Reminder: Quilt’s answers are meant to be a first pass at a questionnaire, and not the final approved answer. Please be sure to review ALL Quilt answers before submitting to a customer!!

We minimize hallucinations by only answering questions we are confident are correct. In the future, we will offer visual indicators in the questionnaire and the extension itself on confidence level to flag answers that might need additional manual review.

We use a proprietary ML pipeline to index the documents you share with us according to their context. We answer questions straight from the indexed documents based on the text that we determine is the most relevant answer for the question. You can click through each question to see what source documents the answer is coming from.

We can only give answers from the documents you share with us. We do this to minimize hallucinations and false positives. Think of us like a brand new SE that is an expert on your documents only. In order for us to answer more questions, be sure to share more documents that could provide the right answer to those questions. Documents that tend to work well are typically information-dense: previously completed questionnaires, security certifications, and developer documentation.

For RFPs and security questionnaires, providing correct and accurate answers is only half the equation. We also have to provide those answers in the right context: be selective about what to say and what not to say, make sure the tone and phrasing matches the context, etc. We are constantly tuning our models with this in mind and have a lot of proprietary strategies around inferring the right context, but we are not perfect! We will continue to get better over time.

The quality of answers depends on the quality and completeness of the source documents you share with us and the kinds of questions that are being asked. In the best case - for instance, product questions for a product with very robust product or developer documentation - we can get to near 100% completion. However, there may be some questions we just are unable to answer due to not having enough context on the question itself or not having the right data sources shared with us.

We aim to get as close to 100% completion as possible. To this aim, we understand that in addition to getting answers factually correct, context and phrasing is also important. We are constantly tuning our models so they do the best job of inferring the correct context and providing correct answers phrased in the right ways.

View the list of the documents you have previously uploaded here.

Navigate to the Source Documents page and choose “+ Source Documents”

We can index the following file types: Google Drive files (Docs, Sheets, Slides, etc.), .doc/docx, .pdf, .xls/.xlsx, .ppt/.pptx, .txt. We can index previous questionnaires that are formatted as either a sheet (.xls/.xlsx/Google Sheet) or doc (.doc/docx/Google Doc). We automatically parse out questions and answers in those documents. We can index publicly available websites and allow you to crawl a tree of webpages to easily and quickly pull in all relevant documentation. This works particularly well for API documentation. Additionally, we can index your Notion and Confluence pages.

Yes, you can click on any from the list of the source documents and see relevant metadata, like title, import method, date uploaded, and date last updated (i.e., reindexed) as well as the preview of the document. You can also navigate to the original source of document.

Select the document in the Source Documents tab and click on the delete button.

You can also select multiple documents to delete at once.

Please reach out to us by email/Slack. We will then update your information from the backend.

View the list of the answers you have approved to be correct here.

We would recommend sorting the answers by date and individually reviewing initial responses.

Sort question-answer pairs by last updated date.

Update the answers to the questions as you get new information.

For your convenience, the version history of a question can be reused.

To upload a single question, you can use the inline form in the “+ Import items button”.

To upload a questionnaire previously completed by your Sales Engineers or by Quilt, you can either upload it via Google Drive or file upload. At the moment, we support .xlsx and .xlsm file types.

After choosing to upload a questionnaire, define the column types as “Question” and “Answer”, so that the tool can extract information for the Answer Bank.

This assistant responds and provides source document references to individual user queries.

No, at the moment, the assistant does not function like a chatbot, meaning it only keeps track of the current question asked.

You can copy to clipboard, upvote or downvote an answer for feedback, and delete your question history.

You can also edit Quilt’s answer to update it with more accurate information and save the answer to the Answer Bank for further reference.

You can review the references for your answers and navigate to the source documents those references originate from.

A blue reference means the answer is being pulled directly from the Answer Bank, where you or someone else from your organization had marked it as a reliable reference earlier.

A purple reference means the answer is coming from a source document you or someone else from your organization had uploaded previously.

This assistant takes advantage of the previously uploaded documentation to quickly process Sales Engineers’ RFPs. Quilt’s answers will improve over time, but they will not be 100% correct, so please review them.

Select the document you want to upload. Make sure it is in .xlsx or .xlsm format.

Specify the columns where the question is located and where you would want the answer to appear.

After you are done assigning question and answer columns, Quilt will start processing your document.

You can choose the option in the “Ready for Review” questionnaires. Look through the response and edit it accordingly.

Additionally, you can look at the references that correspond to the responses in the questionnaire. Please do not hesitate to reach out if a reference does not seem appropriate.

Yes, you can. You can also assign

First, download the prepared questionnaire.

Then, navigate to the Answer Bank and upload the questionnaire by clicking on the “+ Import items button”

Finally, assign the question and answer columns for the answer bank to extract the knowledge from the uploaded questionnaire and continue to the next sections.

Once you are done, there should be a confirmation message at the top of the screen and the answer bank will populate with new responses.

You can find a link to the Chrome store on your Home page. Alternatively, you can find it on the Chrome store here.

You can use the Chrome extension to fill out RFPs in Google Sheets, automate vendor portal questions, chat with Quilt, and add documents to Quilt.

Sign in into Quilt, navigate to the Home page, and click on “Open Extension.” Note: you may have to accept some additional Google permissions on your end prior to being able to use the extension.