Cleaning Agent
Strips noise from notes, calls, PDFs and web captures. Normalises structure, removes duplicates and flags unverifiable claims.
Each agent owns a narrow mandate, a model and explicit tools. Runs are logged with tokens, cost and score so every draft is auditable.
Strips noise from notes, calls, PDFs and web captures. Normalises structure, removes duplicates and flags unverifiable claims.
Maps the cleaned input to core topics, audience keywords and live trend signals. Produces the semantic search brief.
Retrieves the most relevant pieces of your evidence, past posts, call notes and source library using hybrid vector + lexical search.
Turns the research brief into a strategy document: post type, hook style, narrative arc, CTA, tone and proof points.
Writes in your voice, under 1,500 characters, mobile-first. Enforces your cadence, banned words and opening-line rules.
Scores hook power, voice authenticity, value density and engagement potential. Sends weak drafts back with specific edits.
Rewrites only what the reviewer flagged, preserving the author’s argument and voice. Iterates until the threshold is met.
Produces three hook variants, hashtag sets and a copy-ready final. Keeps the substance intact and removes engagement bait.
Scores every engaged profile against your ICP across role, company, buying signal, timing and engagement quality.
Audits headline, about, featured and experience sections. Generates tested headline formulas and a conversion checklist.
Detects 24 common AI writing patterns, banned words and uniform rhythm. Proposes human edits without flattening personality.
Synthesises weekly performance into hook patterns, format signals and next best actions. Feeds the strategy layer.