Daily Brief

Your agent shouldn't run on your laptop. Give it its own computer in the cloud, with one API call. Philipp Schmid from Google DeepMind walks through the Gemini Interactions API, Google's new API for both models and agents. It handles server-side state, long-running background jobs, and built-in plus custom tools across text, audio and images, and it replaces user/model turns with a timeline of steps. Then he shows the Antigravity agent in the Gemini API, which runs the same harness as Antigravity in its own managed cloud sandbox. Agents can run code, install tools, share environments with oth

If you run Claude and Codex side by side, you're the router passing messages between them. It doesn't have to be that way. Vlad Luzin, co-founder and CTO of BAND, argues the future belongs to AI agents talking to other AI agents, inside companies, between companies, and between businesses and consumers. Most of us already run multi-agent systems by hand, copying output between a planning session and a reviewing session, and loop engineering just hands that job to a script. He explains why: a single agent suffers from confirmation bias and attention dilution, no matter how big its context. The

Engineers are going from typing code to governing agents. The next step is a system that turns bug reports into production code. Davis Palmie, member of technical staff at Factory, explains the software factory: a system of agents that takes input signals like bug reports and user feedback and turns them into production code. He covers the questions every leader asks, from runaway costs and model choice to what happens to engineers and org charts, and argues coding was never the bottleneck: review, debugging, docs and testing are. He lays out the principles a factory needs (model-agnostic, so

Full episode: https://youtu.be/LwQQ7nBCGSs Me on twitter: https://x.com/dwarkesh_sp

Attackers use AI too, and the fastest AI attack he cites took four minutes. A pen test once or twice a year can't keep up. Eli Cohen of Snyk, co-founder of the runtime security company Helios, explains why security has to go on the offense in an agent-first world. Developers now ship far more code, much of it insecure, while attackers use frontier models to chain small vulnerabilities into critical ones in minutes. He walks through why traditional tools fall short: static scanning misses runtime issues, dynamic testing misses business logic, and human pen tests are expensive and happen only a

Luca Ferrari is co-founder and CEO of Bending Spoons, a serial acquirer of AOL, Vimeo and Evernote, Airtable, etc, that buys to hold forever, and whose only real edge is that it operates software companies better than almost anyone else. Bending Spoons got 800,000 job applications last year and hired fewer than 300 people. Luca runs hiring the way a quant runs a portfolio — hundreds of signals tested against future performance — and he's blunt about what the data says. Harvard and Stanford barely predict anything. Interviews are the worst signal in the process unless they're scripted. The bes

a16z Partner Kimberly Tan sits down with Vesta co-founder and CEO Mike Yu to discuss why rebuilding the mortgage industry requires more than layering AI agents onto legacy software. Mike explains why Vesta chose to replace the core system of record used by mortgage lenders, despite the complexity of building in one of the most heavily regulated industries. They discuss how outdated data architecture limits automation, how Vesta is using AI agents to handle mortgage workflows, and what it takes to earn the trust of lenders moving mission-critical operations onto a new platform. They also deba

Full episode: https://youtu.be/LwQQ7nBCGSs Me on twitter: https://x.com/dwarkesh_sp

Agents finish a task, then forget what they learned. Retrieval alone won't fix that. Will Lyon, senior product manager at Neo4j, explains why agent memory built on embeddings and retrieval isn't enough: recall isn't actionable knowledge. Agents need knowledge that is connected, typed and traceable. He shows Neo4j's model of agent memory as a context graph with short-term, long-term and reasoning memory, covering entity extraction and resolution, shared ontologies, and decision traces that let many agents learn from each other. Then he turns memory into action: distilling grounded, governed sk

Coding agents are great inside one repo. Postman has 115 microservices and thousands of endpoints. Kamalakannan Nandagopal, staff engineer at Postman, shares how Postman made coding agents work across a real distributed system. Docs go stale, skills and MCPs are only as good as their context, and agent memory stays stuck with one person. Borrowing from Postman's go-to-market team, they realized APIs are the context layer, and built an API context graph that maps every service, endpoint, implementation and call, all the way down to databases, with every data point grounded in code or productio

Let the model decide what should happen next. Never let it improvise how a production cluster gets restarted. Viren Baraiya, co-founder and CTO of Orkes and the original creator of Netflix Conductor, explains how to run agents in production. Real agents aren't just chatbots: they run on schedules, react to events, coordinate other agents and can run for months, so the harness around them starts to look like an application, much like a set of microservices. His key idea is a clean split between the brain and the hands. The LLM plans what should happen next; a deterministic, durable harness doe

Handing people AI tools doesn't change how they work. Giving them real time to learn does. Em Shreve, head of AI enablement at Automattic, the company behind WordPress.com and Tumblr with over 1,400 people in 82 countries, explains how a fully remote company builds AI fluency. Their bet: people need real time to learn, not just tools. So they run two-week, in-person programs that are half workshops and half real project work, for engineers, cross-functional teams and non-technical groups like finance and leadership. She covers the curriculum (skills, MCPs, hooks, autonomous agents) and why it

From building AI systems that reason over noisy physical experiments to creating laboratories where every instrument can become intelligent, Periodic Labs is betting that the next frontier of AI won’t come from simply training on more internet data — it will come from letting models experiment with the real world. In this episode, Periodic Labs’ Liam Fedus and Ekin Dogus Cubuk join swyx and Brandon to explain why scientific discovery is fundamentally different from math and coding, and what it takes to build AI scientists that can actually discover new materials. We go deep on Periodic’s visi