Evaluating Agent Tool Calls
Most agent evals grade the final answer. The harder failure is a tool returning 200 OK with an empty field. Evaluate the data your agent got, in Python and JS.
AI Sales Reps and What's Really Powering Them
AI SDRs are a $4B market headed to $15B. Here's how they actually work under the hood, and why the data matters more than the model.
Your AI Tools Are Only as Good as the Data Behind Them
60% of AI projects fail because of bad data, not bad models. Why the data layer determines whether your AI tools actually work.
A Prospect Research Agent with Claude Code + datalegion-cli
Build a prospect research agent in 10 minutes with Claude Code + datalegion-cli. Outputs a per-account dossier and per-contact email-sequence outlines.
Natural Language Search for People Data
Natural language search lets anyone query B2B people data in plain English. Search millions of professional profiles without SQL or a developer.
API, SDK, MCP, CLI: Building Data Products for the Agent Era
How we built four interfaces to the same data and why AI agents work best with a CLI. Introducing datalegion-cli.