← back to the directory
Hosted Service Observability & Evaluation

Confident AI

1Cloud 2dashboard 3companion 4to 5DeepEval 6evaluations

the six Ws · specification

W1 Who

Teams already using the DeepEval library who want a shared cloud dashboard.

W2 What

Confident AI is the hosted companion platform to the open source DeepEval framework for managing datasets, tracing and evaluation results.

W3 Where

Cloud SaaS platform accessed via a login command, syncing results from the local DeepEval CLI.

W4 When

Actively maintained alongside DeepEval into 2026 with regular feature additions including MCP server integration.

W5 Why

Adds shareable reports, dataset management and production monitoring on top of DeepEval's local evaluation logic.

W6 With

Requires the open source DeepEval Python package and an API key to sync results to the cloud.

W7 Watch

Commercial hosted service, evaluation logic runs locally via DeepEval but results and datasets are synced to Confident AI's cloud unless disabled.

deepeval clouddataset managementllm tracingtest reports

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.