EDUCATION
Promptev answers students and staff from your syllabi, handbooks, lecture material and research, names the document behind every answer, and says so plainly when the material does not contain one. Each course or department can have its own project, so nobody gets an answer from material that was not meant for them.
1,000 free credits for a 30-day trial · no card · model calls go to your provider on your own keys
What gets in the way
Students are already asking AI about your course. An agent attached to your own material answers from it and names the document; when the material does not contain the answer, that is what it says, rather than producing something plausible.
Content and questions work across many languages, in either direction, so a question asked in Mandarin, Arabic or Spanish can be answered from English course material without maintaining a translated copy of everything.
Marking schemes, references and case notes live alongside the handbook. Permissions travel with the content and the identity of the person asking is part of the search, so the same agent gives a student and a lecturer two different, correct answers.
Worked examples
Use case 01
Create a project for a course or a department, attach its syllabus, notes and handbook, and put an agent on it. Students ask about deadlines, reading and process, and get the document named. A project is a boundary, so one module’s assistant never reaches another’s material.
How it holds upProjects are the isolation boundary inside a workspace: their own agents, knowledge, tools and API keys.
Use case 02
Ingest a body of papers and ask across all of them at once — what a method was, where findings disagree, which paper said the thing you half remember. Scanned pages and figures are read by a vision model, and a misspelt author still finds their paper.
How it holds upExact phrases, fuzzy fragments and meaning all reach the same result list, and every hit names its paper.
Use case 03
A student writes in their own language and gets the answer in it, drawn from material written in another. No parallel corpus to maintain, and no separate assistant per language.
How it holds upAccent-insensitive and partial matching are part of the retrieval itself, so a name typed without its diacritics still finds the document.
Use case 04
New staff ask how to submit marks or where the ethics process lives, and get the institutional document rather than a colleague’s recollection. Put it in Slack, in a portal, or behind the roles you already assign — a viewer can talk to agents and nothing else.
How it holds upSingle sign-on provisions new joiners on first sign-in with the role you choose, and groups from your identity provider can drive who sees what.
Beyond chat
Write what the agent should do in plain words, attach the tools it may use, and choose what starts it. Every tool that writes, sends or spends carries its own approval rule, and a run that stops for a person resumes where it left off.
Webhook — a file arrivesAn example run
How it works
Connect one source, wait for it to be read, and ask a question. An afternoon is a realistic first result, not a quarter.
Step 01
Authorise it once with your own account, then pick exactly what Promptev should read — a specific Drive folder, a Confluence space, a Jira project — rather than everything you can see. Permissions travel with the content, and it stays in step as files change.
Step 02
Say what it should do in plain words, attach the knowledge it may use, choose the model — on your own provider key — and give each tool its approval rule. Test it in the built-in chat before anyone else sees it.
Step 03
The App, Slack, WhatsApp, a widget on your own site, your code through a scoped API key, or any MCP-compatible developer tool. Roles decide who may build and who may only talk to it.
What it connects to
Eight apps to connect — Google Workspace, Microsoft 365, Dropbox, Confluence, Jira, Azure DevOps, Slack and WhatsApp — are 16 services and 198 tools. Everything else is reached the same three ways: any REST API as an HTTP tool, seven database engines as database tools, or any MCP server you run. All three obey the same approval rules and land in the same audit trail.
What stays yours
Each of these is independent of the others, so you can bring one, several, or all of them. What remains is the platform work — connectors, agents, approvals, audit, channels — which is the part worth buying.
Managed by Promptev, inside your own cloud account in whatever region you choose, or fully on your own machines. The product is the same in all three.
Model calls go to your provider on your own keys, including a self-hosted or OpenAI-compatible endpoint. A workspace can run its documents, embeddings and retrieval on a database you own, and keep files in your own bucket.
SOC 2 Type II, with a data processing agreement and a service level agreement available and sub-processors published. Your content is never used to train a model, and every answer names the documents it came from.
Start here
Attach one module’s material, ask a question you set the answer to, and check the document it names. 1,000 free credits for a 30-day trial, no card.
Plain answers
Answers come from the material you attached, and each one carries the documents behind it, so a claim can be checked against a file you own. When your material does not contain the answer, the agent says so rather than producing one.
Yes. A project is the boundary inside a workspace — its own knowledge, tools, agents and API keys — so a project per course or per department means students only ever get answers from their own material. Someone can build in one project and only chat in another.
Content and questions work across many languages, and the two do not have to match: a student can ask in their own language about material written in English, and get the answer in the language they asked in.
Your content is used to answer your questions and nothing else — it is never used to train a model. Promptev holds SOC 2 Type II; a data processing agreement and a service level agreement are available, and sub-processors are published. Beyond that you can hold the data yourself: documents, embeddings and retrieval in a database you own, files in your own storage bucket, model calls on your own keys, and the whole platform running in your cloud account or on your own machines.
Managed by Promptev, inside your own cloud account in whatever region you choose, or fully on your own machines — the product is the same in all three. Beyond that, a workspace can point its documents, embeddings and retrieval at a database you own, keep files in your own storage bucket, and register your own connector applications so the consent screen carries your company’s name. Model calls always go to your provider on your own keys.
The same as for one person, because there are no seats and no plans. Promptev is pay as you go: a new workspace starts with 1,000 free credits for a 30-day trial and no card, then you buy credits when you need them from $5. Giving everyone a viewer role costs nothing until they use it. Model costs are billed by your own provider on your own keys. Enterprise is an annual licence for a custom deployment in your cloud or on your premises, with onboarding and support — talk to us at [email protected].