Skip to main content
How it works

Seven states. One recursive loop. Compounding over time.

Every post a brand publishes moves through the same pipeline — and the engagement it earns is fed back into a per-brand brain that shapes the next idea. The brain feeds the loop and the loop feeds the brain: each cycle, it gains density and gets sharper. Here's each state.

  1. 01

    Capture

    Ideas arrive from anywhere — a Telegram drop, the web form, or the engine itself proposing angles off your competitors' best-performing posts and live opportunity signal: rising keywords, trends, and breaking catalysts. Each lands in the inbox, scoped to one client brand.

  2. 02

    Iterate

    Generate 3–5 alternative angles in the brand's voice (pinned to Claude Sonnet 4.5). The voice profile, ground-truth facts, and available assets are injected — and the exact prompt is recorded with the output.

  3. 03

    Score

    Rate iterations 1–5. A percentile-gated ranker learns which hooks, formats, and angles actually earn engagement for this brand, and biases future generation toward them.

  4. 04

    Promote

    Pick the winner. Provenance — idea, iteration, model, and prompt — is copied onto the post, so six months later you can always answer “why did we say this?” without a fragile join.

  5. 05

    Review

    The default gate. Out of the box a human — or the client, via batch approval — signs off before anything publishes: the safeguard against shipping a typo across four brands at 7am. Once a brand has earned your trust, autonomous posting can be turned on per brand and per channel; the gate is a policy you control, not a wall.

  6. 06

    Publish

    Ship across the v1 channels — LinkedIn, Meta, and YouTube. Each platform is its own render with its own metrics keyed to it, so performance never gets blurred into one fuzzy average. TikTok and more channels arrive in v2.

  7. 07

    Learn

    Engagement and cross-channel metrics flow back as signals that grow the per-brand brain — re-weighting the ranker and seeding the next capture. The loop closes; the brain it feeds gets sharper every turn. That's the recursion: output becomes sharper input.

See it on one of your clients.

A 20-minute walkthrough, capture to published, on a brand you actually run.

Book a walkthrough