Validation Layers: Pre-flight, In-flight, Post-flight

2026-05-07
Section 2 · Trust ArchitectureDefense in depth, not in a single guardrail

Three validation phases. Each catches a different failure.

A single content filter is not a trust architecture. Wrap every consequential action in three checks — they are cheap to add, expensive to skip, and the failure modes they catch are non-overlapping.

Pre-flight

Should this action be attempted at all?

Catches

  • Out-of-policy actions (Zone violations from the previous slide)
  • Schema violations and obviously malformed arguments
  • Budget exhaustion — the agent has spent its allowance
  • Prompt-injection attempts surfaced by the planner
  • Stale context — the world has moved since the plan was made

Techniques

Schema validatorsPolicy engines (OPA-style)Budget countersAllow-listed tool sets per goalInput sanitization
In-flight

Is the action behaving as expected as it runs?

Catches

  • Tool calls returning unexpected types or sizes
  • Latency or error spikes from downstream systems
  • The agent re-trying a failing call too quickly
  • Drift between what was planned and what is being executed
  • Cost or token consumption exceeding the trajectory budget

Techniques

Circuit breakersAdaptive timeoutsToken / cost metersStep-level signed receiptsAnomaly detection on traces
Post-flight

Did the outcome match the intent — and is the world still consistent?

Catches

  • State changes that violate invariants (negative balances, orphaned records)
  • Outcomes that satisfy the literal goal but miss the intent
  • Side effects in systems the agent was not supposed to touch
  • Drift in agent quality over time (silent degradation)
  • Patterns visible only across many runs (systemic bias, exploitation)

Techniques

Invariant checks on state diffIndependent evaluator modelSample-based human reviewCross-run analyticsReplay for incident review

Pattern to remember: Plan → Authorize → Execute → Verify. Authorization is the pre-flight gate. Verification is the post-flight gate. The agent's loop runs between the gates, not around them.