AI Agent Evaluation Suites in 2026: Real Metrics That Matter
How to evaluate AI agents using Promptfoo, Langfuse, Helicone, and custom test suites. Real metrics, real failure modes, and what to actually measure.
Tag
testing
5 articles tagged testing. Browse the full blog.
TDD with AI Coding Agents: The Write-Failing-Test Pattern
How to do test-driven development with AI coding agents. The failing test first workflow with Claude Code and Copilot. Real examples, real pitfalls.
How to Use GitHub Copilot to Write Better Unit Tests
Use GitHub Copilot's /tests command, edge-case prompting, and table-driven patterns to write unit tests faster without sacrificing quality.
How to Use Claude Code to Add Tests to an Untested Codebase
How to point Claude Code at a legacy module, generate Vitest or pytest tests, iterate on coverage, and set conventions via CLAUDE.md.
AI Agent Evaluation: Benchmarks, Custom Evals, and What Actually Matters
How to evaluate AI agents using SWE-bench, WebArena, GAIA, and custom evals. What the numbers mean, what they miss, and how to measure what matters.