AI Agents

When working with Dataiku Agent Management, you may sometimes need to actually make third-party agents available in the Dataiku Flow, in order to leverage them or build upon them.

Agent Management agentic capabilities are only a subset of Dataiku DSS capabilities for building, troubleshooting, evaluating, deploying, monitoring, and exposing at scale AI Agents for the enterprise. Please refer to Dataiku DSS documentation for more details.

• Introduction to Agents in Dataiku
  • Types of agents
  • Using agents
• External Agents
  • Snowflake Cortex Agents
    • Prerequisites
    • Usage
  • Databricks Agents
    • Prerequisites
    • Usage
    • Limitations
  • AWS Bedrock Agents
    • Key Features
    • Prerequisites
      • AWS Requirements
    • Usage (Bedrock Agent)
    • Usage (Bedrock AgentCore)
    • Cautions
  • Google Vertex AI Agents
    • Prerequisites
    • Usage
    • Cautions
• Agent Review
  • Overview
  • Tests
    • Single-turn tests
    • Multi-turn tests
    • Adding tests
    • Quick Test
    • Running tests
  • Traits
  • Review run results
    • Analyze results
    • Test Annotation & Feedback
    • Test status
    • Trait status
  • Compare runs
  • Settings
    • Multiple executions of a test
    • Helper LLM
    • Trait setup
    • Permissions
• Tracing
  • Anatomy of a trace
  • Traces built into the LLM Mesh
  • Adding your own trace items
  • Trace Explorer
    • Creating a Trace Explorer Webapp
      • Use with Prompt Recipe, Agent Connect and Dataiku Answers
    • Using the Trace Explorer
    • Accessing via Explore Trace shortcut
    • Pasted traces management
    • Troubleshooting & Notes
• Agent Evaluation
  • Overview
  • Recipe configuration
    • Input dataset
    • Outputs
    • Metrics
    • Custom Traits
  • Trajectory explorer