MCP

Notion’s Sarah Sachs & Simon Last on Custom Agents, Evals, and the Future of Work

Apr 15, 2026 · 1:25:37

Sarah Sachs and Simon Last of Notion explain how Custom Agents were rebuilt four to five times since 2022, with early attempts failing due to lack of tool-calling standards and short context windows. They shifted from few-shot prompting to tool definitions and progressive disclosure, now supporting over 100 tools. Their eval system includes frontier evals that pass only 30% to gauge model progress, and they employ Model Behavior Engineers to write evals and triage failures. The episode covers their views on MCP versus CLI, meeting notes as data capture, and the software factory concept of agents collaborating to develop codebases. They also discuss Notion's culture of low-ego, high-velocity rebuilding and the philosophy that every surface must work for both humans and agents.

Extreme Harness Engineering: 1M LOC, 1B toks/day, 0% human code or review — Ryan Lopopolo, OpenAI

Apr 7, 2026 · 1:17:54

Ryan Lopopolo of OpenAI's Frontier team details his team's extreme experiment in harness engineering: building a 1M LOC internal Electron app with zero human-written or reviewed code, relying instead on Codex agents that process 1B tokens daily ($2-3k/day). He argues that humans are the bottleneck and that teams should encode non-functional requirements into specs, skills, and observability tooling rather than prompting agents to 'try harder.' The result is Symphony, a ghost library spec and Elixir reference implementation that automates the entire pull-request lifecycle, including self-review and merge. Lopopolo explains how the team scales by treating software as agent-legible text, using worktrees for multi-agent collaboration, and feeding agent mistakes back into the repository via docs like core-beliefs.md. He also discusses Frontier's enterprise platform for safe agent deployment, noting that success depends on giving agents full context—even company culture and inside jokes—so they can act as full teammates.

Anthropic’s Felix Rieseberg on AI Coworkers, Local-First Agents, and the Future of Knowledge Work

Mar 17, 2026 · 1:27:34

Anthropic's Felix Rieseberg explains how Claude Cowork—a VM-based, user-friendly version of Claude Code—was built from pre-existing prototypes in ten days, and why putting AI 'where you work' on the local machine is more powerful than cloud-only approaches. He argues that Silicon Valley undervalues the local computer, comparing it to how we all use MacBooks instead of iPads. The VM gives Claude its own computer, enabling it to install tools and run scripts without constant approval, serving as both a safety boundary and a capability unlock. Rieseberg contrasts Cowork's evaluation on knowledge work tasks (e.g., mortgage management, tax filing) with Claude Code's coding evals, and explains the shift from MCPs to file-based skills—markdown files that tell the model what to do. Real use cases include organizing desktops, uploading videos, and filing taxes. He also expresses concern about the impact on junior employees and hints at future work on autonomy, multiplayer coordination, and portability.

[State of Context Engineering] Agentic RAG, Context Rot, MCP, Subagents — Nina Lopatina, Contextual

Dec 31, 2025 · 26:48

Nina Lopatina of Contextual AI discusses the state of context engineering, arguing that while the field is still in prototyping, 2025 will see true scale with full-system design patterns. She notes that agentic RAG—especially query reformulation into subqueries—has become the baseline, dramatically improving retrieval. Context rot is widely cited but industry benchmarks at real scale (100k+ documents, billions of tokens) remain rare. MCP is both a driver and a flaw: giant JSON tool definitions stuff the context window, yet MCP servers enable rapid prototyping before optimizing down to direct API calls. Sub-agents with turn limits are critical—unlimited agency degrades performance and causes hallucinations. Instruction-following re-rankers are essential for scaling retrieval across massive databases, providing more recall upfront and precision in the final context. Benchmarks are being saturated faster than ever: a Princeton benchmark from October was saturated by Claude Code in weeks, with solutions so good the gold dataset had errors. Lopatina also shares a lesson from using ChatGPT as a snowboarding coach—after several months of training for a 25-lap mogul race, she had to close…

One Year of MCP — with David Soria Parria and AAIF leads from OpenAI, Goose, Linux Foundation

Dec 28, 2025 · 1:39:19

David Soria Parra, MCP lead at Anthropic, along with Jim Zemlin (Linux Foundation CEO), Nick Cooper (OpenAI), and Brad Howes (Block/Goose), recount the one-year evolution of the Model Context Protocol from a local experiment to the de facto standard for agentic systems, now donated to the new Agentic AI Foundation. They detail four spec releases—from local stdio to remote HTTP streaming, OAuth 2.1 authentication (and enterprise lessons learned), long-running tasks, and MCP Apps (iframes for richer UI)—and explain why internal enterprise adoption is exploding faster than expected, mostly invisible and at massive scale. The group reveals how three competitive AI labs came together to donate protocols and agents to a neutral foundation, how the foundation will balance taste-making (curating meaningful projects) with openness, and their 2025 vision: MCP as the communication layer for asynchronous, long-running agents that discover and install their own tools, unlocking another order of magnitude in AI productivity.

Anthropic, Glean & OpenRouter: How AI Moats Are Built with Deedy Das of Menlo Ventures

Nov 14, 2025 · 1:26:59

Deedy Das of Menlo Ventures returns to explain how Anthropic became the fastest-growing software company ever (zero to billions in revenue) and why Glean’s boring enterprise search moat of hard integrations and ranking problems is harder than competitors think. He reveals the $100M Anthology Fund’s strategy: backing OpenRouter, Goodfire, Prime Intellect, and Whisper—companies that solve thorny infrastructure or research problems rather than chasing apps. Das argues that model-layer companies will capture most value because building great models is harder than building apps, and that Anthropic’s product innovations like Claude Code emerge from a culture that lets researchers experiment freely. He also warns that vibe coding is becoming a cognitive crutch for engineers, eroding deep problem-solving skills, and discusses how enterprise AI market share has shifted dramatically: OpenAI went from 50% to 20%, while Anthropic rose from 12% to 32% of enterprise LLM API spend.

Breaking AI to Fix It: Ian Webster's Journey from Discord's Clyde to Promptfoo's $18M Series A

Oct 24, 2025 · 43:17

Ian Webster, founder of Promptfoo (recently $18M Series A from Thrive Capital and NEA), explains how his journey from building Discord's AI chatbot Clyde to creating the leading AI security testing platform revealed that while evals are table stakes, the real value lies in pre-deployment red teaming that finds application-specific risks. Webster argues that traditional guardrails are insufficient—'you can't fix stupid'—and that Promptfoo uses AI-versus-AI techniques to generate tailored attacks for each app's business context. Over 10% of Fortune 500 companies now use Promptfoo, and he discusses the evolving challenges of MCP security (mostly 'glorified API wrappers') and the need for IDE plugins and code-aware discovery to keep up with increasingly complex agents running 30-minute tasks. The episode also covers why security sales in AI is uniquely hard, how open source builds trust in a space full of 'snake oil,' and why the future of AI security must shift from runtime protection to earlier testing in CI/CD.

Terminal-Bench: Pushing Claude Code, OpenAI Codex, Factory Droid, et al to the limits

Oct 18, 2025 · 35:27

Alex Shaw and Mike Merrill, creators of Terminal-Bench, explain how their coding agent benchmark became an industry standard adopted by Anthropic, OpenAI, and leading agent companies. They bet on terminal-based interaction over GUI because text is the modality that works best with models, and designed tasks as containerized environments with instructions and test scripts. Nicholas Carlini at Anthropic became an early champion, leading to Terminal-Bench being featured on Claude’s model card without notice. They built the minimal Terminus agent to isolate model capabilities from agent optimizations, and their framework adapts existing benchmarks like SWE-bench. Future plans include cloud hosting, multi-dimensional evaluation incorporating cost and economic value, and enabling RL post-training on benchmark tasks.

DevDay 2025: Apps SDK, Agent Kit, MCP, Codex and why Prompting is More Important than Ever

Oct 7, 2025 · 44:52

Sherwin Wu and Christina Huang from OpenAI's platform team discuss the new AgentKit suite and Apps SDK, arguing that visual agent builders and prompt optimization remain critical for production AI. They detail AgentKit's components—Agent SDK, visual Builder, Evals, and Tool Registry—and how Apps SDK inverts the website-chatbot paradigm by embedding apps inside ChatGPT. OpenAI adopted Anthropic's MCP protocol for tool connectivity, and the team dogfoods these tools for their own customer support at openai.com. They explain that automated prompt optimization and evaluation pipelines are essential for scaling agents, and share how Codex is used internally for code generation and PR reviews. The episode also covers the Service Health Dashboard for real-time API SLO tracking, reflecting OpenAI's reliability investments.

⚡️Claude Sonnet 4.5 and Anthropic's roadmap for Agents and Developers — Mike Krieger, Anthropic

Sep 30, 2025 · 26:25

Mike Krieger, Anthropic's CPO, discusses the launch of Claude Sonnet 4.5 and its implications for AI development, emphasizing the growing symbiosis between product and research teams. He describes his personal 'vibe evals' for new models, including generating a Virtual Boy-style game and a Nintendo board presentation, and notes that Sonnet 4.5 traffic eclipsed Sonnet 4 on day one. Krieger explains how Anthropic is improving model output quality across UIs, Excel, and PowerPoint, and highlights the shift toward interactive planning rather than pure autonomy. He reveals the rename of the Claude Code SDK to the Claude Agent SDK, reflecting its general-purpose use for complex agentic workflows beyond coding. Krieger stresses the need for better visual understanding in models and invites developers to share feedback on hard challenges to help improve the platform.

Context Engineering for Agents - Lance Martin, LangChain

Sep 11, 2025 · 1:03:18

Lance Martin from LangChain discusses context engineering for AI agents, arguing that managing context from tool calls is the key challenge and introducing five techniques: offloading, reducing, retrieval, caching, and context isolation. Offloading saves raw tool call outputs to disk and passes only summaries, drastically cutting token usage—Martin's deep research agent went from 500,000 tokens per run to much less. Manus uses file system offloading and warns that irreversible pruning risks information loss, while Cognition advocates fine-tuned summarization for agent-agent boundaries. For retrieval, Martin contrasts Windsurf's multi-step indexing with Claude Code's agentic search using grep and llms.txt, finding the latter more effective. He applies the Bitter Lesson to agent engineering: his own Open Deep Research evolved from a highly structured workflow to a simple agent loop as models improved, and he warns against rigid abstractions that hinder adaptation.

⚡️Composio: 10,000+ tools that evolve for Agents — Karan Vaidya and Soham Ganatra

Aug 4, 2025 · 22:09

Composio co-founders Karan Vaidya and Soham Ganatra join Swyx and Alessio to discuss their platform for self-evolving agent skills, now with 25,000+ actions and 100,000+ developers. They explain how MCP's client-side limitations led them to build a learning infrastructure that analyzes agent usage patterns to improve tool reliability over time. The team uses agents to build and maintain 95% of their 500+ integrations, adding 35 per week, with plans for 5,000 by year-end. They reveal that more than 20-25 actions confuse LLMs, so they offer a natural-language execution tool and dynamic tool exposure via MCP. Key challenges include enterprise APIs with poor documentation and the need for dev environments. Composio's internal agent benchmarks and A/B testing infrastructure optimize tool schemas for LLM calling.

[AIEWF Preview] Containing Agent Chaos — Solomon Hykes

Jun 3, 2025 · 27:14

Solomon Hykes, creator of Docker and founder of Dagger, argues that the industry needs an open standard for AI coding agent environments to avoid repeating the fragmentation seen before Docker. Dagger, a workflow engine originally built for post-development automation (CI/CD), is now being pulled by its community into the agentic space to solve environment isolation, portability, and observability for concurrent agent teams. Hykes insists containers are the right base layer but require a new, agent-native UX—unlike legacy Dockerfile or Compose—that is decoupled from any IDE, model, or cloud provider. He critiques current vertical monoliths (e.g., proprietary IDE-hosted agent environments) and advocates for a Lego-like modular approach where the environment is the standard linchpin. Dagger integrates with existing stacks rather than replacing them, and Hykes previews fresh, unreleased content for his upcoming keynote at AI Engineer World's Fair.

⚡️Open Questions in Agentic RL — Will Brown (Prime Intellect)

May 9, 2025 · 17:13

Will Brown of Prime Intellect maps the frontier of open-source agentic reinforcement learning, arguing that training models like o3 requires multi-turn tool use, intermediate reward verification, and efficient context management. He outlines challenges such as scaling tool calls to hundreds (e.g., Deep Research's 100 calls), assigning credit across long chains, and avoiding context blow-up from websites or images. Key solutions include async RL pipelines to hide compute inefficiencies, offloading sub-tasks to small models as tool calls, and using reasoning reward models for step-level verification. Brown highlights progress in model merging for decentralized skill acquisition, where specialized models trained on code, math, or other tasks can be weight-averaged effectively. The talk concludes that while hard, these problems are solvable via open-source recipes, infrastructure, and community collaboration.

Claude Code: Anthropic's CLI Agent

May 7, 2025 · 1:16:22

In this episode, Boris Cherny and Cat Wu from Anthropic discuss Claude Code, a CLI-based coding agent they describe as a Unix utility rather than a polished product, emphasizing raw model access and simplicity. The tool started as Boris's personal experiment, then spread internally after engineers used it daily, with Anthropic's product principle of 'do the simple thing first' guiding features like memory via markdown files and context compaction by asking Claude to summarize. They ship updates including web fetch, auto-accept, and thinking via chain of thought, and note that 80% of Claude Code's code is written by Claude Code itself. Average spend is $6/day per user versus $20/month for Cursor, and Boris reports a personal 2x productivity gain, with some engineers seeing 10x. The team is growing and investigating open-sourcing the tool, while continuing to build for the terminal as a raw, composable utility for power users.

Why Every Agent needs Open Source Cloud Sandboxes

Apr 24, 2025 · 1:06:39

Vasek Mlejnsky, CEO of E2B, explains how his company grew from 40,000 sandboxes in March 2024 to 15 million in March 2025 by providing cloud sandboxes for AI agents. Originally built from DevBook's interactive docs playground, E2B now serves use cases from code interpreting and data analysis to Computer Use and reinforcement learning with Hugging Face's Open R1. The sandboxes are general Linux VMs with fast startup, security isolation, and persistence, handling untrusted code and allowing forking/checkpoints for parallel agent execution. Mlejnsky discusses the LLMOS landscape, pricing challenges (moving from token-based to value-based), MCPs as higher-order tools, and why he relocated from Prague to San Francisco to be closer to users. E2B is hiring across engineering and customer success as it aims to become full-lifecycle infrastructure for LLMs.

Claude Plays Pokémon Hackathon: Escape from Mt. Moon!

Apr 5, 2025 · 1:15:00

David Hershey (creator of Claude Plays Pokémon), Andrew (a developer building a Pokémon-playing virtual streamer), and Jesse Han (Morph Labs CEO) detail how to build agents that escape Mt. Moon in Pokémon FireRed using Anthropic's Claude and Morph Cloud's Infinibranch technology. Hershey explains that Claude's vision is often unreliable—it spent 8 hours pressing A on a doormat thinking it was a dialogue box—and that spatial reasoning remains a core bottleneck, best mitigated by touchscreen controls rather than prompt engineering. Andrew reveals he relied on reading raw RAM and A* pathfinding rather than computer vision, calling it “cheating” but pragmatically useful: his biggest breakthrough was a single prompt line telling the agent to try something else if it fails to grab a starter Pokémon. Jesse introduces Morph's EVA agent framework, which uses low-overhead snapshotting for test-time search, and the hackathon's judging criteria—escape Mt. Moon in the fewest agent turns, with a $1,000 prize for the coolest use of Infinibranch branching. The episode serves as both a technical walkthrough and a challenge to build general-purpose agents that can handle complex, open-ended tasks…

The Creators of Model Context Protocol

Apr 3, 2025 · 1:20:21

Justin Spahr-Summers and David Soria Parra, co-creators of Anthropic's Model Context Protocol (MCP), explain its origin as a solution to the M×N integration problem they experienced when copying data between Claude Desktop and IDEs. They detail MCP's design inspirations from LSP, its three core primitives (tools for model-driven actions, resources for app-controlled data, and prompts for user-initiated macros), and why they chose JSON-RPC with stateful connections. The episode contrasts MCP with OpenAPI, discusses client control and trust in servers, and outlines the future roadmap including a streamable HTTP transport and remote-server authorization via OAuth 2.1. The guests express a wish for more sampling clients and full spec support, and emphasize that MCP is an open, multi-company project with community commit access.

npm install Agents — with Sunil Pai and Rita Kozlov (VP AI) of Cloudflare

Mar 19, 2025 · 35:36

Shawn Wang hosts Sunil Pai and Rita Kozlov to discuss Cloudflare's new Agents product, which uses Durable Objects to provide a scalable, stateful runtime for building AI agents. Sunil built an initial prototype in two weeks, which Rita helped polish into a full SDK and starter kit. They demo a chat agent with persistent state, human-in-the-loop confirmation, and built-in scheduling via cron, all running on Durable Objects without Kubernetes. The conversation covers local-first syncing (Durable Objects as always-on sync clients), the need for observability across millions of agents, and excitement about MCP for easy integrations. Rita teases upcoming "durable object enabled containers" to bridge long-running and CPU-heavy workloads, and a new browser rendering REST API launching the same day.

Why every AI Engineer needs an AI Gateway (ft Portkey.ai CEO)

Feb 5, 2025 · 31:18

Rohit Agarwal, CEO of Portkey, explains why every AI engineer needs an AI gateway: an operational platform that connects to LLMs more efficiently, handling routing, observability, guardrails, and cost management. He notes that 90% of production use cases don't use automatic routing, but reasoning models and agents are driving new routing demands. Portkey's open-source gateway minimizes latency with a 21 MB memory footprint using JSON transformers. Key jobs include routing, observability (monitoring price, performance, accuracy), guardrails (e.g., regex-based, empty output detection, PII redaction), and human feedback tied to business metrics like video download rates. Rohit also highlights MCP adoption for simplifying agent-to-service connections, with bidirectional communication via RPC.