How a domain agent differs from a chatbot or a general agent
A general-purpose agent is given a goal and a toolbox and left to plan. A domain agent is given one step of a mapped process — "match the invoice to the purchase order", "route the new lead", "count the catalog and send the digest" — with the inputs that step receives, the outputs it must produce, and the rules that govern it. The narrower scope is the point: it can be tested, its writes can be gated, and a person can tell at a glance whether it did the right thing.
In tacitrun the process comes first. A business user describes the workflow or uploads the procedure; the platform compiles it into a graph of steps and then composes one domain agent per step that a person used to do by hand. The agent inherits its job description from the graph, not from a prompt someone wrote in isolation.
What a domain agent is allowed to do
Reads are free; writes are not. A domain agent may read from any system it is connected to, but anything that changes a record — sending an email, creating an order, updating a field — stops in an approval queue for a person to accept, modify or reject. That gate fires on the actual call to the system, not on the agent’s own judgement about whether the action is risky.
Autonomy is earned. A new domain agent only drafts. It runs in shadow mode beside the team, its proposals are compared with the human decisions, and only after it agrees often enough, and IT approves, can it act on its own.
The terms, as the product defines them
- Domain Agent
An AI agent built from a process step, scoped to one job.
An AI agent generated from a process. It is scoped to one part of the workflow, knows the relevant policies (from your corpus), can use the tools it needs, and is tested before it ever acts. A domain agent starts by drafting decisions for a human and only earns the right to act on its own after it agrees with your team often enough in shadow mode.
- Process
A workflow, mapped as a step-by-step graph.
A business workflow — like vendor onboarding, invoice approval, or returns intake — captured as a graph of steps (a BPMN-style diagram). Each step is done by a person, a system, or a domain agent. A process is the blueprint; domain agents are what run parts of it.
- Earn autonomy
A domain agent acts on its own only after it proves it agrees with you.
The core safety idea: nothing acts autonomously by default. A domain agent drafts → is reviewed → shadows → and only then, with evidence and a human approval, earns the right to act. Trust is earned, not assumed.
Questions people ask about this
- What can a Gmail (Google Workspace) domain agent actually do?
- Once Google Workspace is connected, a domain agent can: search/list messages with the normal Gmail search syntax (e.g. "category:promotions newer_than:7d"), read a message, list labels, archive or label messages (single or up to 1000 at once), move a message to Trash, and send email. Archive means removing the INBOX label — the message stays searchable, it just leaves the inbox. These are grounded in the Gmail API, not simulated. Two notes: (1) it needs the gmail.modify scope, so if you connected Google Workspace before this was added, reconnect it (Tacit re-prompts consent). (2) To run automatically on incoming mail today, use a scheduled domain agent that searches recent messages and archives/labels them — a true "new email" push trigger is on the roadmap, not yet available.
- What’s the difference between a process and a domain agent?
- A process is the workflow blueprint (a graph of steps). A domain agent is an AI agent built from part of that process to actually run it.
- Will a domain agent act without my approval?
- No — not by default. A new domain agent only drafts decisions for a human. It can act on its own only after it proves itself in shadow and a human promotes it.
- How do I cancel my subscription, and what happens to my domain agents?
- The workspace owner can cancel from Workforce & billing (/foundry/usage) → Plan & subscription. Cancellation is "at period end" and is set on your Stripe subscription at the same moment: the current billing period is charged in full (no refund), Stripe bills nothing after it, and your domain agents keep running until that period ends — the exact date is shown on the card once you confirm. On that date your plan drops to Free and all your digital workers are shut down (their services are deleted, so they stop running and stop incurring compute/AI cost). You can undo the cancellation any time before that date with "Resume subscription", which also clears it at Stripe. Your domain agent definitions are kept, so if you resubscribe you just redeploy them.
Related
See it on one of your own processes. Free for the whole product for a trial period, no card needed to start, every write held for your approval.