AI Complete

AI Complete

Type: ai-complete  ·  Package: AI Activities v1.0.0  ·  Output: string

Sends a prompt to a large language model and returns its answer as text. Use it to summarise, draft, translate, classify, or answer questions about some content.

If what you need is specific fields (a serial number, a date, an amount), use AI Extract instead: it returns an object rather than text you would then have to parse.

How it works

Sends system (the model’s role and rules) and prompt (the task at hand), plus the images if there are any, and returns the answer text.

Required parameters

Parameter	Editor	Description
credential	credential	Zoan Cloud credential holding the provider’s API key.
prompt	expression	The question or task for the model.

Optional parameters

Parameter	Editor	Description
provider	enum	AI provider. Defaults to Anthropic (Claude).
model	expression	Model id. Leave empty to use the provider’s default model.
system	expression	System instructions: the model’s role, rules and output style.
images	list	Paths of images to send with the prompt (.jpg, .png, .gif, .webp).
effort	enum	How much work the model puts in: low, medium, high, xhigh, max.
thinking	boolean	Let the model reason before answering.
maxTokens	expression	Maximum length of the answer, in tokens. Default 16000.
timeout	expression	Seconds to wait. Default 600.

Output

Returns a string with the model’s answer.

System and prompt

The split matters: system describes who the model is and what rules it follows for the whole request; prompt is the task at hand. Putting the rules in the prompt works, but they get diluted when the content is long.

system → "You are a support email classifier. Answer with exactly one of these
          words: incident, question, spam."
prompt → = emailBody

Example

Classify an incoming email and branch on it:

AI Complete   credential = = credential("anthropic-key")
              system     = "You are a support email classifier…"
              prompt     = = email["body"]
              maxTokens  = 10
              → output: kind
If            condition = = kind == "incident"
  ...

Summarise a long contract:

PDF Get Text   path = = contractPath   → output: text
AI Complete    credential = = credential("anthropic-key")
               system     = "Summarise as bullets, five at most, in English."
               prompt     = = text
               → output: summary

Match maxTokens to what you ask for

The default (16000) leaves plenty of room for a long answer. If you expect a single word, lower it: the call gets cheaper and the model stops elaborating.

Common errors

Message	What happened
The model hit the 'maxTokens' limit before finishing	The answer does not fit. Raise maxTokens or ask for less text.
The credential does not contain an Anthropic API key	The credential exists but is empty or holds something else.
Claude declined this request for safety reasons	The model refused the content. This is an answer from the model, not a configuration failure.

Related activities

• AI Extract — when you want fields instead of text.
• PDF Get Text — get a document’s text.