For builders using
coding agents.
Emerging practices for building with AI.
We help you see new angles, try better approaches, and build more powerful things.
Play latest episodeLATEST EPISODE
EP 14The Missing Piece for AI Agents That Keep Working
An agent that handles new GitHub issues needs to keep working through crashes, restarts, and changes in who's using it. Pi Durable gives you a foundation for building that kind of persistent workflow. The key is separating agent state from the process running it. Cloudflare Durable Objects can give that state a shared cloud home, with execution triggered by requests and configured wakeups. In this episode, we explain how the two fit together, use an interrupted refund to examine recovery, and look at shared chat, runtime reloads, and a phone-local agent. We also discuss what stored task state could reveal without advancing the agent.
EP 14 · OCT 22, 2026 · 43 MIN
Recent episodes
VIEW ALL EPISODES
EP 13How to Make Coding Agents Faster: Crabbox + 3 Fixes
Your coding agent can spend more time waiting for tests and builds than writing code. As inference gets faster, tool calls can become a larger share of the wait. Speeding up that feedback loop means examining which checks run, how they run, and where they run. Crabbox, from Peter Steinberger and the OpenClaw team, keeps agents local while expensive work runs on other machines. In this episode, we share our experience offloading Electron tests with Crabbox, discuss the tradeoffs of selective testing and parallel verification, and look at faster tools such as Oxlint and a custom Swift linter. We also discuss which optimizations are worth the effort.
EP 12How to Build AI Agents Like Dots, Instinct, Muse & Grok Bot
How do you build an agent like Dots, Muse, Instinct, or Grok Bot? Start high up the stack, and move down only when you need more control. Vishnu Krishnaprasad, founder of YC F26 startup Agent37, explains when to use Hermes, OpenClaw, or Pi, why each user needs a separate sandbox, and how to turn a proven manual workflow into skills. He also demos a Dots-like agent built on Hermes.
EP 11How to Use Bend2 to Verify Code Written by Coding Agents
Your coding agent can write code and prove that it follows a rule you specify, for every allowed input. We use Bend2 to show how to choose rules worth proving, get the agent to work through the proofs, and decide where the extra effort pays off. You can start with one important part of an existing app; you still decide whether those rules capture what you actually want.
From the blog
VIEW ALL POSTS
4 things worth building with Pi Durable and Cloudflare Durable Objects
Durable workflows, shared team agents, agents that run anywhere, and new tools built on persistent agent state.
4 Emerging Practices for Building with Taste in the Age of AI
How to express taste in forms a model can use: harnesses, expert language, tool interfaces, and oracles.