01
The same questions, and the answers already exist
The documentation covers it. The customer could not find it, and neither could the agent who joined last month. The gap is not knowledge, it is retrieval.
CUSTOMER SUPPORT
Deploy a support agent that answers from your documentation, product guides and internal wiki — on your own website, in Slack, in WhatsApp, or through your code. It names the source of every answer, and when your material does not contain one it says so rather than inventing it.
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 documentation covers it. The customer could not find it, and neither could the agent who joined last month. The gap is not knowledge, it is retrieval.
Content and questions work across many languages, including asking in one language about material written in another — so English documentation can answer a question asked in Arabic, Japanese or Spanish without maintaining a translated copy of everything.
A customer must not see what the internal runbook says, and your team should not have to keep two knowledge bases to guarantee that. Permissions travel with the content, so the boundary lives in the retrieval rather than in a prompt.
Worked examples
Use case 01
Add it with one script tag. It renders in the page rather than in a frame, so it carries your styling, and it only runs on the domains you name. It answers from the documentation, guides and wiki pages you attached, and names where each answer came from.
How it holds upWhen the material does not contain the answer, the agent says so. It does not fill the gap.
Use case 02
There is no ready-made ticketing connector, and there does not need to be. Describe your helpdesk’s REST API once and reading, creating, assigning and updating tickets become governed tools — or attach its MCP server if it ships one. Either way it is a tool like any other.
How it holds upAn HTTP tool obeys the same approval rules and lands in the same audit trail as a built-in connector tool. Writing a ticket is a write, so give it “ask once” or “always ask”.
Use case 03
The same agent answers in the App, in Slack channels and threads, in WhatsApp — documents, images and voice notes included — in the widget on your site, and in your own code through a scoped API key. One agent is attached per channel, so nobody maintains six versions of the same assistant.
How it holds upSix places an agent can answer: the App, Slack, WhatsApp, your website, your code over REST, and any MCP-compatible tool.
Use case 04
Give the agent a tool that opens a ticket or posts into a channel when it cannot answer, and set that tool to ask once or always ask so a person sees it before anything leaves the building. Requests can be answered in the App, by e-mail or in Slack.
How it holds upApproval requests expire rather than waiting forever, and a retried turn re-parks on the request already in front of the approver instead of stacking another behind 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.
ChatAn 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 your documentation, embed the agent with one script tag, and watch which source it names. 1,000 free credits for a 30-day trial, no card.
Plain answers
Yes — one script tag. It renders in the page rather than in an iframe, so it can carry your own styling, and it only runs on the domains you name.
Yes, through an HTTP tool or an MCP server rather than a ready-made connector. Describe the endpoints, methods and authentication once, and reading, creating, assigning and updating tickets become tools an agent calls under your approval rules and inside your audit trail. Anything with an API is reachable this way, without waiting for us to build it.
Content and questions work across many languages, and the two do not have to match: a customer can ask in their own language about documentation written in English, and get the answer in the language they asked in.
It says so. Answers come from the material you attached and each one names the documents behind it, so an empty result is reported as an empty result. Attach an escalation tool — a ticket, a channel message, an e-mail — and set it to ask once or always ask if you want a person in the loop first.
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].