Evaluation Context Protocol (ECP) vs Outside Agent

ECP is a vendor-neutral JSON-RPC protocol for grading agent outputs, tool calls, and audit context across frameworks, models, and CI systems.

Build AI agents that interact with the outside world.

About Evaluation Context Protocol (ECP)

ECP is a vendor-neutral JSON-RPC protocol for grading agent outputs, tool calls, and audit context across frameworks, models, and CI systems. ECP gives evaluators a common way to inspect what an agent returned, what tools it used, and what audit evidence it exposed, independent of the framework that built the agent or the platform that runs the test. tool_calls Did the agent call the required tool with the right arguments?. ecp run --manifest Can this run in CI and fail a build?.

About Outside Agent

Build AI agents that interact with the outside world. Give your AI agent a phone number, memory, and the tools to text, call, take action, and hand off to your team when needed. Agent action Start client intake Give the client space to explain . Agent Your timeline, people, and documents are ready for legal review. One URL from your console connects any editor, Claude Code, Codex, Cursor, VS Code, and more. Your coding agent builds, tests, and publishes it, then your customers talk to it on web, SMS, or voice.