Chicory AI
  • Getting Started
    • Introduction to Chicory
    • Quickstart Guide
    • Understanding Chicory
  • API Reference
    • OpenAPI Specification
      • Projects
      • Training
      • Data_sources
      • Messages
      • Chats
      • Health
      • Models
Powered by GitBook
On this page
  1. Getting Started

Introduction to Chicory

Where Data teams build reliable and accurate AI Agents

NextQuickstart Guide

Last updated 8 days ago

Chicory gives data teams the ability to build, deploy, and manage AI agents. Agents built using Chicory are powered by an automated ontology mapping your code, documents and data. This gives Chicory agents the ability to understand and work on your unique data landscape.

Learn more about our vision and technology in .

Key Features

  • Living Ontology & Data Understanding Module: Auto-builds and syncs your unified data model.

  • AI Agent Framework: End-to-end environment for building, testing, deploying, and versioning data-focused agents.

  • Chicory Answers: Conversational interface for instant, context-aware data queries.

  • Chicory Agentic Flow: Orchestrates multi-step analyses and automations (e.g., EDA, pipeline tuning).

  • Automated Runbook Execution: Define and run complex data processes via structured runbooks (YAML/JSON/Markdown).

  • Intelligent Data Connectors: Ingest metadata and data from 100s of sources

  • No Ops Overhead: We handle training, hosting, and scaling—so you focus on insights.

Core Use Cases

  • Data Harmonization: Automatically align schemas, formats and business definitions at ingest—so datasets are join-ready in hours, not days.

  • Pipeline Optimization: Analyze your full DAG to surface cost- and latency-hotspots, then recommend configuration tweaks that free up budget.

  • Business Intelligence: Trace any KPI shift through data, code and dashboards—getting you root-cause answers in minutes.

  • Feature Engineering Agent: Scan your data estate to discover, score and prioritize the highest-impact variables for every ML model.

  • Data Debugging Agent: Trigger runbooks on pipeline errors, gather logs, pinpoint failures, and suggest fixes in seconds.

  • Data Understanding & Governance: Ask “Where did this metric come from?” or “What does this column mean?” and get instant, auto-generated lineage and documentation.

How to Get Started

To begin leveraging Chicory AI, the first step is to connect your primary data assets. This allows the Data Understanding Module to start building the initial version of your living ontology. Refer to our to build and deploy your first AI agent and see it deliver outputs. This hands-on experience is the best way to understand Chicory AI's practical capabilities and how it can be applied to your specific data challenges.

Understanding Chicory
Quick Start Guide