Interventions

What are interventions?

Intervention types

Intervention outcomes

Automatic intervention tracking

• A policy denies an action
• A budget limit is exceeded
• Rate limiting triggers
• Human approval is required

from agent_sentinel import guarded_action, PolicyEngine

# Configure strict budget
PolicyEngine.configure(
    session_budget=1.0,
    strict_mode=True
)

# This will trigger an intervention if budget is exceeded
@guarded_action(name="expensive_call", cost_usd=0.50)
def call_expensive_api():
    return "result"

Intervention metadata

• Action details: name, description, inputs
• Risk assessment: risk level, blast radius (impact if allowed)
• Cost metrics: estimated cost, actual cost (if executed), cost prevented
• Policy context: which policy triggered the intervention
• Agent context: agent_id, run_id
• Outcome: what happened (blocked, approved, modified, etc.)
• Rationale: why Sentinel intervened
• Agent intent: what the agent was trying to do

Viewing interventions

• Navigate to Interventions page
• See cost saved, high-risk blocks prevented
• Filter by type, outcome, risk level
• View detailed blast radius analysis

Platform API

GET /api/v1/interventions
GET /api/v1/interventions/stats
GET /api/v1/interventions/{id}

Example: Blast radius tracking

from agent_sentinel import guarded_action, PolicyEngine

PolicyEngine.configure(
    denied_actions=["delete_production_database"]
)

@guarded_action(
    name="delete_production_database",
    cost_usd=0.0,
    tags=["dangerous", "destructive"]
)
def delete_db():
    # This will never execute - blocked by policy
    # Intervention will record:
    # - type: HARD_BLOCK
    # - risk_level: CRITICAL
    # - blast_radius: "Prevented deletion of production database"
    # - outcome: BLOCKED
    pass

Cost prevention metrics

• Total cost prevented: Sum of estimated costs for blocked actions
• High-risk blocks: Count of critical/high-risk interventions
• Top blocked actions: Most frequently blocked action types
• Triggering policies: Which policies provide the most value

See also

• Policies - Configure policies that trigger interventions
• Approvals - Human-in-the-loop workflow for escalated actions
• Compliance - EU AI Act compliance features