Build Notes
Real shipping logs. Iterations, failures, design trade-offs, and lessons learned from building AI systems and automation tools.A transparent development archive focused on practical lessons and problem-solving, not polished blog posts.
Building an AI Dev Team: Hierarchical Multi-Agent Orchestration
How I structured two coding CLIs and a set of model-tiered workers into a role-based agent company with a team lead, a manager, and specialized implementers.
Self-Generating Chatbot QA: An LLM-as-Judge Evaluation Pipeline
An automated pipeline that generates test questions from a chatbot's own source documents, scores answers with a frontier LLM, and leaves final judgment to a human.
Automated Pre-Deployment Risk Audits with a Read-Only Code Agent
A recurring feature-ledger review where a read-only code agent deep-reads candidate features and emits strict structured risk reports before deployment.
A Slack-Triggered Autonomous Incident-Response Agent
A live local service that watches Slack incident channels and automatically drafts remediation plans through a read-only agent planning queue.
An Agent That Applies for Government Funding
A launcher-triggered routine that discovers new government startup-support programs daily, spawns a sub-agent per program, and drafts submission-ready applications.