Frequently asked questions
What CorpusKit Cloud does, where documents are stored, what it costs and how to start.
CorpusKit Cloud
What is CorpusKit Cloud?
CorpusKit Cloud is Noice's hosted service for CorpusKit, the open source research portal. Noice runs the portal on your documents, applies upgrades and handles support in Melbourne business hours. People ask the portal a question and get an answer that cites the page it came from.
What is a knowledge box?
A knowledge box is a private, searchable collection on the Progress Agentic RAG platform. It holds your documents, their index and the knowledge graph, and every portal sits on one.
What can people do in a portal?
Ask questions and get cited answers, search by meaning or exact words, browse the library, explore the knowledge graph, keep an investigation open for months, generate briefings and FAQs with references, and set short knowledge checks.
Which files can it read?
PDFs, Office files and web pages, and on a Pro licence, audio and video. Each upload through the portal can be up to 100 MB, and a website can be re-synced on a schedule. Scanned collections may need Pro.
How are answers checked?
Figures, populations, named studies and years are tested against the cited text, sentence by sentence. A sentence that fails is removed, and a note says so. Each answer is rated high, moderate or low confidence.
Can we use a portal from an AI assistant?
Yes. Each portal has a read-only MCP connector. A portal administrator creates a key, and any MCP-capable assistant or agent can search the collection, ask for cited answers, fetch a document and browse the catalogue. Each key reaches one portal and can be revoked at any time.
Data and security
Where are our documents stored?
Your documents, their index and the knowledge graph are held in your knowledge box. Noice creates knowledge boxes in Progress's Australian region (AWS Sydney) by default, and in other regions on request. Sign-in emails, portal settings, sessions and saved investigations are held by our hosting provider, configured for its Oceania region.
What do language models receive?
Language models receive document text for summaries and labels, and each question with the passages found for it. Available models vary by Progress plan; ask us where one runs before you load documents.
How do people sign in?
Sign in with an emailed link, or with your organisation's single sign-on (Microsoft Entra ID, or another OpenID Connect provider such as Okta or Google Workspace), set up on request.
Who can see a portal?
A portal can be public, open to everyone who signs in with your organisation's single sign-on, or restricted to the people you invite. It has four roles, from viewer to portal administrator, and an exportable audit log.
What happens to our original documents?
They stay where they are. CorpusKit reads a copy of your documents, and your document system stays as it is.
Will you complete our security questionnaire?
Yes. We complete security questionnaires during evaluations, and the code is public at github.com/noicework/corpuskit.
Pricing and buying
How much does it cost?
Hosted is A$750 a month and Managed is A$1,750 a month, excluding GST and the Progress Agentic RAG licence. Setup packages start at A$4,950, or you can load and configure the portal yourself.
Are there per-user fees?
No per-user fees. Progress plans allow any number of named users, and CorpusKit Cloud is a flat monthly or yearly fee.
Do we need a Progress licence?
Yes. Every portal sits on a Progress Agentic RAG knowledge box, licensed in your organisation's name. You can buy the licence directly from Progress or through Noice, and a licence you already hold works too.
Can the portal use our own web address?
Yes. On Hosted and Managed, your portal can live at your own web address, such as research.yourorg.au, or at yourname.corpuskit.cloud. A portal on your own web address keeps that address if you leave.
What happens if we leave?
The licence and knowledge box are in your organisation's name, so your documents, index, labels and graph stay with you. Each investigation and saved session exports to Word, and you can run the open source portal yourself.
Getting started
How do we try it?
Ask for a 14-day trial, using reports you have already published. Trials run at yourname.corpuskit.cloud, by invitation. Trial documents are held in Noice's Progress account in the Australian region.
Can we see it working first?
Yes. Ask the documentation portal a question at demo.corpuskit.org, or email hello@corpuskit.cloud to book a demo on your own collection.
Can we run CorpusKit ourselves?
Yes. CorpusKit is open source under Apache 2.0. It runs on common cloud platforms or as a container, with your own Progress Agentic RAG licence.
Getting started
Ask for a 14-day trial, using reports you have already published. To book a demo on your own collection, email hello@corpuskit.cloud.