Multi-Agent Investigation
When Annie investigates an incident, she coordinates multiple specialists working in parallel:| Agent | Role |
|---|---|
| Observability Agent | Searches logs, metrics, and traces across your monitoring tools |
| Infrastructure Agent | Explores topology, dependencies, and recent changes |
| Code Agent | Examines source code, configuration files, and recent commits |
Why This Matters
Why This Matters
- Parallel investigation: Multiple agents work simultaneously, dramatically reducing investigation time
- Deep expertise: Each agent is optimized for its domain
- Intelligent coordination: Agents share context and build on each other’s findings
- Adaptive depth: Simple questions get quick answers; complex incidents get thorough investigation
How Annie Learns
After each investigation, Annie:- Reflects on what worked and what patterns emerged
- Curates learnings into structured knowledge for future use
- Applies relevant context automatically in future investigations
- “Last time this alert fired, the issue was a security group change”
- “Database connection errors below 5/min are normal noise for this service”
- “The payment-service depends on Redis in us-east-1”
What Annie Remembers
Infrastructure Patterns
Service relationships, deployment topologies, dependencies
Operational Baselines
Normal vs anomaly thresholds, error signatures, warning patterns
Tool Shortcuts
Effective queries, useful metrics, dashboard locations
Business Context
Which services power which features, team ownership, critical paths
Custom Knowledge
Add knowledge Annie can’t learn automatically: team conventions, business context, vendor specifics, escalation procedures.Learn about Customization
Configure custom instructions and knowledge for your organization