--- title: "AI Data Extractor" slug: "ai-data-extractor" updated: 2026-11-12T14:20:56Z published: 2026-11-12T14:20:56Z canonical: "help.gong.io/ai-data-extractor" --- > ## Documentation Index > Fetch the complete documentation index at: https://help.gong.io/llms.txt > Use this file to discover all available pages before exploring further. # AI Data Extractor > **Who can use this**: Business admin > > **Available on**: Gong Foundation AI Data Extractor is an AI agent that turns customer conversations into structured, reliable data and reduces the need for manual data entry. It automatically pulls details from calls and emails, and saves them in Gong and can optionally write them to the CRM fields you choose, so you can rely on accurate, consistent data. Instead of asking reps to remember every competitor, risk, or reason for churn and update it by hand, AI Data Extractor keeps fields up-to-date based on what customers actually say. This improves data quality, supports better reporting, and frees reps to focus on selling. Learn more about [creating and managing extractors](/v1/docs/create-and-manage-extractors). ## What are some use cases? AI Data Extractor gives you reliable, structured data on key topics without adding work for your team. Common examples include: - **Track account and deal details**: Make sure details specific to the account or deal aren’t missed, such as the number of requested seats, the discount offered on multi-year deals, the name of the CRO, or the expected closing date. - **Track competitors**: Capture which competitors were mentioned in deals or accounts so you can analyze win rates, pricing pressure, and positioning across segments. - **Measure methodology adherence:** Populate fields that track whether reps followed your sales methodology, asked key questions, or covered required topics. - **Identify decision makers and influencers**: Extract who is involved in the deal, what their roles are, and how engaged they are, then write this into deal or account fields. - **Capture product interest and use cases**: Record which products, use cases, or business problems were discussed, so you can analyze demand and tailor follow-ups. You can create an extractor for any question that can be answered from customer conversations. ## How are extractors defined? Each extractor is made up of three main parts: 1. **Question**: What you want Gong AI to answer based on conversations. For example: “Which competitors were mentioned in this deal?” 2. **Additional instructions (optional)**: Extra context that helps Gong AI answer consistently. Detailed instructions significantly improve the quality of the extractors’s answers. For example, you can explain how your company defines a specific term or methodology, or what to prioritize when multiple answers appear. 3. **Target object and data type** - **Target object**: Either deals or accounts. - **Data type**: The data type of the field the answer is stored in. Options are: - Yes/No: A true or false answer - Free text: An open-ended text answer. This includes rich text and long text fields. - Single-select picklist: One value from a predefined list of options - Multi-select picklist: Multiple values from a predefined list of options - Number: A numeric value - Date: A date - Range: A numeric value with a configurable minimum and maximum You can choose more than one data type for the same extractor. ## Set the target object The target object, either deal or account, defines which object the data extracted by the extractor is related to, and where it should be saved. If the data you are extracting is related to deals, select Deals. If the data you are extracting is related to accounts, select Accounts. The target object is used by Gong to identify the most relevant calls and emails to use to find the answer to the question posed by the extractor. For accounts, a wider range of calls and emails may be examined, as the answer to the question may be found over calls that relate to different open deals. For deals, Gong can identify the calls that are related to the deal and extract the answer from those calls. ### Filter the target object By default, the extractor runs on all deals or accounts that have had activity in the last 30 days. This can be heavy on resources, especially if there are deals and accounts that are not relevant for a specific extractor. You can add filters to control which deals and accounts are analyzed, for example to deals in a specific pipeline stage or accounts in a particular region. This will reduce the resources required by the data extractor. ## Set the data type The data type sets the format you want the answer to be generated in. The data types available allow you to ask questions that return long and detailed answers, quick answers, numerical data, or a date. You can also select more than one type of formatting. For example, if you want to extract data on “Which competitors were mentioned?”, you can set the data types to be: - **Yes / No**: Indicates if a competitor was mentioned - **Text**: List the competitors mentioned - **Single select picklist**: Displays the primary competitor - **Multi-select picklist**: Select all competitors mentioned from a predefined list ## How AI Data Extractor works AI Data Extractor runs behind the scenes, using Gong’s understanding of conversations together with your CRM setup. AI Data Extractor runs on published extractors only. The AI Data Extractor works as follows: 1. **Admin defines an extractor**: A business admin (for example, enablement or RevOps) creates an extractor and configures: - The question and any additional instructions - The target object (deal or account) - One or more output data types (Yes / No, text, single picklist, multi-select picklist) 2. **Account data saved in Gong**: Extractors with an account target object are automatically saved in Gong. You can also choose to export them to an existing CRM field. 3. **Deal data mapped to CRM fields**: Extractors with a deal target object must be mapped to a selected CRM field. - You can only choose a CRM field that is already imported into Gong. - Gong does not create new fields in the CRM, you must export data to an existing CRM field. 4. **Gong analyzes conversations**: After the extractor is published, Gong checks accounts and deals with recent customer activity and analyzes their calls over a rolling historical window. Gong AI extracts answers to your question based on what was actually said as follows: - Gong selects deals or accounts that had a call in the last month or received an inbound email. - For those deals and accounts, answers are generated according to call data from the last six months. Data from other activities such as emails are not used. 5. **AI Data Extractor updates fields automatically**: Gong recalculates answers for active accounts and deals whenever a new relevant conversation takes place. When new or better information is found, the previous value is overwritten so your data stays current. Because AI Data Extractor runs automatically, reps do not need to do anything for the fields to be updated. The agent keeps working in the background as new conversations come in. ### Which conversations are included in the analysis? AI Data Extractor may use data from any non-private call or emails that has been imported to Gong. This can include calls and emails the team member who sets up the extractor doesn’t have permission to view, for example if their permission profile restricts their access to calls or emails. When testing, the team member will be able to see the extractor’s results, even if they don’t have access to the underlying call. They will not be able to view the call content itself. You can narrow which of those conversations an extractor reads by adding filters under Sources when you create it. Gong applies them together with the target object filters, so it analyzes only the calls and emails that match both for each deal or account. ## Where you can see extracted data AI Data Extractor saves the values in Gong as well as exporting to your CRM, so you can use the results anywhere those fields are available. For example: - In Gong: - Deal boards, CRM fields can be added as columns on your boards - Account pages, as part of the account details - Other Gong views that you can customize - In your CRM: - List views - Reports and dashboards - Automations and workflows that depend on field values From the perspective of your team, the fields behave like any other CRM field. The difference is that they are filled and maintained by AI rather than by manual data entry. ## CRM mapping AI Data Extractor can export generated answers to CRM fields. For extractors whose target object is **Deals**, CRM mapping is required. For extractors whose target object is **Accounts**, CRM mapping is optional because account extractor results are automatically saved in Gong. To be available for CRM mapping, CRM fields and custom objects must be imported into Gong. To import a custom object, contact Gong Support. In addition to standard CRM fields, extractors can be mapped to attributes in CRM custom objects associated with accounts or deals. Custom object mapping is supported only when there is a one-to-one relationship between the account or deal and the custom object. If multiple custom object records are associated with the same account or deal, Gong can't determine which record to update, so the update won't be applied. In addition, the custom object instance must already exist on the account or deal. Gong can update an existing object, but it doesn't create new records. ## How extractors consume credits Published extractors consume Gong credits when Gong analyzes conversations for them. Extractors published before credits were applied to AI Data Extractor will continue to run without consuming credits for a limited period of time. ### Estimated credit consumption Before you publish an extractor, Gong shows an estimate of how many credits it will consume. The estimate combines the credits consumed when you publish the extractor and the credits it’s expected to consume over the next 30 days. The estimate is based on the filters and sources you set, so narrowing them may reduce consumption. The estimate is approximate, and Gong can’t calculate it when there isn’t enough related call data. ### Paused extractors when credits run out When your company has no credits available: - You can’t publish extractors that consume credits. - Published extractors that consume credits pause automatically, and the Status column shows Paused. - Paused extractors stop analyzing new conversations, but the data they already generated remains available. After your company has credits again, you can restart a paused extractor. Learn more about [restarting a paused extractor](/v1/docs/create-and-manage-extractors#restart-a-paused-extractor). Learn more about [managing credit usage](/v1/docs/when-credits-run-out). ### Existing extractors and Gong credits Extractors that were published before credits applied to AI Data Extractor will start to consume credits at a later date. To see when an extractor starts consuming credits, open the extractor. ## What you need to get started To start using AI Data Extractor, you need: - To connect Gong to Salesforce, HubSpot or Microsoft Dynamics and import relevant fields: AI Data Extractor uses CRM fields that are already imported into Gong. Make sure the fields you want to populate exist in your CRM, are imported into Gong, and support write access from the Gong integration user. You cannot use the CRM API with the AI Data Extractor. - A business admin to configure the extractor. This includes: - Deciding which questions to ask - Choosing the target object and output types - Mapping each AI output to the correct CRM field Once your first extractors are published, AI Data Extractor starts analyzing conversations, updating CRM fields, and giving your organization richer, more reliable data without extra work for your reps. A team member who manages the business entities in Gong, such as deal and forecast boards. [Find my Business admin](/v1/docs/find-your-technical-or-business-admin). Gong’s core platform for gaining advanced visibility into your revenue operations. Also the prerequisite license needed for Gong’s add-on packages. Access to features depends on your [company’s plan and your assigned seat](/v1/docs/plans-and-seats).