Conversational insights
Query and analyze your context lake with AI. Ask questions in natural language, get answers grounded in your catalog data, and turn insights into dashboards or reports — without switching tools or writing queries by hand.
Why it matters
Engineering data lives across dashboards, scorecards, incidents, and ownership records. Extracting answers usually means manual investigation or expertise in multiple tools. Conversational access lets anyone explore delivery trends, investigate incidents, or prepare leadership reports from the same unified context.
How Port helps
Port connects AI to your software catalog & context lake in three ways:
- AI agents in Port analyze metrics, explain trends, and recommend next steps using data and MCP connectors from GitHub, Jira, PagerDuty, and more.
- MCP outside Port lets you query the same context from Claude, Cursor, or any MCP-compatible client — ideal for ad-hoc questions during reviews or investigations.
- Dashboards and reports combine built-in Port widgets, custom widgets, and AI-generated outputs through tools like Claude or Lovable.
Across all three, you can explore service ownership, DORA and delivery metrics, scorecard compliance, incident context, and cross-team comparisons from one connected data layer.
Choose how you interact
- AI agents
- Chat outside Port
- Dashboards and reports
AI agents in Port
Use Port's AI agents and custom skills to analyze engineering intelligence data inside the platform. Agents work directly on your catalog and can pull live context from connected tools.
Example uses:
- Delivery analysis — "Which teams had the biggest increase in PR cycle time this quarter, and what's driving it?"
- Scorecard remediation — "What do we need to fix to reach Silver on our DORA scorecard?"
- Reliability review — "What are our top services by incident frequency, and are they improving?"
Chat with your context lake outside of Port
Connect AI tools like Claude or Cursor to Port through the MCP integration. Ask questions in natural language and get answers grounded in services, teams, deployments, incidents, and metrics — extended with real-time data from external MCP connectors.
Example: An engineering director preparing for a quarterly review asks Claude: "Show me the top 5 teams by deployment frequency this quarter, and highlight any with change failure rate above 15%." They follow up with incident details for the lowest-performing team, pulled via the PagerDuty MCP connector — no dashboard building required.
Insight dashboards and reports
Turn context-lake data into visuals you can share and revisit:
- Built-in dashboards — Real-time widgets for DORA, delivery, and scorecard metrics across teams and services.
- Custom widgets — Tailored charts and calculators for organization-specific metrics.
- AI-generated reports — Board-ready summaries and interactive pages via Port MCP and tools like Lovable.
Example: A VP asks Claude via Port MCP for a Q1 engineering health report covering DORA metrics, scorecard compliance, and AI adoption by team — then shares the result with leadership as an interactive page.
Follow the recommended guides below to implement this use case.
Recommended guides
- Query DORA metrics using Port MCP - Ask natural-language questions about DORA metrics through Port's MCP integration.
- Triage incidents with MCP - Use AI agents to investigate incidents with live observability and catalog context.
- Onboard developers from internal docs using Port MCP - Answer onboarding questions grounded in your internal documentation and context lake.
- Auto-fix services when scorecards degrade - Delegate scorecard remediation to AI coding agents.