Agentic SDLC

The Agentic SDLC page measures how broadly you use AI across the full software development lifecycle.

Overview

Four summary metrics frame the analysis:

• Total Sessions -- How many coding sessions are included
• MCP Servers -- Number of MCP server integrations detected
• Agentic Workflows -- Count of detected agentic workflow patterns
• CI/CD Workflows -- CI/CD pipeline interactions detected

MCP Server Integration

A section lists every MCP server you have used during coding sessions, along with the number of tool calls made to each. This shows how deeply you leverage external tools and data sources through the Model Context Protocol.

Work Type Distribution

AI Engineer Coach classifies your sessions by the type of work being done:

• Feature -- Building new functionality
• Bug Fix -- Fixing defects
• Refactor -- Restructuring existing code
• Code Review -- Reviewing and inspecting code
• Docs -- Writing documentation
• Test -- Creating tests
• Style -- Formatting and styling
• Config -- Configuration changes

Each category shows a count and percentage. This distribution reveals whether your AI usage is concentrated in one area (e.g., feature work) or spread evenly across the lifecycle.