Use the beta agent to retrieve approved workshop evidence and produce a validated response draft.
Workflow & automation · Changing · 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.
An illustrative recipe. This website does not run the automation.
The goal and the right kind of system
Use the beta agent to retrieve approved workshop evidence and produce a validated response draft.
An agent fits if it must select among approved retrieval tools. Use a fixed route once the lookup and output are predictable.
Inputs and connected services
Inputs: eligible AI Agents (New), Knowledge, run input, scoped conversation ID, tool contracts, and review owner.
Services: Make’s beta agent, selected model provider, and approved tools; MCP is optional with separate authority.
The steps
An illustrative sequence to adapt and test before using real data or enabling ongoing work.
- Configure a narrow goal, provider, read-only tools, and supported execution bounds.
- Keep reusable Knowledge separate from run files and unrelated conversation IDs.
- Inspect selected tools and validate structured output.
- Route the answer to human review; apply a separate action gate if writes are ever added.
Outputs and human checkpoints
Outputs: source-backed response draft, unresolved details, and run / usage evidence.
Human checkpoints: verify source support and actual tool activity. Do not use agent self-review as an enforced approval.
Exceptions, permissions, and stopping conditions
Permission boundary: retrieval and draft only. Missing source, conflicting history, or tool failure produces needs_review.
Stop at supported step / time bounds, invalid output, or budget exception. Shared context and uncertain writes require manual reconciliation.
Adaptable prompt
Answer from the approved Knowledge and read-only lookup tools. Give evidence and unresolved details in the required output structure. Do not write records or send messages. Stop on conflicts, missing sources, or execution limits.
Related reading
AI Agents (New): tools and configuration
Configure a beta agent with a bounded goal, named tools, and explicit execution limits.
Knowledge, conversation IDs, and structured output
Distinguish reusable files from run inputs and request an output downstream modules can validate.
Filters, review gates, and error routes
Route only valid approved records to consequential actions and stop safely on failures.
Credits, provider billing, and run review
Track scenario usage and model-provider usage as different parts of operating cost.
Designing an AI workflow
Make a useful task repeatable with clear inputs, steps, outputs, exceptions, and human checkpoints.
Permissions and meaningful approvals
Decide what a system may read, what it may change, and when someone needs to authorize a concrete action.
Sources and verification
Documentation checked 2026-10-04. Examples are illustrative unless described otherwise.
Make AI Agents (New) configuration · Make
AI Agent best practices · Make
Filtering bundles · Make
Error handling · Make
Credits and provider billing · Make