People, AI and code
AI task
A model gives a typed answer about each record: extracted fields, a label, a summary, a translation or a sentiment.
Nodes › AIOpen in Neblex
- Good for
- Structured answers from AI
- Role
- Works on the records in a flow
- Find it in
- Nodes › AI
When to use it
- Fields should be pulled from emails, PDFs or images into your structure.
- Tickets or messages should be classified, summarized or translated.
- Answers a model is unsure about should go to a person to check.
Reach for something else when
Example
Extract invoice number, date and total from each emailed PDF, and send invoices with low confidence to a person to check.
How it works
- Settings
- Model provider, its Connection and the Model (any provider an AI agent can use, including Ollama or an OpenAI-compatible server through an On-Prem Worker); for Extract with AI the Fields to extract as a JSON Schema; for Classify the Labels, one per line; for Translate the language to Translate into; optional Extra instructions; Review below confidence (0 to 1); Ask again [2]; Temperature.
- Content
- The record's
textfield, or itsdocumentfile ({filename, contentType, contentBase64}, as Read file and uploads hand files on): images and PDFs go to models that read them directly (Anthropic, Amazon Bedrock and, for PDFs, OpenAI and Azure OpenAI; images also to the OpenAI-compatible providers and Ollama), and text files are read as text. Without either, the whole record is the content. Content of any length runs: it goes to the model in parts and the answers are combined (fields merged, summaries summarized again, translations joined in order). - Output
- The record with the task's fields added:
extracted;label;summary;translationanddetected_language; orsentimentandscore(from -1 to 1)._aitells you how it went:model,tokens,schema_valid,reasks,parts,model_reported_confidence(the model's own estimate) andreview_needed. - Checking answers
- Every answer is checked against its structure. One that does not match is asked for again with what was wrong, up to Ask again times. A record whose answer never matched, or whose confidence is below Review below confidence, gets
_ai.review_needed = true: add a Branch on it that sends those records to a Wait for form step so a person checks them, and the rest straight on. After Classify, a Branch or Rules step onlabelroutes each record. - Cost
- Tokens are metered like an AI agent's and count toward the workspace's monthly AI budget; once it is spent, the step stops before its next part with the budget message. Replaying a run reuses the recorded answers without calling the model.
Add it to a flow
- Open the flow from Build › Workflows.
- Open Nodes and find AI task under AI, or search for it. Click it or drag it onto the canvas.
- Drag from the previous step's output handle to its input, then open its settings with ✎ Edit.
- Run the flow and click the step to see the records it received and produced.
More in People, AI and code
Wait for formPauses the run and gives a person a form to review, correct or approve.Nodes › LogicAI agentLets an AI agent reason over each record and use the tools you allow.Nodes › AICodeRuns a Rhai script for logic the other shapes do not cover.Nodes › CodeMCP toolCalls one tool of an external MCP server for each record.Nodes › AIRemote agentSends a task to a remote agent over the Agent2Agent protocol (A2A) and follows it until it ends.Nodes › AI