Kill Switch

Overview

The Kill Switch is an emergency mechanism to immediately terminate an agent’s access to all external services. When activated:

All in-flight requests are terminated
The agent’s credentials are revoked
Future requests are blocked
Webhooks are triggered (if configured)

Propagation time: < 100ms globally

Activation Methods

Dashboard (Recommended)

Go to Agents in the dashboard
Find the agent you want to kill
Click the red Kill button
Confirm the action

The agent status will change to “killed” and all requests will be blocked.

API

curl -X POST https://iam.bloomtechnologies.app/admin/agents/{agent_id}/kill \
  -H "Authorization: Bearer $ADMIN_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "reason": "Anomalous behavior detected",
    "notify": ["webhook"]
  }'

Response:

{
  "status": "killed",
  "agent_id": "agent_abc123",
  "killed_at": "2026-02-01T15:30:00Z",
  "credentials_revoked": 3,
  "in_flight_requests_terminated": 2,
  "propagation_ms": 47
}

SDK (Python)

from bloom_admin import BloomAdmin

admin = BloomAdmin(api_key=os.environ["BLOOM_ADMIN_TOKEN"])
result = admin.kill_agent(
    agent_id="agent_abc123",
    reason="Security concern"
)
print(f"Agent killed in {result['propagation_ms']}ms")

Reactivating an Agent

After investigating and resolving the issue, you can reactivate an agent:

Dashboard

Go to Agents
Find the killed agent (shown in red)
Click Reactivate
Confirm the action

API

curl -X POST https://iam.bloomtechnologies.app/admin/agents/{agent_id}/reactivate \
  -H "Authorization: Bearer $ADMIN_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"reason": "Issue resolved after investigation"}'

Automatic Kill Triggers

Configure automatic kill switch activation based on:

Anomaly Detection

# In scope settings
anomaly_detection:
  enabled: true
  auto_kill_threshold: 0.95  # Kill if anomaly score > 95%

Rate Limiting

rate_limiting:
  requests_per_minute: 100
  auto_kill_on_sustained_violation: true
  violation_window_minutes: 5

Injection Detection

injection_detection:
  mode: "block"
  auto_kill_on_critical: true  # Kill on critical injection attempts

Webhooks

Get notified when an agent is killed:

Go to Activity > Webhooks
Add a webhook endpoint
Select the agent_killed event

Webhook Payload:

{
  "event": "agent_killed",
  "timestamp": "2026-02-01T15:30:00Z",
  "agent_id": "agent_abc123",
  "agent_name": "my-agent",
  "reason": "Manual kill by admin",
  "triggered_by": "[email protected]",
  "metadata": {
    "last_request": "/v1/chat/completions",
    "requests_last_hour": 1547
  }
}

Best Practices

Monitor Before Killing

Review audit logs before killing to understand what the agent was doing

Document the Reason

Always provide a reason when killing - it helps with post-incident analysis

Set Up Webhooks

Configure webhooks to alert your team when agents are killed

Test in Staging

Test your kill switch response in staging before production incidents

FAQ

How fast does the kill switch propagate?

The kill switch propagates globally in under 100ms. All edge locations receive the kill signal within this time.

What happens to in-flight requests?

In-flight requests are terminated with a 503 Service Unavailable response. The client will receive an error indicating the agent has been killed.

Can I undo a kill?

Yes, you can reactivate an agent from the dashboard or API. However, you should investigate the reason for the kill before reactivating.

Are logs preserved when an agent is killed?

Yes, all audit logs are preserved. You can review what the agent was doing before and after the kill.

Get Started

Guides

Integration Methods

Security

Overview

Activation Methods

Dashboard (Recommended)

API

SDK (Python)

Reactivating an Agent

Dashboard

API

Automatic Kill Triggers

Anomaly Detection

Rate Limiting

Injection Detection

Webhooks

Best Practices

Monitor Before Killing

Document the Reason

Set Up Webhooks

Test in Staging

FAQ

​Overview

​Activation Methods

​Dashboard (Recommended)

​API

​SDK (Python)

​Reactivating an Agent

​Dashboard

​API

​Automatic Kill Triggers

​Anomaly Detection

​Rate Limiting

​Injection Detection

​Webhooks

​Best Practices

Monitor Before Killing

Document the Reason

Set Up Webhooks

Test in Staging

​FAQ

Overview

Activation Methods

Dashboard (Recommended)

API

SDK (Python)

Reactivating an Agent

Dashboard

API

Automatic Kill Triggers

Anomaly Detection

Rate Limiting

Injection Detection

Webhooks

Best Practices

FAQ