Skip to content
NagentNagent
Log inSign upHire your AI Growth Team
NagentNagent
Log inSign up
All documentation

Adding knowledge

How to add a document to the Knowledge Hub by pasting text, from a URL or by uploading a file, how tags are suggested, and what the pending, embedded and failed statuses mean.

Browse documentation

A document your agents can read is worth more than ten they cannot

Agents answer from what is in your Knowledge Hub. Your website gives them a start (see Bootstrapping from your website), but the material that makes them useful usually lives elsewhere: a sales deck, a pricing sheet, a call transcript, a competitor's one-pager. This page shows how to add it, and how to tell whether your agents can actually read it.

Open the Knowledge Hub and choose to add a document, or go straight to nagent.ai/admin/knowledge/new. The screen is titled Add knowledge.

Add knowledge with Paste text, From URL, Upload a file, Add a video and Facts sheet across the top, then the document type, title, content, functions and industries fields

Step 1. Choose how to add it

Five buttons sit across the top. The last two are marked Beta.

OptionUse it forWhat happens
Paste textNotes, transcripts, anything you can copyThe text is stored as it is
From URLAn article, a whitepaper, a public pageNagent fetches the page over https and keeps the article text. A page served only over plain http cannot be fetched
Upload a fileDecks, documents, sheets, PDFsNagent reads the text out of the file
Add a videoA product demo, a webinar, a recorded talkUpload an MP4, MOV or WebM file up to 500 MB, or give a public YouTube link. Either can run up to 2 hours; private and unlisted YouTube videos cannot be read
Facts sheetThe claims your agents must get right, such as a starting priceOne row per claim, with its value, a source link, the date it holds as of and an owner, then Create the facts sheet. A workspace has one facts sheet; a second attempt opens the first

Files can be Word (.docx), PowerPoint (.pptx), spreadsheets (.xlsx, .xls, .csv), PDF, Markdown, plain text or JSON, up to 25 MB. Older formats such as .doc, and Apple's Keynote and Pages files, are refused with a message naming the format; save them as one of the above first.

A PDF must carry real text. There is no OCR, so a scanned PDF that is only pictures of pages is refused with "Could not extract any text from this PDF." Paste the content instead, or export a text PDF.

Step 2. Pick the document type

Document type tells agents what kind of material this is. The options are:

  • Research / analyst report
  • Competitor doc
  • Sales deck or one-pager
  • Customer interview / call transcript
  • Product doc / spec
  • Other paste
  • URL article
  • PDF upload, Word document, Presentation, Spreadsheet, and Plain text, markdown or json

The type follows what you are doing. From URL sets it to URL article, and picking a file sets it from the file's format. You can change it afterwards, and it is worth doing: a presentation that is really your sales one-pager is better filed as Sales deck or one-pager.

Who reads it

Who reads it decides which level of your organisation the document belongs to: The whole organisation, or one department or team. Only the levels you lead are offered. A team's document reaches that team's agents first.

Step 3. Title and content

Title is optional. Leave it blank and Nagent takes one from the content, for example the page or document's own title.

Then paste the text, enter the URL, or choose the file.

The Add knowledge form with pasted text filled in

Step 4. Tags: functions and industries

Two optional fields take comma-separated tags:

  • Functions, such as marketing, sales
  • Industries, such as bfsi, fintech

You do not have to fill them in. Nagent reads the start of the document and suggests functions, industries and topics on its own. Anything you type is kept, the suggestions are added to it, and functions and industries are stored in lower case. If the suggestion step fails, the document is still saved with whatever you typed.

For Prompt World, the transcript of a discovery call with a head of marketing might be filed as Customer interview / call transcript, with functions marketing, sales enablement.

Step 5. Add it

Select Add to Knowledge Hub. The button reads "Extracting + embedding" while Nagent reads the content and saves it, then opens the new document's page.

If the button stays on that label for more than a minute, open the Knowledge Hub list. The document has usually been saved and is shown there as pending; there is no need to add it again.

The Knowledge Hub list, each document with its type, its embedding status and when it was updated

What the status means

Saving a document and making it readable are two steps. After the save, Nagent indexes the text in the background: it splits it into passages and embeds them so agents can retrieve the relevant ones. The status in the list and on the document page tells you where that stands.

StatusWhat it meansCan agents read it?
pendingSaved, indexing not finishedNot yet
embeddedIndexed. The list shows how many chunksYes
failedSaved, but indexing did not workNo

A document usually moves from pending to embedded within moments. If it stays pending, open it and select Re-embed.

"Failed to index"

A failed document is stored and unreadable. Your agents behave as though it was never added. The document page shows Last embed failed with the reason.

To fix it:

  1. Open the document from the list.
  2. Select Re-embed to try again.
  3. If it fails again, the content is the usual cause. Check that the text on the page is real text and not empty, edit it if needed, and save. A change to the content re-indexes it on its own.
  4. If you no longer need it, select Archive. Archiving removes its passages from the index.

Our logic: a failed source counts against you

On Workspace set-up, the Knowledge sources card counts documents and assets, and has a row for Failed to index. If any source failed, the card shows "3 sources · 1 failed to index" and asks for your attention, even if you have added plenty.

That is deliberate. A count of rows would say you are done. But a source that failed is one your agents cannot see, and the card is there to tell you what they can read, not what you uploaded.

Workspace set-up, with the Knowledge sources card reading Set up and 1 source

How much your plan holds

Each plan includes a number of knowledge base documents and an amount of storage:

PlanDocumentsStorage
Solo5001 GB
Team5,00010 GB
Business25,00050 GB

Enterprise has no set limit. When a new document would go past either limit, it is refused with a message that starts "Your plan includes" and ends "New uploads are paused until you archive documents or upgrade. Nothing has been deleted." Archive documents you no longer need, or move to a larger plan on billing and plans.

Editing a document later

The document page lets you change its title, its functions and industries, and its content, then Save. Changing the content re-indexes it. The status and the time it was last indexed sit at the top right. Re-embed indexes it again without a change, and Archive takes it out of what agents can read.

A Knowledge Hub document page: the title, type and slug, the embedded status with its chunk count and last embedded time, the Functions and Industries fields, and the content

Who can do this

Reading the Knowledge Hub needs knowledge read permission, and adding or editing documents needs knowledge write permission. A workspace admin holds both.

Where to go next