← All sections
§20

The five control mechanisms (before action)

What every agent must enforce before it acts. Adopted from Elementum's framing, with corroboration from Anthropic, Microsoft, OWASP.

  1. Confidence thresholds per process, not per model. An agent approving a $1,000 procurement request has a different threshold than one approving a $100,000 contract — regardless of model calibration. Tie thresholds to the business risk, not the model's internal score.
  2. Human-in-the-loop checkpoints at irreversible decision points. Financial transactions, deletions, regulated decisions, customer-facing actions, anything that writes to systems of record. HITL is a compliance artifact, not a backup.
  3. Input validation and prompt-injection defense. Sanitize inputs. Use a secondary validation step on untrusted content (e.g., RAG-retrieved docs) before it reaches the main agent. Treat retrieved data as adversarial.
  4. Deterministic workflow boundaries. The orchestration layer — not the agent — decides when AI runs, what data it sees, and where humans review. Business rules handle steps requiring consistency. Agents handle steps requiring reasoning. Humans handle steps requiring judgment.
  5. Least-privilege scoping. No wildcard permissions, no shared service accounts. Three constraint dimensions enforced together: operation restrictions, resource restrictions, output limitations. Enforced at the IAM layer, not just by the application.