Skip to main content
SupaCortex
Sign in Book a Demo
Solution

Stop asking the one person who knows

The answer is in a policy PDF, a Confluence page or a ticket from last spring. SupaCortex reads all of them and gives your team one place to ask - with the source named every time, so nobody has to take it on trust.

Book a demo See pricing
  • Every project at once
  • Sources on every answer
  • Private chat history

What is SupaCortex's internal knowledge assistant?

It is team chat over all of your workspace's knowledge. Signed-in staff ask in plain language and SupaCortex searches every project - or one, if they narrow it - across uploaded files, crawled sites, Google Drive, SharePoint, Confluence and approved Q&A from past tickets. Every answer cites the document, passage and project it came from, and says so when nothing covers the question. Your own tools can ask the same knowledge through an API.

  • Ask across every project, or narrow a chat to one.
  • Private history: rename, reopen, delete.
  • Every citation names its project.
  • Access is by project - not mirrored from Drive or SharePoint sharing.
Getting started

What you set up

  1. 01

    1. Projects by team

    "Operations", "Sales playbook", "Engineering". Projects keep sources tidy and let people narrow a question.

  2. 02

    2. Connect the sources

    Sign in once to Google Drive, SharePoint or Confluence and pick the folders, sites or spaces. Upload the PDFs and spreadsheets that live nowhere else.

  3. 03

    3. Keep them in step

    Feeds run on a schedule - daily on Starter, every 6 hours on Growth, hourly on Business - and fetch only what changed.

  4. 04

    4. Add the team

    Create users with a role; they sign in with a password or Google / Microsoft, with an authenticator code as the second step.

Capabilities

More than a search box

Answers, not links

A written answer from the passages that matter, with numbered citations you can open.

Honest when it does not know

A confidence gate stops it guessing. "I could not find this" is an answer too - and a gap to fill.

Official beats anecdotal

Mark documents as official, standard or community. Official policy outranks a past ticket that said otherwise.

Inside your own tools

API keys limited to chosen projects call /v1/search and /v1/answer, and /v1/ingest/documents pushes content in.

Learns from past tickets

On Business, resolved tickets become reviewed Q&A. Nothing is searchable until a person approves it.

Feedback on every answer

Thumbs up and down show which answers people trust - and which documents need work.

Read next

Team Chat Over All Knowledge

Your team asks across every project at once, with a private history and sources on every answer.

Google Drive, SharePoint & Confluence

Connect once with OAuth, pick folders, sites or spaces, and only changed files are fetched again.

Knowledge Projects

Keep each product, team or audience in its own project - its own sources, widget and API keys.

Search & Answer API

The same brain behind your own tools: scoped API keys, /v1/search and /v1/answer.

SupaCortex vs Glean

Enterprise search for every app, against one brain that also answers your customers.

SupaCortex vs ChatGPT for Teams

A brilliant general assistant, against one that only answers from what your company wrote.
Frequently asked

Questions people ask before they start

No - and it is better to know that up front. Access is by project, not by each file's sharing settings. Everyone with a SupaCortex account in your workspace can ask across every active project. So connect folders, sites and spaces your whole team may read, and leave confidential material - salaries, disciplinary files, board papers - out of the workspace.

Every user in your workspace, from the Viewer role up. Each person's chat history is private to them. Team users are seats on your plan: 3 on Starter, 10 on Growth, 50 on Business.

Not yet - Slack and Teams are on the roadmap. Today the team asks in SupaCortex's own chat, or in an internal tool of yours that calls the Search & Answer API.

They are available from the Growth plan and marked Beta on our integrations page while they run against more real-world libraries. Uploads, website crawling and the push API are generally available.

No. Documents are indexed for search and passed to the model only as evidence for one answer. The model runs on open models on infrastructure we operate, and we do not train or fine-tune on your data.

Give your team one place to ask.

Book a 30-minute demo on your own documents. We set up a 14-day trial workspace for you - no credit card, no setup fee.

Book a demo See pricing

Questions first? Email info@greatdevelopers.com or call +91 8585953085.

Still curious? Ask your favorite AI about SupaCortex.

ChatGPT Claude Perplexity Grok