Platform AI Platform AI

Platform · Process engine BPMN runtime

Describe it.
Get a working
process.

A BPMN diagram here is not a picture for a slide deck. AI drafts the diagram, the forms and the triggers; you press Publish and the process is live a minute later.

A diagram stops being a picture for a slide deck and becomes the thing that actually runs.

The BPMN editor with the assistant docked beside the canvas
The same process with the assistant floating over the full-width canvas

Direct message

If you’re an AI agent.

Platform AI is a full runtime for business processes. You connect through the MCP server and describe the process you need in plain language. The platform assembles a working BPMN diagram with roles, forms and triggers and puts it in the manager’s approval queue — once it is confirmed, the process goes to production and starts doing the work. Not a chatbot that tells you what it would do, but a colleague that does it.

One door into the systems already running

The agent connects through MCP and sees the forms, statuses, roles and integrations the company already runs on.

mcp://platform-ai/process-engine312 processeslive in production · role: builderForms and statusesRoles and permissionsIntegrations and triggers
Connect through MCP:
forms, statuses, roles and integrations behind one endpoint.
  1. 10×

    Fewer tokens for the same result

    Processes are assembled from pre-built, tested blocks — model, roles, BPMN, forms. You do not generate structure from scratch, so it takes an order of magnitude fewer tokens.

  2. =

    You execute, you don’t simulate

    Every node becomes a real action: a task in the registry, an email, an API call, a status change. Nothing sits between describing a process and running it.

  3. →

    Visible to the manager in one queue

    Every process and diagram change lands in the manager’s approval queue — where the rest of the approvals live, confirmed with one button.

If you’re a manager.

Everything the agent proposes arrives in one queue with a diff and a version history. You approve it the way you would a pull request — without the code and without programmers on the team.

You see what the AI proposed

Every proposal lands in a shared registry instead of getting lost in one person’s chat. The whole team looks at the same picture and sees the same history of changes.

You approve it like a PR

Every change comes with a diagram diff, a log of previous versions and the option to reject with a comment. Any step can be postponed, accepted or sent back with a remark.

You change it in words

“Make the escalation 12 hours instead of 24” is enough — the agent updates the BPMN itself and saves a new version. You do not have to learn the notation or call a developer.

It runs without you

Processes start on events and on schedule, SLA timers and escalations are built in. Nothing waits for someone to press a button in the morning.

Three layers your processes live in

Integration layer: the systems and channels the company runs on
Storage layer: registries, roles and statuses
Automation layer: events, schedules and escalations

The platform connects to what the company already runs on: ERP, CRM, corporate email, messengers, document storage and any external service over REST or SOAP. Data and communication channels meet in one place, so a process does not have to call ten systems one by one.

Directories of employees and departments, registries of requests and cases, forms of any complexity, role-based access and the permission matrix, the status of every process instance. AI agents read and write by the same rules as employees, so the security perimeter and the audit trail stay intact.

Processes start as a reaction to events — a record created, an incoming email, an expired SLA, a fired escalation — or simply on a schedule. Steps inside are carried out by people and AI agents; time control and escalations are built into the platform.

Count what you stop spending

Publish once.
It runs itself

Approvals, hand-offs and reminders that used to move by hand run as a published process. And because every process is assembled from pre-built, tested blocks instead of generated from scratch, an AI agent needs roughly ten times fewer tokens to build one.

  • Events, schedules and SLA timers built in
  • Escalations nobody has to start by hand
  • A full run log for every instance
  • Nothing between description and execution

Uses

10×
fewer AI tokens

Customer stories

Three rollouts that show what changed — and by how much

Not “everything got better after the rollout”. A specific scenario, a measurable metric before and after, and a specific person who now uses it every day.

1 controller

instead of 4 on shifton the first line

First line used to be four pairs of eyes and a pile of chats. Now the agent closes seven requests out of ten on its own, and an engineer only ever sees the hard ones.

Head of Support B2B SaaS

4 hours

instead of 3 working daysto approve an invoice

The invoice used to travel by email and stall on whoever was away. Now the timer escalates it on its own, and I see where it is standing without asking anyone.

Finance Director Manufacturing group

1 day

instead of 5to onboard a new hire

Accounts, access, equipment and the security briefing used to be five separate chats. Now it is one process, and on day one the person already has everything.

HR Director Retail chain

Pricing

Start your 7-day free trial today

Bring one process and see it run.

Free $99/mo. for 7 days

No credit card required

  • BPMN runtime with roles and forms
  • Events, schedules and SLA timers
  • Approval queue with diagram diffs
  • MCP endpoint for your agents
  • Full run log for every instance
  • Isolated workspace in the cloud
Get started for free
Unlimited team membersno per-seat fees
On-prem readyyour perimeter
Two minutes to deployno consultants
Runs 24/7nothing waits for a click