01
The same hundred questions, every intake
Holiday, expenses, probation, the laptop. The answers are written down, and nobody can find them in their first week — so the questions arrive as direct messages instead.
HR & PEOPLE OPS
Automate the HR questions people ops answers every week. Employees ask in Slack, in WhatsApp or in a portal, and the assistant answers from your policies, benefits documents and onboarding material, naming the document each time and only ever showing someone what their own access allows. Scheduling, ticketing and anything else that writes waits for a person if you say so.
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
Holiday, expenses, probation, the laptop. The answers are written down, and nobody can find them in their first week — so the questions arrive as direct messages instead.
Salary bands, performance notes and case files sit in the same drive as the handbook. An assistant that indexes everything and answers everyone is the wrong shape for HR. Permissions travel with the content, and the identity of the person asking is part of the search.
A drive folder, a wiki space, a spreadsheet somebody owns. Nobody is going to consolidate them this quarter, and they do not have to — an agent can read all of them and stay in step as they change.
Worked examples
Use case 01
Attach the handbook, the policy space and the benefits documents, then put the agent in Slack or WhatsApp. “How much leave have I got left?” “What is the parental leave policy?” comes back with the document named — and only from documents that person could open themselves.
How it holds upA viewer can talk to agents and nothing else, which is the right role for most staff and costs nothing until they use it.
Use case 02
Give new joiners an agent that knows the handbook, the IT setup guide and the team structure from their first morning. Content stays in step with the source as documents change, so last quarter’s policy does not keep answering this quarter’s questions.
How it holds upA project is a boundary: its own knowledge, tools and agents. An onboarding project and an employee-relations project never see each other’s material.
Use case 03
The agent checks availability, proposes slots and creates the event with its attendees, in Google Calendar or Outlook Calendar. Creating an event is a write, so set that tool to ask once or always ask and a person confirms before an invitation goes out.
How it holds upGoogle Calendar and Outlook Calendar are connected services with 7 and 9 tools respectively — events, calendars, scheduling and availability.
Use case 04
Your HRIS almost certainly has an API, and almost certainly is not on anybody’s connector list. Describe it once as an HTTP tool, or point a database tool at the people database read-only, and headcount questions get answered from the system of record rather than from a stale export.
How it holds upDatabase connections are read-only by default, and you choose which schemas and tables are even visible.
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.
Chat or scheduleAn 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 the handbook, put the agent in Slack, and check that it names the page it answered from. 1,000 free credits for a 30-day trial, no card.
Plain answers
Yes. Book a 30-minute call and we walk you through one built on your own handbook, or start free with 1,000 credits and build it yourself: upload the handbook, give the assistant a line of instructions, try it in the built-in chat and publish it.
Yes, and it is the default rather than a setting to remember. Permissions travel with the content and the identity of the person asking is part of the search, so material someone could not open is never retrieved for them. Answers follow current permissions: when access changes, the answers change with it. Projects give you a second boundary — an employee-relations project and an onboarding project never see each other’s material.
In the App, in Slack, in WhatsApp — including documents, images and voice notes — in a portal or a widget on a page you control, and through the API. One agent is attached per channel, so the same assistant answers everywhere.
Yes. Google Calendar and Outlook Calendar are connected services, so the agent can check availability and create events with attendees. Because that writes, give the tool an approval rule — ask once for the conversation, or always ask — and the request reaches the approver in the App, by e-mail or in Slack.
Then it is a configuration task, not a feature request. Sixteen services across eight apps arrive ready. Everything else is reached three ways: point Promptev at any REST or HTTP API and it becomes a tool an agent calls under the same approval rules and audit trail as a built-in one; attach a database tool and an agent queries PostgreSQL, MySQL, MariaDB, SQL Server, Oracle, ClickHouse or Snowflake in plain language, read-only by default and over only the schemas you make visible; or attach any MCP server you run or trust. It works in both directions too — each project is itself an MCP server at its own URL.
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].