Skip to main content
Credible is the AI context engine. Without context, AI gives confident answers no one trusts. Credible captures what your data means — the definitions, business rules, and relationships buried in docs, dashboards, SQL, and your experts’ heads — as governed semantic models, then delivers your data and its meaning as context to every surface: AI agents, dashboards, data apps, embedded analytics, and whatever you build next. Models are built on Malloy, an open-source language designed for capturing data’s meaning. Your models are code — readable, versioned in Git, portable, and free from vendor lock-in — and the tools and skills Credible’s agents use to build and query them are open source too.

​
How It Works

Everything in Credible follows one path from raw data to trusted answers:
  1. Connect and model. Link your databases through managed connections — credentials stay in the platform, never on anyone’s machine. Then build semantic models with AI agents, in your browser or in your IDE.
  2. Govern and publish. Models live in environments as versioned packages, with access control defined in the model and enforced on every surface. Publishing makes a model available to every consumer at once.
  3. Deliver everywhere. Chat with your data and build reports in workspaces, give AI agents governed access via MCP (the open standard agents use to connect to tools), embed analytics in your product, or connect BI tools through the SQL API. One model, every surface, consistent answers.

​
Get Started

You can build semantic models entirely in your browser or in your own IDE. Both produce the same governed packages — start with whichever fits you and mix them freely.

Build in the App (Recommended to start)

Build with a natural-language agent in the Credible App — no setup or code editor. Ideal for getting started fast and for business users.

Local Development

Build in your preferred IDE with any coding agent — Cursor, VS Code, Claude Code, and more — using the Credible Extension. Ideal for engineers who want Git-based workflows and full control over files.
Both paths use managed connections, publish to the same environments, and produce models ready for every consumer.

​
Explore the Docs

The documentation follows the same path — foundation first, then building, then consuming:
  • Environments — The governed foundation. What environments are, connecting your databases, and setting up in-app or local development. Start here.
  • Semantic Modeling — Building models with AI agents: metadata tags, persistence, fine-grained access control, and publishing.
  • Analyzing Data — Consuming published models: workspaces, AI assistants via MCP, and the Slack integration.
  • Build with Data — For developers: custom AI agents, embedded analytics, BI tool integration, and the REST APIs.
  • Platform Administration — Managing your organization: users and groups, environment best practices, the CLI, and CI/CD.
  • Concepts — The ideas behind the platform: the semantic layer, the Context Engine, the architecture, and why Malloy.

​
Next Step

Everything you build lives in an environment, so that’s the place to start:

Environment Overview

Understand environments — the stable, governed foundation that holds your connections and packages
Have questions or need assistance? Feel free to contact us at support@credibledata.com – we’re here to help!