← All tags

architecture

7 entries across series

Series

• Installment 2

  The Agent Lifecycle Nobody's Managing

  The full agent lifecycle from deployment to retirement. Which stages have tooling, which are completely unserved.

• Installment 5

  Capability-First, Not Persona-First

  Built a 17-dimension persona schema. It was wrong. Capability layer drives behavior; persona is a thin modifier.

• Installment 6

  The Heartbeat Problem

  Naive cron polling creates cascading problems. Event-driven heartbeats with Todoist as source of truth.

• Installment 7

  Your Agent's Memory Is a Liability

  Unbounded state growth degrades everything. Retention policies, tiered storage, and git-backed snapshots.

• Installment 8

  Choosing Your Inference Stack

  Not a benchmark comparison. A real decision tree: local vs API, fallback chains, cost/privacy/latency trade-offs.

• Installment 9

  Mission Profiles: Scoping What Your Agent Can Touch

  Ten a-la-carte profiles with tool ownership boundaries. Predictable, debuggable agent behavior.

• Installment 13

  The Human-Agent Interface

  Separation of concerns: human tools, agent workspace files, and a thin sync layer between them.