> For the complete documentation index, see [llms.txt](https://themochi-app.gitbook.io/mochi-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://themochi-app.gitbook.io/mochi-docs/mochi-sops/ai-tags-inspiration-guide.md).

# AI Tags Inspiration Guide

#### Set these up once. Mochi tags every lead automatically from there.

### How AI Tags Work

You write a prompt in plain language. Mochi's AI reads every conversation and applies the tag when the criteria match. It understands intent, not just exact words — so it catches *"can I get access to your program?"* and *"where do I sign up?"* and *"how do I get started?"* all under the same tag.\
Rule of thumb:<br>

* Use AI Tags when a lead could say the same thing 10 different ways
* Use Pattern Match when your setter sends a specific copy-pasted script or you want an exact keyword tracked

### Writing a Good Prompt

Write it like you're briefing a new hire whose only job is to tag leads. Be specific. Include examples of what DOES and DOES NOT qualify.\
Weak prompt (bad results):<br>

> *"Tag if the lead seems interested"*

Strong prompt (good results):<br>

> *"Tag this lead as Hot Lead if they explicitly express urgency, readiness to buy, or ask how to get started or access the program. Examples: 'I'm ready', 'where do I sign up', 'how do I get access', 'I want in', 'when can we start'. Do NOT tag if they're just asking general questions about what the program includes."*

💡 Use Claude or ChatGPT to improve your prompts — paste your draft and ask it to rewrite as a specific tagging instruction.<br>

### Recommended Tag Library

#### Stage Tags

<br>

| <p>Tag<br></p>                            | <p>Prompt Guidance<br></p>                                                                                                                               |
| ----------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------- |
| <p><code>Qualified</code><br></p>         | <p>Lead has revealed a specific problem, budget signals, and genuine interest in the offer. They're asking serious questions, not just browsing.<br></p> |
| <p><code>Hot Lead</code><br></p>          | <p>Lead expresses urgency, readiness, or strong buying intent after being nurtured. "I'm in", "where do I sign up", "I want to start this week."<br></p> |
| <p><code>Booking Link Sent</code><br></p> | <p>Pattern Match — setter has sent the Calendly link. Set as "sent by setter." Tracks exactly how many links went out.<br></p>                           |
| <p><code>Call Booked</code><br></p>       | <p>Use Calendly integration for this — auto-updates when lead books via tracked link.<br></p>                                                            |
| <p><code>No Show</code><br></p>           | <p>Manual tag — set after a missed call. Triggers re-engagement follow-up.<br></p>                                                                       |

#### Objection Tags

<br>

| <p>Tag<br></p>                                | <p>Prompt Guidance<br></p>                                                                                                                                             |
| --------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| <p><code>Objection — Price</code><br></p>     | <p>After a CTA has been issued, lead mentions cost, budget, price, or "expensive." Do NOT tag if no CTA has been issued yet — that's just a question.<br></p>          |
| <p><code>Objection — Time</code><br></p>      | <p>After a CTA, lead says they're too busy, need more time, or can't commit right now. Scheduling negotiation ("can we do Thursday?") is NOT a time objection.<br></p> |
| <p><code>Objection — Trust</code><br></p>     | <p>Lead expresses scepticism about the offer, results, or credibility after a CTA. "How do I know this works?"<br></p>                                                 |
| <p><code>Objection — Authority</code><br></p> | <p>Lead says they need to check with a partner, spouse, or business partner before deciding.<br></p>                                                                   |

#### Source Tags

<br>

| <p>Tag<br></p>                              | <p>Prompt Guidance<br></p>                                                                                                                |
| ------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------- |
| <p><code>Source: \[Campaign]</code><br></p> | <p>Pattern Match — lead sends your specific campaign trigger word (e.g. "PDF", "GUIDE", "FREE"). Name the tag after the campaign.<br></p> |
| <p><code>Source: Outbound</code><br></p>    | <p>Pattern Match — set as "sent by setter." First message is your outbound opener script. Tracks outbound reply rate.<br></p>             |
| <p><code>Source: Story</code><br></p>       | <p>AI Tag — lead references your story or mentions seeing something you posted recently.<br></p>                                          |
| <p><code>Source: YouTube</code><br></p>     | <p>Pattern Match — lead uses your YouTube CTA trigger word.<br></p>                                                                       |
| <p><code>Source: Referral</code><br></p>    | <p>AI Tag — lead mentions being referred by someone or says a specific person told them about you.<br></p>                                |

#### Engagement Tags

<br>

| <p>Tag<br></p>                                           | <p>Prompt Guidance<br></p>                                                                                               |
| -------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |
| <p><code>Budget Confirmed</code><br></p>                 | <p>Lead has explicitly mentioned they have budget, confirmed an investment range, or said money isn't the issue.<br></p> |
| <p><code>Re-engagement</code><br></p>                    | <p>Manual tag — applied to leads you're reviving after 2+ weeks of silence.<br></p>                                      |
| <p><code>Dutch</code> <em>(or any language)</em><br></p> | <p>AI Tag — lead is writing in Dutch (or your target language). Useful for routing to the right setter.<br></p>          |

### Pro Tips

* Retag leads after creating a new tag — hit "retag leads" in settings so historical conversations get tagged too
* Test your tags using the tag tester before going live
* Start with 6–8 tags — don't overcomplicate on day one. Add more as you identify patterns
* Review tag performance monthly — if a tag is firing too broadly or missing obvious leads, refine the prompt


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://themochi-app.gitbook.io/mochi-docs/mochi-sops/ai-tags-inspiration-guide.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.