Operating manual
Tag: AI Agents
A focused reading path for AI Agents: related field notes, evidence trails, and operating questions from the archive.
- agent-context-is-a-lifecycle-problem.md
Your AI Agent Needs a Context Policy
A practical six-part context policy for AI agents: what to keep, retrieve, compact, and delete across long-running jobs.
open artifact → - ai-memory-needs-an-eviction-policy.md
AI Memory Needs an Eviction Policy
A memory budget sets capacity. A memory policy decides what earns retention—and whether the rule actually helps the workload.
open artifact → - anthropic-is-building-claude-into-institutions.md
Anthropic Is Building Claude Into Institutions
Claude Tag, Project Glasswing, and Claude Corps reveal three routes into institutional AI adoption: workflow, deployment, and talent.
open artifact → - ai-rd-artifact-monitor-benchmarks.md
AI R&D Needs Two Benchmarks: Artifact and Monitor
ResearchArena shows why AI-produced models, kernels, and servers need adversarial artifact tests—and a separate benchmark for the monitor.
open artifact → - agent-run-control-intervention-semantics.md
Agent Run Control: Intervention Semantics
A stop button is not run control. Agent systems need explicit contracts for pause, resume, cancel, retry, compensation, ownership, and recovery.
open artifact → - agent-work-needs-chain-of-custody-not-just-bigger-models.md
Agent Work Needs Chain-of-Custody, Not Just Bigger Models
A four-question acceptance test for trusting agent work: who authorized it, what state crossed the handoff, what evidence proves completion, and what recovery path exists.
open artifact →