# Is there no way to customize or the messages in two-stage fallback?

**URL:** <https://forum.rasa.com/t/is-there-no-way-to-customize-or-the-messages-in-two-stage-fallback/47914>\
**Category:** Feedback on Rasa Open Source\
**Created:** [September 22, 2021, 12:33pm UTC](https://forum.rasa.com/t/is-there-no-way-to-customize-or-the-messages-in-two-stage-fallback/47914 "2021-09-22T12:33:28Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![BrookieHub](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/brookiehub/32/16846_2.png) [@BrookieHub](https://forum.rasa.com/u/BrookieHub)\
**Post date:** [September 22, 2021, 12:33pm UTC](https://forum.rasa.com/t/is-there-no-way-to-customize-or-the-messages-in-two-stage-fallback/47914/1 "2021-09-22T12:33:28Z")

</div>

I have gone through the two-stage fallback part in the documentations of the latest version of Rasa 2.0, but it doesn’t touch upon how we can customize the fallback messages to be more user-friendly.

By default, the bot says something like this during two-stage fallback:

```auto
Did you mean "intent_greet"?
Yes (/intent_greet)
No (/out_of_scope)

```

Which is not user-friendly at all. It should be customizable to say something else like:

```auto
"Did you mean one of the following intents?:
Greetings (/intent_greet)
Something else (/out_of_scope)

```

There was a blog post and a video covering about this customization and how the bot fails gracefully:

> **[Open source Two Stage Fallback Policy with Rasa NLU and Rasa Core](https://rasa.com/blog/failing-gracefully-with-rasa-core/)**
>
> Guideline on how to use the two stage fallback Policy in Rasa Stack, an open source library for natural langauge understanding and dialog management.

However that blog post was for a very older version of Rasa, and the links it leads to have been deprecated.

I tried working my ways around to customize it, but almost 70% of the time, the customization is not able to overwrite the default fallback messages and continues to send the non user-friendly messages.

Could someone from the Rasa Team please look into this and maybe create a video or update the documentations covering this topic? Because being able to customize a two-stage fallback policy message is very essential part of Conversational AI.

Thanks!!

@koaning

---

<div class="post-metadata">

**Author:** ![koaning](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/koaning/32/6626_2.png) [@koaning](https://forum.rasa.com/u/koaning)\
**Post date:** [September 27, 2021, 1:19pm UTC](https://forum.rasa.com/t/is-there-no-way-to-customize-or-the-messages-in-two-stage-fallback/47914/2 "2021-09-27T13:19:57Z")

</div>

There’s no tutorial written for it (yet), but I have a repo that demonstrates this idea using the normal fallback classifier. You can find it, with a demo-project [here](https://github.com/RasaHQ/rasa-action-examples/tree/main/fallback-button). Does that suffice?

---

<div class="post-metadata">

**Author:** ![BrookieHub](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/brookiehub/32/16846_2.png) [@BrookieHub](https://forum.rasa.com/u/BrookieHub)\
**Post date:** [September 27, 2021, 10:10pm UTC](https://forum.rasa.com/t/is-there-no-way-to-customize-or-the-messages-in-two-stage-fallback/47914/3 "2021-09-27T22:10:24Z")

</div>

Thank you so much! That was exactly what I was looking for 😃