Explore classifiers

Choose a Classifier to read its AI Agent Instructions, outputs and examples.

Paper Trade Policy

Checks a simulated buy/sell setup against a predefined strategy and current supplied evidence.

Roleplay Continuity

Flags replies that break character or world facts, or take control of the player.

Context Retention

Marks context to preserve exactly, summarize, or omit before an agent continues.

Business Entity Match

Screens whether two business references may refer to the same organization, not the same person.

Community Policy Fit

Flags messages against stated community rules without treating all criticism as abuse.

Subgoal Overlap

Checks whether a proposed subgoal duplicates work already assigned or completed.

Review Signals

Separates review sentiment, complaints, feature requests and stated repurchase intent.

Custom Feed Rule

Applies a saved feed preference without rewriting the rule for every post.

Obligation Role

Identifies whether a passage states a duty, permission, condition or background fact.

Next Tool Choice

Selects an explicitly supplied tool option rather than inventing a tool call.

URL Risk Signals

Flags suspicious link evidence for review without claiming a URL is safe.

Browser Result Check

Checks whether observed browser results satisfy the requested goal and constraints.

Market Narrative

Labels the stance expressed about an asset in supplied posts; it does not forecast returns.

Hot Take

Finds posts centered on a provocative opinion rather than an ordinary update.

Support Urgency

Rates reported operational urgency separately from how angry the customer sounds.

Paid Search Intent

Classifies a search query’s intent relative to the advertised product before keyword review.

Reply Completeness

Checks whether a support reply addresses the request without inventing a resolution or commitment.

Sponsor Segment

Distinguishes paid-promotion language from the main content of a transcript.

Design System Settings

Maps a visual brief to predefined design tokens rather than generating application code.

Change Impact Triage

Routes code-change descriptions toward the right review depth; it does not certify code as secure.

Next page