> For the complete documentation index, see [llms.txt](https://docs.hockeystack.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.hockeystack.com/account-intelligence/workflows/nodes/transformations/ai-for-accounts.md). # AI **The AI Node applies a custom AI prompt to each account in your workflow.** Use it to generate insights, summarize firmographics, or apply custom scoring logic — all powered by Nova AI, at scale and in real time. *** ### When to Use It Use this node when you want to: * Generate AI-powered fields (e.g. “Sales Pitch Summary”, “Is this account a good fit?”) * Add custom AI scoring logic for accounts * Summarize or interpret existing data fields * Create personalized copy or inputs for downstream steps ### Configuration Overview Here’s what you’ll fill out in this node: **Column Name** The name of the new field you want to add to each account. This is where the AI-generated output will be stored. Example: * ICP Fit Score * Company Summary * Go-to-Market Insight **AI Prompt** This is where the magic happens. Enter a natural language prompt to tell the AI what you want it to return. Example prompts: * “Write a 1-sentence summary of this company’s product based on its website and industry.” * “Based on revenue, employee count, and region, rate this company’s fit for enterprise outreach (1-5).” * “Would this company benefit from a B2B SaaS data platform? Return Yes or No.” > Nova AI will process each account in your View and return a result per row using this prompt.
> **Note:** For scheduled workflows, data is refreshed every 30 days. *** --- # 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://docs.hockeystack.com/account-intelligence/workflows/nodes/transformations/ai-for-accounts.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.