# Flagging a bad reply

> Report an incorrect answer from the agent in one click — it alerts your team and feeds back into improving the agent.

Unifunl.io Support help-center article in Inbox. Language: en. Updated: 2026-08-20. Every help-center page has a Markdown twin — append `.md` to its URL — and an `llms.txt` that covers it and everything under it — append `/llms.txt`.

## This article

- [Flagging a bad reply (Markdown)](https://support.unifunl.io/en/help/inbox/flagging-a-reply.md): the full article text, ready to read
- [Flagging a bad reply (page)](https://support.unifunl.io/en/help/inbox/flagging-a-reply): the rendered page

## Sections

- [Flag a message](https://support.unifunl.io/en/help/inbox/flagging-a-reply#flag-a-message)
- [Turn flags into fixes](https://support.unifunl.io/en/help/inbox/flagging-a-reply#turn-flags-into-fixes)
- [FAQ and troubleshooting](https://support.unifunl.io/en/help/inbox/flagging-a-reply#faq-and-troubleshooting)
- [What's next?](https://support.unifunl.io/en/help/inbox/flagging-a-reply#what-s-next)

## Related articles

- [AI Autopilot](https://support.unifunl.io/en/help/inbox/ai-autopilot.md): Let the agent answer on its own, and take back a single conversation without stopping it everywhere else.
- [Escalation](https://support.unifunl.io/en/help/inbox/escalation.md): What happens when the agent hands a conversation to a human — the yellow note, the silent agent, and how to pick it up.
- [Agent behaviour](https://support.unifunl.io/en/help/ai-center/agent-behavior.md): Pick a personality, set the tone, choose the languages and script, and set the guardrails with Always do, Never do and escalation rules.

## Optional

- [Inbox](https://support.unifunl.io/en/help/inbox/llms.txt): every article in this category
- [Help Center](https://support.unifunl.io/en/help/llms.txt): the whole help center