Skip to content

Learn together. Build with evidence.

The AI team library

One place for the decisions, designs and engineering behind useful AI agents. Find the next piece of work for your role.

20 resources · Page 1 of 2

Follow new releases →
  • guide · Rasa Community

    Build your first Rasa agent

    Run a small Rasa agent locally, inspect the tool behind its answers, and make your first change with one complete downloadable starter.

    AI product engineer

    Rasa team ·

  • guide · Rasa Community

    Build an evaluation set that exposes failures

    Build an agent evaluation set with explicit task slices, traceable data, factual assertions, and failure cases that a headline success rate would hide.

    Evaluation / data specialist

    Rasa team ·

  • guide · Rasa Community

    Choose an agent workflow worth building

    Decide which workflow deserves an AI agent using a worked scope brief, a measurable outcome, and a boundary your product and engineering team can test.

    AI product manager

    Rasa team ·

  • guide · Rasa Community

    Design a handoff a customer can trust

    Design and test an agent-to-human handoff with explicit consent, a useful context packet, and recovery paths when the receiving team is unavailable.

    Conversation designer / UX specialist

    Rasa team ·

  • guide · Rasa Community

    Make an agent release decision with evidence

    Turn agent evaluation results into a release decision with an explicit denominator, a worked decision record, and owners for rollout and unresolved risks.

    AI product manager

    Rasa team ·

  • guide · Rasa Community

    Review what an agent is allowed to do

    Review an agent’s permissions with a worked action register, evidence from the tool boundary, and named owners for authorization, handoff, and unresolved risk.

    Risk reviewer / domain owner

    Rasa team ·

  • guide · Rasa Community

    Roll out an agent with a working stop button

    Plan an agent rollout with dependency checks, outcome signals, a verified fallback, and a rollback drill that proves who can stop an unsafe release.

    Platform / operations engineer

    Rasa team ·

  • tutorial · Rasa Community

    Guard an Action You Cannot Undo

    A scaffolded agent will post a replacement card to any address a caller reads out. Fix it by carrying where the address came from, and by putting the check inside the tool instead of in YAML.

    AI product engineer

    Rod Rivera ·

  • tutorial · Rasa Community

    Instructions Survive the Transport

    A tutorial promised its three skills could keep their instructions when MCP landed. MCP landed — here is the diff that settles it.

    AI product engineer

    Rod Rivera ·

  • tutorial · Rasa Community

    Measure Your Agent: Simulation, Assertions, and LLM Judges

    You changed a prompt and the demo went fine. Is the agent better? Build a simulation-based evaluation suite that answers with evidence — an LLM plays your customer, assertions stay the ground truth, and a judge scores what facts cannot reach.

    AI product engineer

    Rod Rivera ·

  • tutorial · Rasa Community

    The Document Is Derived, Never Written

    Ask an agent for a document and it writes one, with figures nobody can trace. Build the other thing: the conversation edits state, the document is derived.

    AI product engineer

    Rod Rivera ·

  • tutorial · Rasa Community

    Your First Rasa Mantle Agent, With Guardrails On

    Build a working Mantle agent using the starter pack — six AI skills, a nine-check lint, and a git hook that catches the silent mistakes before they cost you an afternoon.

    AI product engineer

    Rod Rivera ·

  • tutorial · Rasa Community

    Personalize the First Word Your Agent Says

    Load what you already know about a customer before the greeting, then spend it later in the conversation — with control levers, not hope.

    AI product engineer

    Rod Rivera ·

  • tutorial · Rasa Community

    Tool Scope and Memory Scope in Rasa Mantle

    Decide where a tool belongs and where a memory field belongs — and build a bank agent that makes the caller verify exactly once.

    AI product engineer

    Rod Rivera ·

  • tutorial · Rasa Community

    Build a Voice AI Agent with Rasa Skills

    Flagship tutorial for the Skills architecture and Deepgram voice — build Atlas, a Horizon Travel assistant, from first skill to progressive control.

    AI product engineer

    Rod Rivera ·

  • article · Rasa blog

    Enterprise AI Security and Compliance: A Practical Framework

    A framework for thinking about security and compliance when agents handle real customer data.

    Rasa team ·

  • article · Rasa blog

    How to Build an AI Agent: A Developer's Guide

    A practical walkthrough of what goes into a production agent, from architecture choices to evaluation.

    Rasa team ·

  • article · Rasa blog

    Introducing Rasa University: A Hands-on Learning Path for Agent Engineers

    The launch post for Rasa University — what the learning path covers and how the developer certification works.

    Rasa team ·