/blog · playbook notes

Notes from the workshop floor.

Slow, careful posts on what we've learned shipping AI-native apps.

The Architectural Shift to Agentic OS: Inside the Transition to Autonomous Workflows and Shielded Execution

The software landscape is undergoing a profound paradigm shift: the transition from interactive, prompt-and-wait chat assistants to background-running, autonomous operating systems. Often described as the dawn of "Software 3.0," this movement represents an evolution where large language models (LLMs) transition from simple copilots to central operating engines capable of driving complex, multi-agent workflows.

May 31, 2026Read

4 min

Beyond the Chatbox: The Rise of Persistent Agentic Operating Systems and Next-Gen DevTools

The software engineering landscape is undergoing a massive paradigm shift. We are moving past the era of stateless, single-response chat boxes and entering an era dominated by persistent, autonomous "agentic" environments. Instead of writing short prompts and waiting for immediate replies, modern developers are orchestrating complex, multi-hour workflows.

May 30, 2026Read

5 min

Stateful Agents, Standardized Protocols, and Native UI: The Next Era of Developer Tooling

The developer landscape is undergoing a major transition. Engineers are moving past brittle, stateless LLM wrappers toward resilient, state-managing agentic systems on the backend, balanced by a return to high-performance, lightweight craftsmanship on the frontend. The current focus centers on building reliable developer tooling, predictable AI execution, and hardware-accelerated user interfaces.

May 30, 2026Read

6 min

Shipping agents in production: a checklist

A short, opinionated checklist for taking an LLM agent from a flashy demo to something you can actually keep on call for.

May 30, 2026Read

6 min

Four tool-calling patterns that hold up

After a year of shipping tool-using LLMs, four patterns keep showing up. The other twenty we tried did not.

May 30, 2026Read

5 min

Treat your evals as code

Evals are not a notebook you run once before launch. They are a test suite. Here is what that looks like in practice.

May 30, 2026Read

/newsletter · low-volume

New posts, straight to you.

One email when something new ships. No spam, unsubscribe anytime.