LIVE⚡Featured Article
Ollama Typed Decisions vs JSON: A Local Ticket Routing Test
Test typed decisions, prompted JSON, and schema output on multilingual tickets, including routing errors and manual review.
Latest Entries
Beads Worker Recovery: Leases, Stale Owners, and Concurrency
Recover crashed AI workers with Beads, reject stale completion, and test concurrent task readiness in an isolated CLI lab.
When an Agent Remembers the Attack: Memory Poisoning and Recovery
Follow a runnable support-agent lab from persistent memory poisoning to selective recovery and a clean retest.
n8n Agents vs AI Agent Workflows: State, Memory, and Postgres
Compare n8n Agents and AI Agent workflows with a support-ticket example: sessions, Postgres state, approvals, and safe retries.
BCO + Critical Boiler: From a Project Brief to an AI Development Workflow
A first look at Better Codex Orchestrator: automatic task planning, adjustable autonomy, specialist agents, traceable execution, and collectible characters.
Critical Boiler: Codex-Ready Projects Without Burning Context on Boilerplate
Why I built Critical Boiler, a stack-aware CLI that generates agent instructions, AI docs, implementation skills, styling foundations, and safer starter files before the real product work begins.
How to Integrate Beads into an AI-Orchestrated System for Agentic Task Planning
Integrate the Beads CLI with planner and worker agents using JSON output, real dependency edges, atomic claims, and an explicit adapter contract for review and completion.