​
Overview

Paige is a hard working, capable virtual teammate. She uses resources in your DealPage Knowledge Base and your DealPage Deals to provide instant, accurate, and definitive answers to questions and complete workflows.

Like any new teammate, Paige is as good as the information you give her. Teams typically integrate their Knowledge Base and Deals with their documentation sites, CRM, email, and meeting transcripts to provide Paige with accurate information to complete her work.

Paige is not actually trained on any of your data. Rather, she is enabled by powerful search (RAG) and agentic techniques.

She can instantly answer questions ranging from: “What data center would we use for a customer in the UK?” to “What is our uptime commitment and SLA with Acme Corp.?”

​
Knowledge Base Sources

The Knowledge Base helps teams maintain a single, organized, up-to-date, and accurate source of truth about their products, security, and services. We offer a ton of integrations and tools to make this as easy as possible.

​
Documents

You can upload any document or presentation to DealPage. We use OCR to extract content from documents, break the content into digestible chunks, and generate ‘embeddings’. For a detailed explainer on embeddings and the use cases for RAG, see here.

​
Web Pages

You can also connect specific documentation sites and landing pages to your Knowledge Base. Content is similarly extracted and embedded for retrieval.

​
Spreadsheets / Tables

Our method for efficient retrieval over spreadsheets and tables allows Paige to find answers in complex .xlsx files and even tables in the middle of .pdfs.

​
Images

Much like with tables, Paige is able to extract information from, and answer questions using content from images like diagrams or screenshots.

​
Verified Answers

Verified Answers are specific Question-Answer pairs maintained by teams to answer common questions. Verified Answers are prioritized over answers from Documents when there is a high-confidence match. Verified Answers are an important way to improve Paige’s performance over time.

​
Deal Sources

Deals are individual Knowledge Bases dedicated to specific accounts your team is selling or supporting. Because Deals are always changing, we highly recommend using integrations to ensure your Deals are up-to-date and comprehensive.

​
CRM

Each Deal syncs automatically with a variety of objects from Opportunities in your CRM. This includes files, notes, tickets, contacts, and more. Syncs run automatically - ensuring Paige is using the most up-to-date information.

​
Meetings

Using our Zapier integration or manual uploads, teams can connect meeting transcripts or notes to DealPage.

​
Emails

Emails sent through a CRM or via Gmail can be synced to the appropriate Deal automatically.

​
Documents

You can upload deal-specific documents like contracts, security agreements, and sales collateral to a deal.

​
Improve the Responses

Click the thumbs up or thumbs down button on the response to provide feedback. This feedback is used periodically to improve the model’s responses. You can also edit the responses and add to your Verified Answers library to instantly improve outputs.

​
FAQ

​
Is my data being used to train models?

  • Your data is never used to train our models, or any 3rd party models. As mentioned above, we leverage RAG to provide Paige with data at “generation-time”, so she doesn’t need to be trained for specific teams. Teams on the Business plan may request fine-tuning for more brand-specific writing.

​
What models do you use?

  • Every answer we provide or workflow we complete involves multiple steps. Our embedding and re-ranking models are trained in-house for optimized performance on large tech knowledge bases. We leverage best-in-class 3rd party models for many tool calling and writing tasks, including GPT-4o and Claude 3 Opus. Some tasks like summarization are completed by self-hosted models.

​
How does you segment deal-specific content from the knowledge base and other deals?

  • Knowledge Base content and Deals are segmented into completely separate search indexes. Every Deal document is tied to a specific deal (by name and unique identifier). This allows our models to plan, and then executu a search in a specific location. This enables powerful behavior - for example, allowing you to ask questions about specific contract terms in a particular account.