OpenAI Decision
Evaluate a predicate, choice, or score with OpenAI Decisions (beta).
Plan availability #
| Feature | Free | Starter | Pro | Enterprise |
|---|---|---|---|---|
| Active workflows | 3 | 10 | 45 | Unlimited |
Allowances follow the published Chatigram pricing page. Your organization’s Billing & Plans screen confirms its subscription and current usage. Plans can change. Plan information reviewed 2026-11-10.
When to use this node #
Evaluate a predicate, choice, or score with OpenAI Decisions (beta).
Add OpenAI Decision to a workflow branch using the node picker. Configure its fields in the inspector, then connect the next step.
Before you begin #
Connect OpenAI in App Connections first. Select the intended account in this node; an account connected to a different service is not interchangeable. Available actions depend on the permissions granted to that connection.
Configure the fields #
| Field | What to enter |
|---|---|
| OpenAI Account | Select the OpenAI connection to use for this node. |
| Model | Supported Decisions model. Choices: gpt-6-luna.Example/default shown in the editor: gpt-6-luna. |
| Input | Content to evaluate. |
| Decision Type | Predicate returns a probability; score returns a weighted level index. Choices: predicate, choice, score.Example/default shown in the editor: predicate. |
| Question Name | Name of this decision question. |
| Instructions | Optional instructions for the model. |
| Choices JSON | For choice: JSON array of at least two {"value":"billing","description":"Payments"} objects. |
| Score Levels JSON | For score: ordered JSON array of at least two {"label":"Low","description":"Minor impact"} objects; indices start at zero. |
Use the result #
Choose the output from the variable picker in a later step. Output names below identify the values supplied by this node; the picker inserts the correct reference for your node instance.
| Output | Meaning / label |
|---|---|
result |
result |
probability |
probability |
confidence |
confidence |
details |
details |
model |
model |
error |
error |
Connect the next step #
This definition exposes these paths:
- Success — branch 1.
- Error — branch 2.
Connect each relevant outcome, especially any error or timeout path. Outputs can differ by outcome; check that a result exists before using it.
Test it in a workflow #
- Configure this node with a small, recognizable test input or a test resource.
- Check the variables from preceding steps and the connection selected in the inspector.
- Save the workflow. For event-driven flows, generate the actual event; use Run only for a Manual workflow.
- Open Workflow Activity and check the outcome before enabling wider use.
AI processing can use your connected provider account and incur charges. Choose an available model in the current selector and test with a small input. Handle provider errors and unavailable results explicitly.
If something goes wrong #
- Reconnect the account if authorization has expired, then verify its permissions on the specific resource.
- Check empty variables, selected resource IDs, and any fields that appeared after resource selection.
- Check the failed step in Workflow Activity before retrying. If the action may already have completed, inspect the destination first to avoid duplicates.
- Follow the troubleshooting guide for a symptom-by-symptom checklist.
Related guides #
- Work with variables
- Understand branches and error handling
- Browse all nodes
- OpenAI Analyze Image
- OpenAI Create Embedding
- OpenAI Edit Image
- OpenAI File Search
- OpenAI Generate Image
Catalog coverage #
This is the currently documented selection. Chatigram continues to add nodes, triggers, App Connections, and integrations. Use each page’s review date and the current application selectors to check what is available now; this catalog is not a fixed limit on future features.