Archive

Builder Log

Builder Log is where I document experiments with agentic AI, automation workflows, local systems, and the messy work of making useful tools reliable. These notes are less about the tool itself and more about what the build teaches.

Builder Log Mar 29, 2026 10 min read
Adding Real-Time Web Search to Your AI Agent: Tavily, Exa, and What Changed
Tavily and Exa add dramatically better web search to an AI agent. What each does, when to use which, step-by-step…
Adding Real-Time Web Search to Your AI Agent: Tavily, Exa, and What Changed
Builder Log Mar 24, 2026 9 min read
Personal Finance Automation with Firefly III, SimpleFIN, and an AI Agent
Self-hosted personal finance tracking without SaaS subscriptions. Firefly III for accounting, SimpleFIN for bank feeds, and an AI agent to…
Personal Finance Automation with Firefly III, SimpleFIN, and an AI Agent
Builder Log Mar 22, 2026 6 min read
What Background Jobs Taught Me About Reliable AI Agents
Moving 18 scheduled AI jobs from cloud to local looks like a cost exercise. It is really a reliability audit:…
What Background Jobs Taught Me About Reliable AI Agents
Builder Log Mar 20, 2026 8 min read
When AI Memory Gets Too Complicated: Lessons from Replacing a Broken Plugin
A memory plugin that controls what the agent remembers controls the agent. What I found when I audited mine, why…
When AI Memory Gets Too Complicated: Lessons from Replacing a Broken Plugin
Builder Log Mar 11, 2025 8 min read
What a Week-Long AI Gateway Incident Taught Me About Reliability
A week of gateway instability reveals failure modes that stable operation hides. What I rebuilt — and the five design…
What a Week-Long AI Gateway Incident Taught Me About Reliability
Builder Log Feb 25, 2025 7 min read
The Hook System Trap: Three Gateway Crashes and One Design Lesson
Three real crashes from the same misconfigured hook pattern — and the architecture insight that finally stopped them. The lesson…
The Hook System Trap: Three Gateway Crashes and One Design Lesson
Builder Log Feb 18, 2025 7 min read
The Heartbeat Problem: Monitoring an AI Agent That Never Stops Running
An always-on AI agent that is up but silently failing is worse than one that crashes loudly. The monitoring architecture…
The Heartbeat Problem: Monitoring an AI Agent That Never Stops Running
Builder Log Jan 28, 2025 6 min read
What AI Agents Should Remember — and What They Should Never Store
Credential discipline and memory architecture for a self-hosted AI agent. The practical rules that prevent security nightmares and memory drift.
What AI Agents Should Remember — and What They Should Never Store
Builder Log Jan 21, 2025 6 min read
Building a Draft-First AI Publishing Pipeline: Five Things That Broke
Building a pipeline where an AI drafts, stages, and waits for human approval before anything goes live. Five real breakages…
Building a Draft-First AI Publishing Pipeline: Five Things That Broke
Builder Log Jan 5, 2025 3 min read
What I Learned Connecting an AI Agent to a Live Publishing System
The first time you wire an AI agent to a live system, you learn exactly what breaks, why auth matters,…
What I Learned Connecting an AI Agent to a Live Publishing System