playbooks

Playbooks is a full semantic programming system for AI agents: a structured Markdown surface language for specifying agent behavior, a semantic intermediate representation called PBAsm, a compiler from Markdown to PBAsm, and a durable runtime that executes PBAsm with the determinism of traditional software and the flexibility of an LLM. Agents are modeled as classes with public playbooks (methods), triggers (event decorators), instance state, and a real call stack. It shipped on PyPI as playbooks through 16 releases ending at v0.7.4, spawned an org-scale ecosystem of sibling projects (VSCode debugger, fine-tuned LM, durable runtime extracted as OSS, docs site, enterprise edition), and was the result of three years of sustained solo work (2022–2026) on a single thesis: natural language as a programming language.

Notable as a complete system that took the idea seriously - PBAsm as an IR, class-based agent modeling with triggers, a VSCode debugger for natural-language programs in May 2025 well ahead of the industry, and an explicit forward-compatibility principle. It was officially sunset on April 5, 2026; the published retrospective in the repo README argues honestly why the generalist-agent-plus-skills approach won, with Anthropic Skills becoming the de facto standard the prior October.