langwatch/scenario
Scenario is an agent testing framework that evaluates AI agent behavior through simulated user conversations.
Collecting fresh signals — velocity needs a few days of history.
collecting data…
star history
Scenario is a testing framework for AI agents available in Python, TypeScript, and Go. It simulates users across different scenarios and edge cases to test real agent behavior in multi-turn conversations, with evaluation and judgment possible at any point. It is agnostic by design and can be combined with any LLM evaluation framework or custom evals. Agents are integrated by implementing a single call() method.
Frequently asked
- What is langwatch/scenario?
- Scenario is an agent testing framework that evaluates AI agent behavior through simulated user conversations.
- Is scenario open source?
- Yes — langwatch/scenario is open source, released under the Apache-2.0 license.
- What language is scenario written in?
- langwatch/scenario is primarily written in TypeScript.
- How popular is scenario?
- langwatch/scenario has 1k stars on GitHub.
- Where can I find scenario?
- langwatch/scenario is on GitHub at https://github.com/langwatch/scenario.