surface↓classification↓intent
Classificationdimension · returns varchar

INTENT

Classify the communicative intent of text (zero-shot NLI)

Per-row classifier — stable across GROUP BY.

classificationnlispecialist-zootext

Arguments

nametypedescription
textVARCHAR—
intentsVARCHAROptional comma-separated intent categories

About

Communicative intent classifier for social media posts. Identifies what the author is trying to accomplish with their post. Backend: specialist zoo zero-shot NLI via /classify_batch. All posts in the batch are scored against the intent label set in a single forward pass. Default intent categories (12): Question, Statement, Opinion, Complaint, Praise, Announcement, Humor, Promotion, Request, Engagement Bait, Rant, Commentary Pass a comma-separated `intents` string to use a custom label set instead of the default. For LLM-style intent classification with nuanced judgment or subtle cases, use INTENT_LLM — see intent_dimension_llm.cascade.yaml.

Examples

Intent detected

SELECT
  intent ('How do I fix this error?')

Nearby rabbit holes

same domain
dimension

AUDIENCE

Identify target audience via zero-shot NLI

classificationnlispecialist-zootext+1
dimension

AUDIENCE_LLM

LLM-backed audience identification (escape hatch for AUDIENCE)

classificationllmllm-escape-hatchtext
dimension

AUTHENTICITY

Assess authenticity of content via zero-shot NLI

classificationnlispecialist-zootext
dimension

AUTHENTICITY_LLM

LLM-backed authenticity assessment (escape hatch for AUTHENTICITY)

classificationllmllm-escape-hatchtext
dimension

BUCKET

Classify text into user-specified buckets via zero-shot NLI

classificationnlispecialist-zootext
dimension

BUCKET_LLM

LLM-backed bucketing (escape hatch for BUCKET)

classificationllmllm-escape-hatchtext
Climb back to The Looking Glass