#ai
10 items tagged with "ai"
Blog Posts (4)
GitHub Agentic Workflows: Automated Test Reviews with MCP
Feb 21, 2026GitHub Agentic Workflows let AI agents run as CI. Here's how we connected Gaffer's MCP server for automated weekly test health reviews.
Test Intelligence: The Missing Context for AI Coding Tools
Feb 14, 2026AI coding tools know your code but not your tests. Test intelligence via MCP bridges the gap with flaky detection, failure clustering, and coverage data.
Give Your AI Coding Tools Access to Your Test Results
Feb 11, 2026Claude Code, Cursor, and Windsurf can query your test history, find flaky tests, and diagnose failures — if you give them structured data. Here's how.
Your AI Agent's Missing Layer: Test Intelligence
Feb 8, 2026Agents write code and run tests. But when tests fail, they're flying blind. Here's how test intelligence closes the loop.
Changelog (6)
AI-Powered Failure Categorization
Test failure clusters are now automatically categorized as product bugs, automation bugs, or environment issues using AI.
Agentic CI: Failure Clustering & Upload Status
New API endpoints and MCP tools for AI agents to diagnose CI failures and check upload progress.
Coverage Analytics in MCP
Query test coverage metrics directly from Claude Code.
MCP Server Enhancements
New tools for comparing test metrics between commits and analyzing test run details with filtering.
MCP Server for AI Assistants
Query your test data directly from Claude and other AI assistants using the Model Context Protocol.
AI-Powered Test Analysis
Get AI-generated insights explaining why your tests failed and suggestions for fixes.