI → Learn AMD best practices and workflows → Build AI applications from client to cloud → Pick only the skills you need Get started: npx skills add amd/skills Explore the project, install a skill, and let us know what you'd like to see next:

AI at AMD

13,609 views • 2 months ago

AWS Startup Advisor now helps you build and migrate production-grade AI agents on AWS. Point it at your idea, prototype, or existing agent code. AWS Startup Advisor will analyze your stack, recommend the right combination of runtimes, models, memory, and guardrails, and generate a deployable POC, so you can validate before you commit. You can get started on Kiro, Claude Code, Cursor, and VS Code.

AWS Startup Advisor now helps you build and migrate production-grade AI agents on AWS. Point it at your idea, prototype, or existing agent code. AWS Startup Advisor will analyze your stack, recommend the right combination of runtimes, models, memory, and guardrails, and generate a deployable POC, so you can validate before you commit. You can get started on Kiro, Claude Code, Cursor, and VS Code.

Amazon Web Services

19,098 views • 1 month ago

AWS Startups offers AI-powered migration planning and execution for startups moving from GCP, OpenAI, or Gemini to AWS. Generate a personalized migration plan in minutes that includes service mapping, cost estimates, architecture diagrams, Terraform templates, credit eligibility, and a step-by-step runbook. When you're ready to execute, choose the path that works for you. Use the AI Agent for guided migration, work hands-on with an AWS expert, or get matched with a certified AWS Partner.

AWS Startups offers AI-powered migration planning and execution for startups moving from GCP, OpenAI, or Gemini to AWS. Generate a personalized migration plan in minutes that includes service mapping, cost estimates, architecture diagrams, Terraform templates, credit eligibility, and a step-by-step runbook. When you're ready to execute, choose the path that works for you. Use the AI Agent for guided migration, work hands-on with an AWS expert, or get matched with a certified AWS Partner.

Amazon Web Services

5,548,009 views • 2 months ago

Made in San Francisco with AWS: David Twizer, CEO & Co-founder, xpander.ai. Why SF? “For the AI agent space, this city is mission zero.” xpander enables teams to build and deploy AI agents with any framework, in any environment. With Amazon Bedrock, the startup can train models and AWS solutions, scaling their business much faster.

Made in San Francisco with AWS: David Twizer, CEO & Co-founder, xpander.ai. Why SF? “For the AI agent space, this city is mission zero.” xpander enables teams to build and deploy AI agents with any framework, in any environment. With Amazon Bedrock, the startup can train models and AWS solutions, scaling their business much faster.

AWS Startups

11,353,493 views • 5 months ago

A Crash Course on Building AI Agents! Here's what it covers: - What is an AI agent - Connecting agents to tools - Overview of MCP - Replacing tools with MCP servers - Setting up observability and tracing All with 100% open-source tools!

A Crash Course on Building AI Agents! Here's what it covers: - What is an AI agent - Connecting agents to tools - Overview of MCP - Replacing tools with MCP servers - Setting up observability and tracing All with 100% open-source tools!

Akshay 🚀

115,943 views • 1 year ago

AI power users are here and the case for agent-friendly software is materializing. Aaron Levie on agents outnumbering people 1000x: "If you start to imagine that we all have to build software for agents… we spend as much time now thinking about the agent interface to our tool as we do the human interface." "If you have a hundred or a thousand times more agents than people, then your software has to be built for agents… it's going to be through an API or a CLI or MCP." "What if you give a coding agent access to your SaaS tools and a coding agent access to your knowledge work, workflows and context?" "It can actually code its way or use APIs through whatever task it's trying to achieve." "That appears to be like a paradigm that is starting to compound… and I actually think it kind of makes sense as the ultimate manifestation of this stuff." Aaron Levie

AI power users are here and the case for agent-friendly software is materializing. Aaron Levie on agents outnumbering people 1000x: "If you start to imagine that we all have to build software for agents… we spend as much time now thinking about the agent interface to our tool as we do the human interface." "If you have a hundred or a thousand times more agents than people, then your software has to be built for agents… it's going to be through an API or a CLI or MCP." "What if you give a coding agent access to your SaaS tools and a coding agent access to your knowledge work, workflows and context?" "It can actually code its way or use APIs through whatever task it's trying to achieve." "That appears to be like a paradigm that is starting to compound… and I actually think it kind of makes sense as the ultimate manifestation of this stuff." Aaron Levie

a16z

42,152 views • 1 month ago

We just raised an $8M seed round to kill AWS, GCP, and Azure. Introducing the agent-native serverless cloud. Your team is shipping code like never before. But you're getting caught up in manual, tedious DevOps work trying to deploy it. InstaCloud provides the serverless compute that lets your services autoscale, with all the infrastructure managed for you. Agents branch into complete replica environments when working, keeping prod safe and iteration speed high. And of course, it all works seamlessly with agents through MCP/CLI. Get off the traditional, legacy cloud. Start deploying your services on InstaCloud today.

We just raised an $8M seed round to kill AWS, GCP, and Azure. Introducing the agent-native serverless cloud. Your team is shipping code like never before. But you're getting caught up in manual, tedious DevOps work trying to deploy it. InstaCloud provides the serverless compute that lets your services autoscale, with all the infrastructure managed for you. Agents branch into complete replica environments when working, keeping prod safe and iteration speed high. And of course, it all works seamlessly with agents through MCP/CLI. Get off the traditional, legacy cloud. Start deploying your services on InstaCloud today.

Hang Huang ☁️

1,396,745 views • 6 days ago

Important new course: Agent Skills with Anthropic, built with Anthropic and taught by Elie Schoppik! Skills are constructed as folders of instructions that equip agents with on-demand knowledge and workflows. This short course teaches you how to create them following best practices. Because skills follow an open standard format, you can build them once and deploy across any skills-compatible agent, like Claude Code. What you'll learn: - Create custom skills for code generation and review, data analysis, and research - Build complex workflows using Anthropic's pre-built skills (Excel, PowerPoint, skill creation) and custom skills - Combine skills with MCP and subagents to create agentic systems with specialized knowledge - Deploy the same skills across Claude Code, the Claude API, and the Claude Agent SDK Join and learn to equip agents with the specialized knowledge they need for reliable, repeatable workflows.

Important new course: Agent Skills with Anthropic, built with Anthropic and taught by Elie Schoppik! Skills are constructed as folders of instructions that equip agents with on-demand knowledge and workflows. This short course teaches you how to create them following best practices. Because skills follow an open standard format, you can build them once and deploy across any skills-compatible agent, like Claude Code. What you'll learn: - Create custom skills for code generation and review, data analysis, and research - Build complex workflows using Anthropic's pre-built skills (Excel, PowerPoint, skill creation) and custom skills - Combine skills with MCP and subagents to create agentic systems with specialized knowledge - Deploy the same skills across Claude Code, the Claude API, and the Claude Agent SDK Join and learn to equip agents with the specialized knowledge they need for reliable, repeatable workflows.

Andrew Ng

890,490 views • 8 months ago

🚀 Introducing the first-ever Agent UI 🚀 This is hands-down my favorite product! Chat with local Agents tailored to my needs. Local memory, storage, knowledge and tools 🔥 ⚡️ Your data, your control 🧠 Compatible with any LLM 🤝 Run multiple agents or a team of agents

🚀 Introducing the first-ever Agent UI 🚀 This is hands-down my favorite product! Chat with local Agents tailored to my needs. Local memory, storage, knowledge and tools 🔥 ⚡️ Your data, your control 🧠 Compatible with any LLM 🤝 Run multiple agents or a team of agents

Ashpreet Bedi

69,015 views • 1 year ago

Remote coding agents are now general purpose productivity tools Here I'm using the Todoist MCP server with Replit ⠕ Agent to clean up the reference section of my task list I'm also using it daily to add labels and keep things organized As it would turn out, coding agents are good for more than coding

Remote coding agents are now general purpose productivity tools Here I'm using the Todoist MCP server with Replit ⠕ Agent to clean up the reference section of my task list I'm also using it daily to add labels and keep things organized As it would turn out, coding agents are good for more than coding

matt palmer

35,917 views • 9 months ago

AI coding agents aren't just about autocorrect, but how do you get the best coding experience with an AI-powered coding agent? In our new short course, Build Apps with Windsurf’s AI Coding Agents, you'll learn how to build, debug, and deploy applications with agentic AI-powered integrated development environment (IDE). AI coding agents, like Codeium's @windsurf, don’t just suggest code, they analyze your codebase, track changes, retrieve relevant information, and apply updates across multiple files. They can help debug, refactor, and even modernize legacy frameworks. But to use them effectively, you need the right approach. This new course shows you how to: 🛠️ Use AI agents to build and refine applications, like a Wikipedia analysis app. 🐞 Debug and refactor JavaScript with AI-assisted automation. 🔍 Understand how search and retrieval power AI coding agents. 🤖 Guide an AI agent effectively—prompting, iterating, and correcting when needed. Taught by Anshul Ramachandran (Anshul Ramachandran), this course gives you hands-on coding experience, insights into how these AI systems work under the hood, and best practices to improve your development workflow. 🔗 Enroll for free:

AI coding agents aren't just about autocorrect, but how do you get the best coding experience with an AI-powered coding agent? In our new short course, Build Apps with Windsurf’s AI Coding Agents, you'll learn how to build, debug, and deploy applications with agentic AI-powered integrated development environment (IDE). AI coding agents, like Codeium's @windsurf, don’t just suggest code, they analyze your codebase, track changes, retrieve relevant information, and apply updates across multiple files. They can help debug, refactor, and even modernize legacy frameworks. But to use them effectively, you need the right approach. This new course shows you how to: 🛠️ Use AI agents to build and refine applications, like a Wikipedia analysis app. 🐞 Debug and refactor JavaScript with AI-assisted automation. 🔍 Understand how search and retrieval power AI coding agents. 🤖 Guide an AI agent effectively—prompting, iterating, and correcting when needed. Taught by Anshul Ramachandran (Anshul Ramachandran), this course gives you hands-on coding experience, insights into how these AI systems work under the hood, and best practices to improve your development workflow. 🔗 Enroll for free:

DeepLearning.AI

23,255 views • 1 year ago

Mech Marketplace: The 1st AI Agent Bazaar is here 🟪 🏪 The first active on-chain marketplace for AI Agents to sell their services, hire other AI Agents, and work together—with zero human input required. 3 things are now possible: 🟪 No more code upgrades: Your AI Agent can simply "hire" another Agent. 🟪 Agents can be monetized: You can "put your Agent to work" and earn. 🟪 TRUE autonomy: Agents can now work together autonomously.

Mech Marketplace: The 1st AI Agent Bazaar is here 🟪 🏪 The first active on-chain marketplace for AI Agents to sell their services, hire other AI Agents, and work together—with zero human input required. 3 things are now possible: 🟪 No more code upgrades: Your AI Agent can simply "hire" another Agent. 🟪 Agents can be monetized: You can "put your Agent to work" and earn. 🟪 TRUE autonomy: Agents can now work together autonomously.

Olas (formerly Autonolas)

53,373 views • 1 year ago

🚀 Today, we announced frontier agents, a new class of AI agents which are a step-function change in what you can do with agents. Our first three agents mark the beginning of a new era in software development: 🟠 Kiro autonomous agent maintains persistent context and learns over time while working independently, so you can focus on your biggest priorities. It can handle a range of tasks—from triaging bugs to improving code coverage—with a single change spanning multiple repositories. 🟠 AWS Security Agent is your virtual security engineer that helps build secure applications by being a security consultant for app design, code reviews, and penetration testing. 🟠 AWS DevOps Agent is your virtual operations team member that helps resolve and proactively prevent incidents. It is on call when incidents happen, instantly responding to issues and using its knowledge of your application and the relationship between components to find the root ause of the problem. More on how we’re helping customers driving towards an agentic future: #AWSreInvent

🚀 Today, we announced frontier agents, a new class of AI agents which are a step-function change in what you can do with agents. Our first three agents mark the beginning of a new era in software development: 🟠 Kiro autonomous agent maintains persistent context and learns over time while working independently, so you can focus on your biggest priorities. It can handle a range of tasks—from triaging bugs to improving code coverage—with a single change spanning multiple repositories. 🟠 AWS Security Agent is your virtual security engineer that helps build secure applications by being a security consultant for app design, code reviews, and penetration testing. 🟠 AWS DevOps Agent is your virtual operations team member that helps resolve and proactively prevent incidents. It is on call when incidents happen, instantly responding to issues and using its knowledge of your application and the relationship between components to find the root ause of the problem. More on how we’re helping customers driving towards an agentic future: #AWSreInvent

Swami Sivasubramanian

26,056 views • 10 months ago

New Course: ACP: Agent Communication Protocol Learn to build agents that communicate and collaborate across different frameworks using ACP in this short course built with IBM Research's BeeAI, and taught by Sandi Besen, AI Research Engineer & Ecosystem Lead at IBM, and Nicholas Renotte, Head of AI Developer Advocacy at IBM. Building a multi-agent system with agents built or used by different teams and organizations can become challenging. You may need to write custom integrations each time a team updates their agent design or changes their choice of agentic orchestration framework. The Agent Communication Protocol (ACP) is an open protocol that addresses this challenge by standardizing how agents communicate, using a unified RESTful interface that works across frameworks. In this protocol, you host an agent inside an ACP server, which handles requests from an ACP client and passes them to the appropriate agent. Using a standardized client-server interface allows multiple teams to reuse agents across projects. It also makes it easier to switch between frameworks, replace an agent with a new version, or update a multi-agent system without refactoring the entire system. In this course, you’ll learn to connect agents through ACP. You’ll understand the lifecycle of an ACP Agent and how it compares to other protocols, such as MCP (Model Context Protocol) and A2A (Agent-to-Agent). You’ll build ACP-compliant agents and implement both sequential and hierarchical workflows of multiple agents collaborating using ACP. Through hands-on exercises, you’ll build: - A RAG agent with CrewAI and wrap it inside an ACP server. - An ACP Client to make calls to the ACP server you created. - A sequential workflow that chains an ACP server, created with Smolagents, to the RAG agent. - A hierarchical workflow using a router agent that transforms user queries into tasks, delegated to agents available through ACP servers. - An agent that uses MCP to access tools and ACP to communicate with other agents. You’ll finish up by importing your ACP agents into the BeeAI platform, an open-source registry for discovering and sharing agents. ACP enables collaboration between agents across teams and organizations. By the end of this course, you’ll be able to build ACP agents and workflows that communicate and collaborate regardless of framework. Please sign up here:

New Course: ACP: Agent Communication Protocol Learn to build agents that communicate and collaborate across different frameworks using ACP in this short course built with IBM Research's BeeAI, and taught by Sandi Besen, AI Research Engineer & Ecosystem Lead at IBM, and Nicholas Renotte, Head of AI Developer Advocacy at IBM. Building a multi-agent system with agents built or used by different teams and organizations can become challenging. You may need to write custom integrations each time a team updates their agent design or changes their choice of agentic orchestration framework. The Agent Communication Protocol (ACP) is an open protocol that addresses this challenge by standardizing how agents communicate, using a unified RESTful interface that works across frameworks. In this protocol, you host an agent inside an ACP server, which handles requests from an ACP client and passes them to the appropriate agent. Using a standardized client-server interface allows multiple teams to reuse agents across projects. It also makes it easier to switch between frameworks, replace an agent with a new version, or update a multi-agent system without refactoring the entire system. In this course, you’ll learn to connect agents through ACP. You’ll understand the lifecycle of an ACP Agent and how it compares to other protocols, such as MCP (Model Context Protocol) and A2A (Agent-to-Agent). You’ll build ACP-compliant agents and implement both sequential and hierarchical workflows of multiple agents collaborating using ACP. Through hands-on exercises, you’ll build: - A RAG agent with CrewAI and wrap it inside an ACP server. - An ACP Client to make calls to the ACP server you created. - A sequential workflow that chains an ACP server, created with Smolagents, to the RAG agent. - A hierarchical workflow using a router agent that transforms user queries into tasks, delegated to agents available through ACP servers. - An agent that uses MCP to access tools and ACP to communicate with other agents. You’ll finish up by importing your ACP agents into the BeeAI platform, an open-source registry for discovering and sharing agents. ACP enables collaboration between agents across teams and organizations. By the end of this course, you’ll be able to build ACP agents and workflows that communicate and collaborate regardless of framework. Please sign up here:

Andrew Ng

105,758 views • 1 year 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

11,180 views • 4 months ago