LEGAL & COMPLIANCE
Promptev builds AI agents for legal and compliance teams that answer from your contracts, matters and policies, and name the documents behind every answer. Each person only ever gets an answer from files they could have opened themselves, so one agent can serve partners, associates and contractors without leaking between 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
The agreement is in a Drive folder, the amendment arrived by e-mail, the playbook is a Confluence space and the executed copy is in a Dropbox share. Answering one question means opening every one of them and hoping nothing was missed.
Upload a matter file to a chat assistant and the permissions stay behind. Promptev carries the identity of the person asking into the search itself, so a document they could not open is never retrieved for them — not for an answer, a summary or a follow-up.
Legal work is verified work. An assistant that cannot show which document an answer came from creates the task of finding out rather than removing it. Every Promptev answer carries the documents it came from.
Worked examples
Use case 01
Connect the places your agreements already live and ask in plain language. “What is the liability cap with this supplier?” “Does this NDA renew automatically?” The agent searches everything the person asking is entitled to see, and names the documents behind the answer.
How it holds upPermissions are part of retrieval rather than a filter applied afterwards, so a document the person may not open never reaches the answer, and every answer names its source.
Use case 02
Point an agent at a folder of executed agreements and ask it for the terms you care about — termination, indemnity, notice periods, governing law — then have it write the result into a spreadsheet. Scanned pages and photographed exhibits are read by a vision model on your own key.
How it holds upEmbedding your content is free. Reading a document costs credits by its size, and pages that need a vision model cost more — nothing is priced per lawyer.
Use case 03
Run an agent on a schedule across your policy space and your regulatory material, and have it post what changed into a channel. Where it needs to act — open an issue, e-mail an owner — you decide per tool whether it does that on its own, asks once, or asks every single time.
How it holds upThree approval settings per tool: no approval, ask once for the conversation, or always ask. Requests arrive in the App, by e-mail or in Slack, and they expire rather than waiting forever.
Use case 04
Ask in English about an agreement written in German, or in Arabic about an English policy — content and questions work across many languages, in either direction. A misspelt party name or a half-remembered phrase still finds its document.
How it holds upSearch finds a document by its meaning, by its exact words or by a fragment of them, and only if you were allowed to open it.
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 compares
Both of these are good products, and neither is priced the way Promptev is. Seat pricing means deciding in advance who is allowed to benefit; paying for work done means a viewer costs nothing until they use something.
| Glean | ChatGPT Enterprise | Promptev | |
|---|---|---|---|
| How it is priced | Per seat, plus consumption credits | Per seat | Pay as you go — no seats, no plans |
| Reported entry point | Around $50–75 per user per month | Reported $45–75 per seat per month | 1,000 free credits for a 30-day trial, then credits from $5 |
| Reported minimum | Around 100 seats | Around 150 seats | None |
| How you buy it | Quoted through sales | Quoted through sales | Self-serve, or an annual licence if you want one |
| How knowledge gets in | Hundreds of connectors | Documents you upload | 16 connected services, plus any REST API, seven database engines and your own MCP servers |
| Where it can run | Confirm with the vendor | Confirm with the vendor | Managed by us, your own cloud account, or your own machines |
Credit where it is due. Glean is a serious product — hundreds of connectors, a choice of many models, and permission-aware access built in, which is theirs as much as ours. Assistant products give a person immediate help with excellent models and no setup at all. Promptev differs on the shape of the pricing and on where it runs: no seats and no minimum, and a workspace can run on its own database, its own models and its own storage, with the engine that enforces the permission boundary open for you to read.
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
Connect one source, ask a question you already know the answer to, and check the citation it gives you. 1,000 free credits for a 30-day trial, no card.
Plain answers
Sixteen services arrive ready across eight apps to connect: Google Workspace (Drive, Docs, Sheets, Slides, Gmail, Calendar), Microsoft 365 (OneDrive, SharePoint, Outlook mail and calendar), Dropbox, Confluence, Jira, Azure DevOps, Slack and WhatsApp — 198 tools in total. You authorise a source once and then pick exactly what Promptev should read: a specific Drive folder, a Confluence space, a Jira project, rather than everything you can see.
The identity of the person asking is part of the search rather than a filter applied afterwards, so material they could not open is never retrieved for them by any route. Answers follow current permissions: if someone loses access to a document, they lose it in Promptev too. Every answer names the documents behind it, so it can be checked.
Both. An agent can create an issue, write to a spreadsheet, send a message or query a database, and each of those tools carries its own approval rule: no approval, ask once for the conversation, or always ask. Every run lands in an audit trail written in language a person can read.
Answers come from the material you connected, and each answer carries the documents it came from — so a citation is a file in your own store that you can open. When the material does not contain the answer, that is what the agent says.
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].