ENGINEERING & DEVOPS
Promptev connects Azure DevOps, Jira, Confluence and Slack out of the box, and reaches the rest of the stack — your Git host, your internal services, your databases — through HTTP tools, database tools and MCP servers. Agents summarise work, draft updates and open tickets, with an approval rule on every action that writes.
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 work item is in Azure DevOps or Jira, the runbook is a Confluence page, and the decision that explains both is a Slack thread from March. Answering “why is it like this?” means visiting all three, in order.
Your Git host, your paging tool, that internal service with the good API. Point Promptev at any REST endpoint and it becomes a tool an agent calls under the same approval rules and audit trail as a built-in one. Attach an MCP server you already run and its tools appear beside the rest. The answer to “do you integrate with X” does not depend on our roadmap.
Reading a board is safe. Transitioning an issue, posting into a public channel or calling your deploy API is not. Every tool carries its own approval rule — no approval, ask once, or always ask — and every run lands in the audit trail.
Worked examples
Use case 01
Ask one question and get one answer drawn from work items, repositories, pipelines and boards in Azure DevOps, issues and sprints in Jira, pages in Confluence and threads in Slack. The answer names where each part came from.
How it holds upAzure DevOps alone carries 22 tools; Jira 16, Slack 12, Confluence 10. Each service brings both knowledge to answer from and actions an agent can take.
Use case 02
Have an agent read the board each morning and post what moved, what is blocked and what is still unassigned into a channel — or compose several agents into an orchestration where one gathers, one writes and one delivers.
How it holds upA run starts on a schedule, on a webhook, or when another agent calls it as a tool. Posting is a write, so it takes whichever approval rule you gave it.
Use case 03
Describe your Git host’s REST API once and searching, reading and commenting become governed tools. Point a database tool at a read-only replica and an agent answers questions about production data in plain language. Attach an MCP server you run and its tools sit beside the built-in ones.
How it holds upNone of these is second-class: an HTTP tool, a database tool and an MCP tool obey the same approval rules and land in the same audit trail as a connector tool.
Use case 04
Sign in to the promptev workspace MCP from Claude Code, Cursor or any MCP client and build agents as yourself. Each project is also an MCP server at its own URL, so an MCP-speaking developer tool gets that project’s knowledge and its governed tools with the caller’s permissions intact. There is also a REST API with scoped keys, and a webhook trigger for anything that needs to start a run.
How it holds upThe same knowledge tool is in the Python and JavaScript SDKs (pip install promptev, npm install @promptev/client) and the HTTP API: upload documents and search them with a project key that reads only its own project.
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.
WebhookAn 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
Connect a board and a wiki, ask something you would normally go looking for, and see where the answer came from. 1,000 free credits for a 30-day trial, no card.
Plain answers
The eight apps you connect are Google Workspace, Microsoft 365, Dropbox, Confluence, Jira, Azure DevOps, Slack and WhatsApp. Azure DevOps is a full connector, with 22 tools across work items, repositories, pipelines, boards and sprints. Any other code host is reached as an HTTP tool over its REST API, or through an MCP server if the vendor or your own team runs one — and either route obeys the same approval rules and lands in the same audit trail as a built-in connector.
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.
No, and it is not trying to. An IDE assistant helps you write the file in front of you. Promptev works across the systems around the code — the board, the wiki, the channel, your own services — and takes governed actions in them. They sit together happily: each project is an MCP server, so an MCP-speaking developer tool can pull that project’s knowledge into the editor.
Only if you allow it. Actions are the tools you attach, and each one carries its own approval rule: no approval, so it simply runs — right for reading; ask once, where the first call in a conversation stops for a person and the rest of that conversation runs without asking again; or always ask, where every call stops. Requests are answered in the App, by e-mail or in Slack, and they expire rather than waiting forever. Every change and every run is in the audit trail.
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].