The Rough Edges of Upgrading a Self-Hosted AI Agent
A firsthand upgrade exposed how database bloat, live state, schema changes, and indexing can turn a package update into a full maintenance event.
Topic
reliability
5 related items across notes, deep dives, spotlights, and projects.
What Makes an AI Workflow Repeatable?
A useful AI workflow is not just a prompt that worked once. It is a small system with explicit inputs, checkpoints, fallbacks, and evidence that someone else can run again.
How AI Agents Decide Which Tool to Use
Tool selection is not a fixed lookup. An agent weighs the task, available tool definitions, required arguments, and prior results—then revises its next move when new evidence arrives.
Why More Context Can Make an AI Agent Worse
A larger context window gives an agent more room. Filling that room with stale instructions, duplicated facts, and raw tool output can make the agent less reliable.
Designing Tools a Model Can Actually Use
A model can only use a tool as well as the interface describes the job, constrains the inputs, reports the result, and supports recovery when something goes wrong.