# How should a chatbot recover when it misunderstands?

Offer options and explain what went wrong: people preferred repair strategies that showed initiative and gave a clear way forward.

Evidence: Limited (Early signal, treat it as a hypothesis) · LLM fit: Low (Older AI research, check before applying) (https://aiuxevidence.com/how-we-rate)
One scenario-based preference study with pre-LLM chatbots.

## Design it like this

When a chatbot misunderstands, offer concrete options and briefly explain why.

- Offer a few likely interpretations as options. [from the study]
- Explain briefly why the bot didn't understand. [from the study]
- Show initiative rather than asking the user to rephrase. [from the study]
- Keep an easy route to a human or a manual path. [our reading]

## What they found

### Ashktorab et al. (2019), experiment

Scenario-based study with 203 Mechanical Turk workers comparing eight chatbot repair strategies after a misunderstanding, including confirmation, offering options and explaining the system. Providing options and explanations were generally favoured, because they showed initiative and gave an actionable way to recover.

> “We found that providing options and explanations were generally favored, as they manifest initiative from the chatbot and are actionable to recover from breakdowns.” (Abstract)

## Trade-offs and when it doesn't apply

- Scenario-based preferences, not real behaviour.
- Pre-LLM chatbots.
- Options can be wrong too.

## What it looks like

- Do: “Did you mean: change booking, cancel, or something else?”
- Don't: “Sorry, I didn't get that. Please rephrase.”

## How to check it in your product

Track recovery rate after breakdowns: share of conversations that continue successfully after a misunderstanding.

## Open questions

- Do these preferences hold for LLM chatbots that rarely fail to parse but often fail to understand intent?
- How should repair work in voice?
- When should the bot hand off to a human?

## FAQ

### What is the best chatbot repair strategy?

In Ashktorab et al. (203 participants), providing options and explanations were generally favoured.

### Why do users prefer options?

They show initiative and give an actionable way to recover.

## Related questions

- [Is a blank chat box good UX for AI products?](https://aiuxevidence.com/e/blank-prompt)
- [How should users and AI agents share control of a task?](https://aiuxevidence.com/e/agent-handoff)
- [How do you set user expectations for an AI that makes mistakes?](https://aiuxevidence.com/e/set-expectations)

## Sources

1. Zahra Ashktorab, Mohit Jain, Q. Vera Liao, Justin D. Weisz (2019). Resilient Chatbots: Repair Strategy Preferences for Conversational Breakdowns. CHI 2019. https://doi.org/10.1145/3290605.3300484

Canonical: https://aiuxevidence.com/e/chatbot-repair