Gmail

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.

Dreamer: the Agent OS for Everyone — David Singleton

Mar 20, 2026 · 1:04:23

David Singleton, former Stripe CTO, introduces Dreamer, a consumer platform for discovering, building, and using AI agents and agentic apps centered on a personal Sidekick that acts as both companion and kernel-like traffic cop. He demonstrates building a conference schedule app in 25 minutes via natural language, a ski trip app that splits expenses, and tools like Gmail, Google Search, and live sports data feeds. Dreamer features an open tool ecosystem where builders get paid, a private waitlist skip at dreamer.com/latentspace, and a Builder-in-Residence program with a $10,000 prize for the best tool by mid-April. Singleton explains the OS model with Sidekick as kernel and agents as users enforcing data isolation and cross-agent coordination only through Sidekick. He shares insights on tiny-team building (six-person core, 17 total), hiring engineers who collaborate with coding agents, and LLMs' current lack of taste and creativity.

The AI Frontier: from Gemini 3 Deep Think distilling to Flash — Jeff Dean

Feb 12, 2026 · 1:23:31

Jeff Dean, Google's Chief AI Scientist, explains how the company's dual strategy of frontier "Pro" models and distilled "Flash" models, alongside co-designed TPUs and latency-optimization, keeps Gemini at the Pareto frontier. Distillation compresses high-capability large models into smaller, efficient ones, enabling Flash models to exceed earlier Pro generations. He emphasizes energy-based thinking: data movement costs thousands more picojoules than arithmetic, making batching and speculative decoding essential. TPU development requires predicting ML workloads 2–6 years out, often speculatively adding hardware features. Gemini was born after Dean wrote a one-page memo arguing that fragmented model efforts across Google Brain and DeepMind should merge into a single unified multimodal effort. Looking ahead, he predicts personalized models attending to all user data and reasoning speeds of 10,000 tokens/second will transform software engineering.

⚡️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.

Building Manus AI (first ever Manus Meetup)

Mar 27, 2025 · 48:59

Tao Zhang, co-founder of Manus, explains how Manus gives LLMs 'hands' to take real-world actions, inspired by MIT's 'mens et manus' (mind and hand). Manus assigns each task its own cloud virtual machine via E2B, provides pre-paid data APIs (stock, social media), and a knowledge system to remember user preferences. Their previous product, Monica.im, grew to 20M monthly active users and $50M ARR before they pivoted from a failed AI browser project to Manus. On the GAIA benchmark, Manus achieves a per-task cost of ~$2, far cheaper than OpenAI's Deep Research (~$20) and prior SOTA. Zhang emphasizes a 'less structure, more intelligence' philosophy, opting not to predefine workflows but to give the model rich context and tools. He also discusses plans to partner with Cloudflare, pay paywalls on behalf of users, and integrate more APIs based on usage patterns, while ruling out building their own foundation model.

Bee AI: The Wearable Ambient Agent

Feb 17, 2025 · 1:07:40

Bee AI's Maria and Ethan explain their wearable ambient agent, arguing that personal AI with continuous context is the future, and detail its $49.99 hardware, 7-day battery, and free inference. They trace their origin from a 2016 personal AI startup to Squad (sold to Twitter) and then to Bee, emphasizing that hardware was necessary because app friction (e.g., remembering to open it) killed the ambient experience. Privacy is addressed by not storing audio, only summaries, and offering geofencing and concept fencing to block sensitive topics. The software pipeline uses voice activity detection to reduce compute, speaker identification, and custom small models for memory retrieval instead of traditional RAG or knowledge graphs. Social features are in beta, with agent-to-agent negotiation—e.g., both agents coordinating a dinner reservation based on preferences and calendars. They are hiring AI engineers and see always-on AI as inevitable.