Skip to main content
Last updated on
Tags:
Options
Open in ChatGPTAsk ChatGPT about this pageOpen in ClaudeAsk Claude about this page

Governance Decisions

When an agent operation is evaluated, OpenBox returns one of five governance decisions.

Decision Types​

DecisionEffectTrust Impact
HALTTerminates entire agent sessionSignificant negative
BLOCKAction rejected, agent continuesNegative
REQUIRE_APPROVALOperation paused for human reviewNeutral (pending)
CONSTRAINOperation proceeds under recorded constraintsNeutral (constrained)
ALLOWOperation proceeds normallyPositive (compliance recorded)

ALLOW​

The operation is permitted to proceed.

When returned:

  • Operation matches allowed patterns
  • Agent trust tier permits the action
  • No policy violations detected

Effect:

  • Operation executes normally
  • Event logged for audit
  • Behavioral score slightly improves

CONSTRAIN​

The operation proceeds, but under constraints recorded at evaluation time.

When returned:

  • A guardrail transformed rather than blocked the input
  • Trust tier default requires isolation for this operation type
  • A behavioral rule permits continuation only under constraint

Effect:

  • Operation executes with the recorded constraints applied
  • Event logged with the specific constraint applied
  • Optionally handed to the Sandbox for isolated execution (Alpha); see Authorize
  • Behavioral score unaffected

REQUIRE_APPROVAL​

OpenBox pauses the operation pending human approval.

When returned:

  • Policy explicitly requires HITL
  • Operation crosses risk threshold
  • Agent trust tier mandates review

Effect:

  • Request appears in the Approvals queue with full context
  • SLA tracking shows whether the request is within SLA, at-risk, or breached
  • Session Replay shows the operation context and decision timeline
  • Once a reviewer approves or rejects, the operation proceeds or stops

Approval flow:

1. Operation triggers REQUIRE_APPROVAL
2. Request appears in dashboard queue
3a. Approved → Operation proceeds
3b. Rejected → Operation blocked
3c. Timeout → Operation expires

BLOCK​

OpenBox blocks the specific operation.

When returned:

  • Policy explicitly blocks this operation
  • Trust tier prohibits the action
  • Behavioral rule violation detected

Effect:

  • Operation does not execute
  • Event logged with denial reason
  • Behavioral score decreases

HALT​

The entire agent session is terminated.

When returned:

  • Critical policy violation
  • Multi-step threat pattern detected
  • Agent trust score critically low
  • Explicit termination rule triggered

Effect:

  • Current activity fails
  • Workflow is canceled
  • All pending operations abandoned
  • Discards any pending patch: HALT always dominates, even over a pending BLOCK-with-Patch retry
  • Agent may be blocked from further execution
  • Significant trust score decrease
  • Alert generated
  • Feeds trust incidents and identity signals

Decision Precedence​

When multiple policies apply, decisions follow precedence:

Updated to insert CONSTRAIN into the precedence order below. 
HALT > BLOCK > REQUIRE_APPROVAL > CONSTRAIN > ALLOW

If any policy returns HALT, the agent session is terminated regardless of other policies.

Decision in Session Replay​

Session Replay shows decisions at each operation:

Added a CONSTRAIN row to the example below. 
09:14:32.001  DATABASE_READ     customers.find    ✓ ALLOW
09:14:32.045  LLM_CALL          gpt-4             ✓ ALLOW
09:14:32.560  OUTPUT_GUARDRAIL  mask-pii          ◐ CONSTRAIN (PII masked)
09:14:32.892  EXTERNAL_API_CALL stripe.com        ⏸ REQUIRE_APPROVAL
09:14:45.002  APPROVAL_GRANTED  user: john@co     ✓ APPROVED
09:14:45.123  EXTERNAL_API_CALL stripe.com        ✓ ALLOW (resumed)
09:14:46.001  DATABASE_WRITE    audit.log         ✓ ALLOW

Customizing Decisions​

You can tune how the Authorize phase produces decisions:

  1. Policies (OPA/Rego) - Return allow, deny, or require_approval for specific operations and conditions.
  2. Behavioral Rules - Detect multi-step patterns and escalate to CONSTRAIN, BLOCK, REQUIRE_APPROVAL, or HALT.
  3. Trust-tier conditions - Apply stricter decisions for lower-tier agents and relax controls for higher-tier agents.
  4. Approval timeout settings - Configure how long REQUIRE_APPROVAL requests can remain pending before expiring.

Use policy and behavioral-rule testing before rollout to confirm expected outcomes.