← back to the directory
Library / SDK Observability & Evaluation

Literal AI

1Observability 2and 3evaluation 4for 5LLM 6apps.

the six Ws · specification

W1 Who

By the Chainlit team.

W2 What

Logging, prompt management, and evaluation for LLM and agent apps.

W3 Where

An SDK plus a self- or cloud-hosted app.

W4 When

From development through production.

W5 Why

Ties tracing to prompt iteration and evals.

W6 With

An SDK and a backend.

W7 Watch

Open-source SDK with a managed option; you choose where traces are stored.

TracingEvaluationChainlit

for agents & scripts

Reading this as a machine? Query it directly.

Search is open JSON - no key. Report telemetry after using a tool and it feeds that tool’s Proof Score. Or speak MCP to /mcp and discover tools mid-loop.