Launch Week 3: Five days of launches
Confident AI
Docs
Pricing
Products
LLM Evaluation
LLM Evaluation

Benchmark LLM systems with research-backed metrics.

LLM Observability
LLM Observability

Trace, monitor, and alert on production LLM systems.

AI Red Teaming
AI Red Teaming

Stress-test LLM apps against adversarial attacks.

AI Governance
AI Governance

Enforce AI standards and controls across teams.

Book a DemoSign Up
Book a DemoSign Up

Reference

Exhaustive references for every way to program Confident AI.

Overview

The Reference section is the exhaustive, low-level description of every surface you can program Confident AI through. Where the rest of the docs walk you through workflows, the reference lists each endpoint, its parameters, and what it returns.

The same project API key authenticates every surface, and they all operate on the same underlying objects: datasets, prompts, traces, metrics, test runs, and the rest of your project data.

References

API Reference

The RESTful Confident API. Authentication, conventions, data models, and every endpoint across v1 and v2.

MCP and SDK references are coming soon.

Building a production pipeline?Design a scalable API workflow for evals, datasets, traces, and promptsTalk to an engineer

Last updated on

Built byConfident AI