SALES & REVENUE
Promptev reaches your CRM through an HTTP tool or its MCP server, your pipeline data through a database tool, and your proposals, battle cards and call notes through the drives and wikis they already live in. One question, one brief, with every source named.
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 record is in the CRM, the last exchange is in a mailbox, the proposal is in a drive and the note from the technical call is in a wiki. Twenty meetings a week makes that a day of assembling context nobody bills for.
Point Promptev at its REST API and reading and writing records become tools an agent calls under your approval rules. If it ships an MCP server, attach that instead. If the numbers you actually report on live in a warehouse, a database tool reaches seven engines, ClickHouse and Snowflake among them.
Content stays in step with the source as files change, so the agent answers from the version that exists now rather than from the copy somebody pasted into a deck last quarter.
Worked examples
Use case 01
Ask once and get the record from your CRM, the recent thread from the mailbox and the relevant documents from the drive, assembled into one brief with each source named — instead of four tabs and a guess about which proposal was the final one.
How it holds upRetrieval carries the caller’s permissions, so a rep gets the deal material they are entitled to and nothing from the parts of the business they are not.
Use case 02
Attach a database tool to the warehouse or the replica holding pipeline data and ask in plain language — totals by stage, deals that have not moved, what closed against what was forecast. Results come back as a table or a chart, and can be written into a spreadsheet.
How it holds upSeven engines: PostgreSQL, MySQL, MariaDB, SQL Server, Oracle, ClickHouse and Snowflake. Read-only by default, over only the schemas you make visible.
Use case 03
Creating a record, moving a stage or logging an activity is a write, and writes into a CRM are exactly the thing you want a rule on. Give those tools “ask once” so the first call in a conversation stops for a person, or “always ask” so every one does.
How it holds upRequests reach the approver in the App, by e-mail or in Slack, they expire rather than waiting forever, and every call an agent makes is in the audit trail.
Use case 04
Connect the drives and spaces where battle cards, pricing sheets and market notes actually live. The agent reads what is there now, answers with the document named, and can post a weekly digest of what changed into a channel.
How it holds upFiles stay in step with the source as they change, and you pick exactly which folders and spaces are read rather than everything you can see.
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.
Schedule — weeklyAn 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
Describe your CRM’s API once, attach a drive, and ask for a brief on a deal you already know. 1,000 free credits for a 30-day trial, no card.
Plain answers
Any CRM with an API, through an HTTP tool — you describe the endpoints, methods and authentication once, and reading and writing records become governed tools — or through its MCP server if it publishes one. There is no ready-made CRM connector; the eight apps you connect are Google Workspace, Microsoft 365, Dropbox, Confluence, Jira, Azure DevOps, Slack and WhatsApp. An HTTP tool is not a second-class citizen: same approval rules, same audit trail.
Both, and you decide per tool. Reading usually needs no approval. For writes — creating a record, moving a stage, logging an activity — set “ask once”, where the first call in a conversation stops for a person and the rest of that conversation runs, or “always ask”, where every call stops.
Yes, with a database tool. Seven engines are supported, ClickHouse and Snowflake among them; connections are read-only by default and you choose which schemas and tables are visible. Answers come back as tables or charts and can be written into a spreadsheet.
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].