PlatformPlatform (with DeepEval)

Confident AI

The hosted home for your DeepEval results: dashboards, datasets and regression history.

What it is

Confident AI is the hosted platform built by the DeepEval team. Your DeepEval tests run as usual, and the results are sent to a web dashboard where you can manage test datasets, share reports, and watch your scores over time.

Why a QA engineer cares

Local pass/fail is fine for one person, but a team needs history and a shared view. Confident AI gives you trend lines, so you can see if last week's prompt change quietly lowered quality.

Get started

Install it, then run the example below.

Install

pip install deepeval   # then: deepeval login

Quickstart

# 1. Connect your account (opens the browser once)
# deepeval login

# 2. Run your normal DeepEval tests
# deepeval test run test_llm.py

# 3. Results now appear in the Confident AI dashboard
#    with datasets, sharing and score history over time.

What you get

✓Dashboards and shareable eval reports
✓Manage and version your test datasets
✓Track score trends and catch slow regressions
✓Runs on top of your existing DeepEval tests

Best for

Team dashboardsDataset managementTracking over time

Where it fits

It is the dashboard for DeepEval. Start with DeepEval locally, add Confident AI when a team needs the shared view.

Official docs for Confident AI →

Other AI-testing tools

promptfoo

Run evals and safety tests on prompts and models, works in CI

DeepEval

Pytest-style AI evals (correct, relevant, bias)

Ragas

Check RAG bots: did they find and use the right source

LangSmith

Trace, save datasets and run evals for AI apps

Giskard

Scan AI models for weak spots and unsafe answers

Put it to work

See where Confident AI fits in the full picture, or follow the step-by-step AI for QA roadmap.

The AI testing guide The AI for QA roadmap