Move records through a fixed scenario and inspect which values each module receives.
Workflow & automation · Documented · Documentation checked 2026-10-04
Make scenarios and Make AI Agents (New); connected model providers have their own terms.
Scenario limits vary by plan. AI Agents (New) is in open beta; custom AI providers require a paid plan.
The worked example is illustrative and has not been tested in a signed-in product account.
What it does and how it connects
Move records through a fixed scenario and inspect which values each module receives.
A scenario connects modules in a fixed process. Each module receives bundles of data; mapping selects values from earlier steps. An AI scenario adds model work to that route, while an AI agent can choose tools. Fixed routing is easier to inspect when the required steps are known.
Walkthrough
Use the product named in the access panel. The steps below combine documented controls with the editorial example.
- Create a sample scenario using a manual pilot rather than automatic live inputs.
- Add the intended input and one processing module.
- Map only required fields and inspect input / output bundles during Run once.
- Verify the result before adding connections, automatic scheduling, or write actions.
Worked example
Pass a fictional workshop request to a normalized draft record. Keep ID and source text visible so you can trace the output. Add AI only if classifying the request actually needs language interpretation.
Illustrative scenario
Input: request_id and fictional request text
Normalize: preserve original text and ID
Optional AI: suggest topic and missing details
Output: private draft for review
Live writes: disabled
Stop: absent ID or unusable input
Inspect and verify the result
Inspect actual bundles and mapped fields. Check that repeated records remain distinguishable and missing values are not silently replaced. Confirm connected accounts before adding an external action.
Limits and troubleshooting
Mapping a whole object where a module needs one value can cause failures. Multiple bundles can multiply later operations. If output is wrong, inspect data flow before rewriting an AI prompt.
Data, permissions, and actions
Connected modules send data to their services and act through their account connection. Scenario logs can retain payloads. Keep the pilot synthetic and scope every connection to the intended operation.
Related reading
Filters, review gates, and error routes
Route only valid approved records to consequential actions and stop safely on failures.
Fixed AI triage with a review filter
Classify synthetic requests while keeping authoritative review separate from AI output.
A bounded beta knowledge agent
Use the beta agent to retrieve approved workshop evidence and produce a validated response draft.
Evaluations: does the system do the job?
Create representative tests for quality, tool behavior, refusal, escalation, and the effects of a change.
Sources and verification
Documentation checked 2026-10-04. Examples are illustrative unless described otherwise.