Don't give your agent memory before you give your user control
A field note from adding memory to a Bible study agent app: start with user-visible records, then add semantic retrieval and traces.
Agent memory and user control
Start here when you are deciding what an AI product should remember, what it should show the user, and what should require review first.
What this path is for
-
Make saved memory visible to the user.
-
Keep review, deletion, and traceability close to retrieval.
-
Separate useful personalization from silent accumulation.
Writing in this topic
-
-
I Stopped Being the Switchboard for My Coding Agents
A decision memo on moving from agent-by-agent coordination to Firstmate and Herdr: isolated worktrees, durable state, supervised loops, decision gates, and evidence-backed PR handoffs.
-
Day 3 with Fable: Announcing the Autonomy Alpha
The Autonomy alpha is live — a native macOS app and local MCP server that lets AI agents work through your real accessibility setup — plus the day-three build-log of shipping it with Claude Fable 5.
-
I Built an AEO Agent Workflow. Google Made Me a Skeptic.
A field note from setting up a local Pi workflow with OpenRouter agents to research AEO topical authority. The real surprise was not any agent tactic — it was what Google's own guidance actually says.