Glossary · Term

tau-bench

← all terms

Definition

Plain language

A benchmark that tests AI agents on realistic customer-service phone-call style conversations.

As stated in the literature

A multi-turn agentic benchmark covering Retail, Airline, and other domains, evaluated with pass@k reliability metrics; distinct from tau2-bench, which extends it with additional tool environments.

Also called: τ-bench, tau bench

Why it matters: It exposes how reliably agents handle real customer-service workflows, where one wrong step can violate policy or anger a user.

For example, an agent must handle a multi-turn airline-rebooking call, looking up the customer's reservation and applying the right fare rules.

Heard on the show

“The second benchmark is τ-bench retail — multi-step tool use, the agent has to make correct tool calls and produce complete responses.”
Episode 181 — How to Backpropagate Blame Through a Team of Chatbots — And When It Backfires

Mentioned in 3 episodes

  1. 181
    How to Backpropagate Blame Through a Team of Chatbots — And When It Backfires
  2. 151
    Why More Experience Made This AI Agent Worse, And How to Fix It
  3. 071
    When the Model Is Fine and the Plumbing Is Broken: Fixing Agents at the Interface

Related terms