Routes

A route connects one actor to another. The route carries an activation prompt — a short description of when this route should fire. The platform uses it to decide which actor handles the next turn.

​

Draw a route

Adding an actor with Add actor in a selected actor’s toolbar draws the route for you. To open a route later, click its label, or When? on a route that has no label yet.

​

Writing good activation prompts

Activation prompts read like instructions to a smart teammate, not configuration. Think of them as the trigger description an account manager would give to their team.

​

Good

When the user reports a billing problem (a charge they don’t recognise, a duplicate, a refund request) and has provided their account email.

Whenever the conversation touches scheduling — picking a time, rescheduling, or asking when something is available.

When the user wants to talk to a real person, expresses frustration, or asks about something outside our published policies.

​

Less useful

intent = billing

if user said pricing

classification: support_tier_2

The platform can route on the precise language; you don’t need to compress to keywords.

​

Multiple routes from the same actor

An actor can have many outgoing routes — one per route it should consider. When the routing layer evaluates the user’s latest turn, it considers all outgoing routes from the current actor and picks the one whose activation prompt fits best.

​

Route labels

Labels are short — 1 to 3 words. The platform auto-generates them from your activation prompt every time the prompt changes. To change a label, reword the prompt. The activation prompt is the source of truth for routing — labels are only for canvas readability.

​

What the routing layer actually does

When the user sends a message, the platform evaluates:

1. Is the current actor’s job done? If the actor’s Definition of Done is satisfied — hand off.
2. Should we hand off anyway? Check each outgoing route’s activation prompt against the conversation. If one fits clearly, route to that target.
3. Otherwise — stay on the current actor.

You don’t write any of this logic. The combination of routes + activation prompts + Definition of Done gives the platform everything it needs.

​

Limit who can reach an actor

An activation prompt only guides the router. To keep an actor out of reach until a parameter or slot matches (managers only, or only once an order number is known), or until an AI judges that a condition you wrote is met, add an Only when… condition to the route: see Conditional routes. A route with a condition is drawn dashed on the canvas; every other route is solid.

​

Route handles (advanced)

Most routes connect from an actor’s default output to the target’s default input — that’s the only case for free-form actors. When you build scripted actor flows with ai-condition steps, routes have handle-specific outputs (true / false). You don’t usually touch this directly — the step builder handles it for you.

​

Delete a route

Click the route’s line, then the trash icon above its label, or press Delete. You can also open the route and click Delete route. A toast offers Undo, and Ctrl+Z on the canvas puts it back too.

​

Reusing the Sales Triage flow

The running example throughout these docs uses two routes: The Start → Triage route needs no activation prompt — it’s the default entry point.

​

Next