AI
OpenAI in a decision flow.
A Connection node calls OpenAI mid-decision with the credentials your own contract issued. Whatever comes back is data the rest of the flow can read, branch on, and keep in the decision's trace.
- Category
- AI
- Type
- Integration
- Authentication
- api_key
- Test environment
- Production host only
What a flow can call
4 operations, each one a step you can place on the canvas.
- POST
/v1/responsesAsk a model (Responses)
The current text endpoint — Responses, not Chat Completions.
- POST
/v1/responsesExtract structured JSON
Same endpoint constrained to a JSON schema, so the reply parses instead of needing a regex.
- POST
/v1/embeddingsEmbed text (vector)
Turns text into a vector for similarity work — matching a free-text employer or address against known values, or spotting near-duplicate applications.
- GET
/v1/modelsList available models
Model ids the key can actually reach. Cheapest way to confirm a key works, and better than hardcoding a list that ages out.
Provider documentation: https://developers.openai.com/api/docs
Where it sits in the decision
A provider call is a node, not a side effect.
The call runs where the policy needs it — after the cheap checks that might make it unnecessary, before the rules that depend on it. Calls that do not depend on each other run together rather than in sequence.
Because it is part of the run, the response is part of the record. When someone asks why an applicant was declined months later, what OpenAI returned at the time is in the trace, not re-fetched from a service whose answer has since changed.
- 01Add OpenAI as a connection, with your credentials.
- 02Place a Connection node and choose the operation.
- 03Read the response in the rules, tables and branches that follow.
- 04Test the whole path in Sandbox before it carries live traffic.
Ready when you are
Wire OpenAI into a real decision.
Build the flow in Sandbox, connect your account, and watch the decision pull what it needs before it answers.