AI Team Fundamentals
3 minute read
Overview
Edge Delta AI Team provides a collaborative layer of AI-driven assistants that investigate, summarize, and act on observability data. Each teammate can tap into telemetry flowing through Edge Delta pipelines and sanctioned knowledge sources to answer questions, trigger workflows, and generate tailored summaries for your operations teams.
Core Building Blocks
OnCall AI serves as the front door to the team, routing requests to the right specialists and stitching their findings into concise summaries.
The built-in specialists—Cloud Engineer, Code Analyzer, DevOps Engineer, Issue Coordinator, Security Engineer, and SRE—cover infrastructure, code, security, and incident response while collaborating with OnCall AI to deliver outcomes.
You can create dedicated assistants by shaping system prompts, selecting connector access, adding conversation starters, and scheduling recurring checks for custom teammates.
Finally, connectors provide data reach: event connectors stream alerts and tickets into an automatically created OnCall AI pipeline, and streaming connectors add telemetry sources to existing Edge Delta pipelines so teammates can query information through the Edge Delta MCP connector.
Collaboration Model
AI Team work happens in shared channels such as alerts-feed
, incident-response
, platform-ops
, code-issues
, and security-events
, where both specialists and humans can coordinate. Direct messages provide read-only conversations for quick questions, and any change that touches infrastructure or tooling flows through channels for transparency. OnCall AI oversees each exchange, delegating tasks and keeping the thread organized.
Data Access Model
Setting up the first event connector provisions an AI Team cloud pipeline that routes events to the OnCall AI destination. Additional event connectors become inputs on that same pipeline. Streaming connectors prompt you to choose an Edge Delta pipeline (or create one) so the data is processed alongside your existing telemetry. AI teammates read from these pipelines via the Edge Delta backend, respecting whatever processors and controls you configure upstream.
When to Use the AI Team
- Investigate incidents end to end: correlate metrics and logs, build timelines, surface impact, propose mitigations, and drive follow-up actions.
- Watch infrastructure health and resource usage to surface cost or capacity concerns before they become outages.
- Maintain security posture by reviewing IAM changes, correlating CloudTrail activity, and keeping responder channels aware of new signals.
- Guard code quality by letting teammates highlight risky pull requests, missing tests, and failing checks ahead of human review.
- Coordinate routine operational work—opening tickets, updating deployment plans, and summarizing outcomes across Slack and other connected tools.
Related Resources
- AI Team Connectors for supported streaming and historical integrations
- Create Custom Teammates to design domain-specific assistants
- Edge Delta MCP Connector for extending AI Team data access
- Security and Compliance Controls for guidance on audits and data protection