Operating manual
Tag: ai-agents
A focused reading path for ai-agents: related field notes, evidence trails, and operating questions from the archive.
- agent-audit-budgets-need-a-control-group.md
Agent Audit Budgets Need a Control Group
Test confidence-ranked human review against independent baselines, then promote it only when it reduces measured risk at the same audit budget.
open artifact → - dynamic-agent-calls-need-revisable-reservations.md
Dynamic Agent Calls Need Revisable Reservations
Revisable reservations let agent infrastructure hold, expire, and revise capacity as runtime-revealed service graphs change.
open artifact → - the-last-wrong-step-is-not-where-the-agent-failure-started.md
The Last Wrong Step Is Not Where Failure Started
A four-stage operator model for tracing long-horizon agent errors from their initiating deviation through propagation, resolution, and terminal impact.
open artifact → - agents-need-a-compiler-before-the-control-plane.md
Agents Need a Compiler Before the Control Plane
Why consequential infrastructure agents need compiled intent, bounded policy search, isolated tests, and deliberate production admission.
open artifact → - ai-misuse-doesnt-stop-at-the-session-boundary.md
AI Misuse Doesn't Stop at the Session Boundary
Cross-session AI misuse can hide capabilities assembled over time. A bounded capability ledger pairs longitudinal detection with explicit governance.
open artifact → - self-correction-needs-executable-verification.md
AI Self-Correction Needs Executable Verification
A practical verification promotion gate for deciding when an AI agent correction has enough evidence to replace prior state or trigger action.
open artifact →