Rules drive every step
The engine follows your process step by step, with no AI steering the route. This is the default, and the right fit for most work.
The Vertesia process engine runs business work that mixes clear rules, AI agents, and human review. The engine decides what happens next. Agents do the reading and judging. Every step is logged, and work picks up again after a restart.
Click a part of the engine to see how it works.
Workflow tools force fixed code, and chat agents choose their own route. Flip the switch to see what changes when the engine owns the route and agents do the thinking.
Treated as attachmentsRead, understood, and acted on at every step
Hard-coded rules or an AI's guessClear conditions the engine checks
Can change anything they reachCan only change the fields each step allows
Approvals lost in emailHuman tasks built into the process
Timeouts and lost progressWaits for days, then picks up where it left off
Tell the Studio Assistant what you need, share a screenshot or whiteboard photo, or share a BPMN diagram. The assistant drafts the process and checks it before it can run.
An agent step reads the contract and pulls out the parties, the value, and risky clauses. It can only fill in the fields its step allows.
Anything the agent tries to write outside its fields is rejected.
The engine checks conditions you set, like “contracts over $50,000 go to legal.” An agent can suggest a path, but only from the options you defined.
The process creates a task in the legal team's inbox and waits. It can wait for days without using compute, then continues as soon as someone answers.
Approved contracts are stored and filed. Vertesia keeps a full history of which steps ran, what each one changed, what the agent did, and who approved it.
Traditional process engines were built for two kinds of actors: code that runs fixed steps and people who make judgment calls. Vertesia adds a third, AI agents, which can reason like people and run like code, but only within the limits the engine sets.
Every step in a process declares exactly what information it can add or change. The engine enforces this strictly, so no agent can act outside what the process permits.
A process moves forward on clear, defined conditions, not on what an AI happens to say. Transitions are triggered by data, by an agent's choice from a fixed set of options, or by a person.
Long-running processes can pause and wait for a person to review, without wasting compute. Human review is a core feature, not an edge case.
An optional AI supervisor can steer a process with a set of approved commands. It never rewrites the process itself. Every command is logged with a full audit record.
Already have BPMN diagrams? Share them with the Studio Assistant. It turns them into a Vertesia process and keeps a link to the original diagram.
The Studio Assistant can draft a process from a plain-text description, a screenshot, or a whiteboard photo. Each draft is checked before it runs. The assistant can also test it and suggest changes for a person to approve.
Build big processes from smaller ones. Reuse steps like invoice review or document intake, run branches side by side, and run code when you need an exact answer.
Run a process on fixed rules, add an AI supervisor that can step in, or hand open-ended work to an agent.
The engine follows your process step by step, with no AI steering the route. This is the default, and the right fit for most work.
An AI supervisor watches the process and can retry, skip, or reroute a step. The engine checks each command before it applies it.
For open-ended work, an AI agent can work on its own, outside a process, with its tools and your permissions.
Instead of people reading every document, routing it, and filling out forms, AI agents handle the work. People stay in the loop for approvals, exceptions, and judgment calls.
Every step can use your content. Process steps can search, read, and update documents stored in Vertesia, under the same access rules.
Agents work within your permissions, and their work is logged so you can audit it. Your content stays under your control and is never used to train public AI models.
Agentic workflow automation means AI agents do the steps of a business process for you. People step in only when needed. Unlike rule-based tools, agents can read documents, decide based on what they find, and handle cases that don't fit a script.
An agent works toward a goal and chooses its own steps. A process has named steps, clear rules for what happens next, and pauses for human review. Inside a process, agents do open-ended work, like reading a document, while the engine decides the route.
Yes. Share your BPMN diagrams with the Studio Assistant, and it turns them into a Vertesia process. Choices, parallel paths, and loops map to process steps. You review the draft and confirm before it is published.
Processes are durable. Each step is saved as it finishes, so a restart, a redeploy, or a long wait doesn't lose progress. A failed step can be retried, and the history shows exactly what happened.
Each task goes to a specific person or to a team, such as legal or finance. Team members see the task in their inbox, can open the whole process for context, and answer it there.
Yes. Some tasks work best with a different model. You can pick a model for each step in a process, to balance quality and cost.
See how Vertesia handles your document work with AI agents, clear rules, and human review.