> For the complete documentation index, see [llms.txt](https://learn.doubletick.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://learn.doubletick.io/doubletick-ai/understanding-ai-custom-field.md).
# Understanding AI custom field
Learn what an AI custom field is, the problem it solves, how it works, and where you can use it across your business.
An AI custom field in DoubleTick automatically analyzes your WhatsApp conversations and updates customer data based on what's being discussed. Instead of manually reading chats and tagging customers, AI does the heavy lifting. It scans conversations, understands intent, and assigns structured values to customer profiles automatically. This means your WhatsApp chats are no longer just conversations. They become organized, measurable business data.
#### What's covered
* [What problem does it solve](#what-problem-does-it-solve)
* [How an AI custom field works](#how-an-ai-custom-field-works)
* [Where you can use AI custom fields](#where-you-can-use-ai-custom-fields)
* [Why start using AI custom fields](#why-start-using-ai-custom-fields)
* [Key takeaways](#key-takeaways)
* [Frequently asked questions](#frequently-asked-questions)
#### What problem does it solve
As your business grows, your WhatsApp conversations increase. These include sales inquiries, pricing discussions, complaints, refund requests, and renewal follow-ups. Now imagine hundreds or thousands of chats a day. Can a team leader realistically read every conversation? In small volumes, maybe. In high volumes, not possible. Manual monitoring becomes time-consuming, inconsistent, and difficult to scale. This is exactly where AI custom fields make a difference.
#### How an AI custom field works
Here's the process, step by step:
* You create a custom field inside DoubleTick. For example, Deal Qualification Score.
* You define the possible values it can take. For example, Highly Qualified, Moderately Qualified, Low Qualified, or At Risk.
* You instruct the AI on how to evaluate conversations. For example, "analyze buying intent, urgency, and budget signals."
* AI scans conversations automatically. Choose chat messages, call transcriptions, or both. You can also choose whether it scans customer messages only or customer and agent messages.
* AI updates the customer profile based on conversation context, assigning the most relevant value. This happens automatically at regular intervals, with no manual tagging required.
For the full walkthrough, see [How to create an AI custom field](/doubletick-ai/understanding-ai-custom-field/how-to-create-an-ai-custom-field.md).
#### Where you can use AI custom fields
AI custom fields are flexible and can be used across departments:
* **Sales**: lead qualification, buying intent detection, competitor tracking, deal risk identification.
* **Support**: complaint categorization, urgency level detection, escalation tracking.
* **Billing**: refund discussions, payment confirmation, subscription renewal signals.
* **Retention**: cancellation intent, price resistance, customer dissatisfaction.
#### Why start using AI custom fields
If your chat volume is high, manual monitoring will never give you full visibility. AI custom fields let you scale conversation monitoring, improve accuracy, reduce manual effort, enable data-driven decisions, and generate structured reports. AI reads every conversation, so your team can focus on strategy and action.
AI custom fields turn WhatsApp from a communication tool into a business intelligence system. They help you organize conversations, track patterns, improve visibility, and make smarter decisions without increasing manual workload. As your conversations grow, AI ensures your clarity grows with them.
#### Key takeaways
* AI custom fields automatically scan conversations and assign structured values to customer profiles, so you don't have to tag customers manually.
* Setup takes four steps: create the field, define its possible values, instruct the AI, then let it scan and update profiles automatically.
* AI can scan chat messages, call transcriptions, or both, depending on what you select.
* They're used across sales, support, billing, and retention to qualify, prioritize, and track conversations at scale.
#### Frequently asked questions
Do I need to read every chat manually if I set up an AI custom field?
No. The AI **scans eligible conversations automatically** and updates the field at regular intervals. Your team only needs to review exceptions or use the updated data in workflows and reports.
Can AI custom fields scan calls as well as chats?
Yes. Choose **chat messages**, **call transcriptions**, or both as the source. Call analysis includes AI agent calls and team-member calls transcribed with AI.
Which teams can use AI custom fields?
Any team that needs conversation data in a structured format can use them. Common use cases include **sales qualification**, **support triage**, **payment tracking**, and **retention risk detection**.
#### Related articles
{% content-ref url="/spaces/53n17VnOICC1LtDqlENV/pages/pJllWQhxztq0NGJJkuB2" %}
[How to create an AI custom field](/doubletick-ai/understanding-ai-custom-field/how-to-create-an-ai-custom-field.md)
{% endcontent-ref %}
{% content-ref url="/spaces/53n17VnOICC1LtDqlENV/pages/U3AisZC9aqV3qw9EcK34" %}
[How AI custom fields support business operations](/doubletick-ai/understanding-ai-custom-field/how-ai-custom-fields-support-business-operations.md)
{% endcontent-ref %}
{% content-ref url="/spaces/53n17VnOICC1LtDqlENV/pages/W50L4N3XB2X9Sh2g0dcK" %}
[How to Configure an AI Custom Field Issue in CX Overview](/doubletick-ai/cx-overview/how-to-configure-an-ai-custom-field-issue-in-cx-overview.md)
{% endcontent-ref %}
---
# 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 by asking a question.
Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:
```
GET https://learn.doubletick.io/doubletick-ai/understanding-ai-custom-field.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.
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.