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