12 posts found
Learn how base compiles one vendor-neutral canon into native agent config for Claude Code, Codex, and GitHub Copilot — with drift protection in CI.
Explore three projects that treat agent config as compiler output: validated sources in, drift-gated artifacts out — base, skillsmith, and ObjectCore.
Explore how ObjectCore serves one plugin marketplace from git in dev and a database in production — same pure function, SHA-pinned, provenance-attested.
Learn how I built a deep research agent that fans out across sources, then refutes its own findings with three skeptics before reporting a single cited claim.
Learn why I moved agent orchestration into durable workflow steps instead of a coordinator agent, and the model, safety-gate, and cost tradeoffs it carried.
Map OS abstractions to Claude Managed Agents architecture and build a three-agent auto-PR pipeline that plans, codes, and reviews autonomously.
Discover how Claude Managed Agents replaces months of custom agent infrastructure with a decoupled architecture that cuts time-to-first-token 60%.
Explore Chrome's WebMCP protocol that lets websites expose structured tools to AI agents, replacing brittle scraping with stable, typed APIs.
Four AI orchestration systems taught me that 19 agents produce more drift than 3 supervised ones. STUDIO adds confidence scoring and preference learning.
Build an autonomous coding agent that cuts context switches from 20 to 3 per feature using phased planning, ReAct execution, and persistent self-learning.
Replace generic linters with 50 platform-specific rules per CMS. Specialized Claude Code plugins outperform general agents for Sitecore and Umbraco analysis.
An autonomous coding agent executed 47 stories across 6 epics, producing 4,200 lines of code and Lighthouse 99 performance with two hours of human input.