> For the complete documentation index, see [llms.txt](https://docs.coresignal.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.coresignal.com/self-service/features-and-tools/ai-data-search/build-lists.md). # Build Lists Once you've generated a list of data records through your prompt in Data Search, list customization gives you direct control over what data appears and how it's maintained over time. You can edit records manually, add new data fields, and enrich only the records that matter most to your workflow. {% embed url="" %} ### Flexible enrichment Enrichment lets you manage the created list. * You can enrich the entire list at once or only selected records * After a data record is enriched once, any further enrichments or customizations of that record do not consume additional credits * Enrichment costs are calculated based on the number of data records, with a limit of 100 records in the preview list A selective approach helps control credit usage while keeping your data aligned with immediate business needs. ### Managing data records Records can be removed individually by clicking on a row and confirming deletion. This makes it easy to keep lists accurate and up to date without rebuilding them or rerunning queries. Click a row and confirm the deletion to remove unwanted records from your list. ### Adding new data fields Additional context can be added through data enrichment by selecting the **Enrich** button or **Add data field** column.
You can choose extra data fields from the chat window on the left. Selected fields are displayed in the preview window and are filled with data after enrichment is done.
## Data export When your custom list is complete, you can export the data. There are several options to choose from based on your needs:
### 1. Export CSV/JSON Best for: Quick exports and immediate access * Instantly download up to 100 records currently visible on your list * Available in CSV or JSON format * Unlimited downloads with no charges ### 2. Generate enriched JSONL The generated JSONL file includes all available data fields from our datasets, while Lists can be customized to include only the selected fields. Best for: Large-scale exports requiring comprehensive data * Export up to 10,000 records in a single file * Pricing based on the number of data records found using your prompt * File generation takes up to 10 minutes * You'll receive a notification when your file is ready for download Files section is visible to the entire team (team members). All generated JSONL files remain available for 30 days and can be accessed in the Data Search Files section. {% hint style="info" %} #### Why does JSONL take longer? We verify all data in real-time before generating large files. This quality assurance process ensures you receive accurate, current information without stale or empty rows. {% endhint %} ## History By default, all lists are saved to History and are private to you. Your teammates will not be able to see them unless you choose to share them or export the data to a shared folder. This means you can freely draft and experiment without cluttering your team’s workspace. You can return to any recent chat, continue the conversation, and find it using the History button. Your chat list automatically shows messages from the last 30 days, and any chats older than 30 days are cleared from the history.
--- # 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://docs.coresignal.com/self-service/features-and-tools/ai-data-search/build-lists.md?ask=&goal= ``` `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.