LLM Personalize
llm-personalize · action
Rewrites a message body in a chosen voice before it is sent. Put it before a messaging node and feed its output into the body.
| Field | Meaning |
|---|---|
credentialId | An LLM credential |
model | The model to call, such as gpt-4o |
body | The message to rewrite |
tone | friendly, formal, concise, enthusiastic or professional |
extraInstruction | Extra guidance for this rewrite |
useContactContext | Include the customer’s name, company and job title. On by default |
maxTokens | Cap on the output |
text, plus inputTokens and outputTokens.
AI Classify Intent
ai-classify-intent · action
Reads a reply and sorts it into one of four intents, then routes the customer down the matching arrow. Put it after a send node that got an answer.
| Field | Meaning |
|---|---|
credentialId, model | Which model reads the reply |
text | The reply to classify, usually {{node.<id>.output.replyText}} |
extraContext | Extra context such as the campaign brief |
maxTokens | Cap on the output. Defaults to 200 |
| Intent | What it means |
|---|---|
positive | Real buying interest — asks for a demo, pricing, a trial, or a timeline |
negative | Declines or opts out |
question | A concrete question that needs answering before they decide |
neutral | Everything else, including praise with no intent to buy |
neutral when a reply does not clearly belong anywhere. A warm “Nice product, I’ll keep it in mind” is neutral, not positive — which is what you want, because that reply should not trigger a handoff.
Give each outgoing arrow the key of the intent it handles. Output also carries confidence and a rationale.
AI Score Delta
ai-score-delta · action
Reads a conversation snippet and returns a score change between −50 and +50.
| Field | Meaning |
|---|---|
credentialId, model | Which model reads the text |
text | The snippet to judge |
delta and a rationale, plus the token counts. Chain it into an Adjust Score node to write the change to a fit criterion, or read delta directly in a Path rule.