Behind the curtain

The swarm.

Six specialist agents plus a coordinator do the work that keeps FranchiseFrontline useful: watch every platform, route the bad reviews to the right human, draft brand-voice responses, follow up on leads, summarize the week. Every agent's prompt is published here so customers can read what we ask the machine to do.

Agents

review-aggregator

Pulls new reviews from Google Business Profile, Yelp, Tripadvisor, Facebook. Dedupes. Normalizes into one schema.

Read the prompt →

escalation-router

Triages each new review against the location's escalation rule. Decides who gets pinged first and when it climbs the chain.

Read the prompt →

response-drafter

Drafts a response in the brand voice. Platform-compliant. Never posts on its own.

Read the prompt →

brand-sentry

Watches brand-wide drift for HQ customers. Flags rating slides, guideline violations, platforms not connected.

Read the prompt →

lead-watcher

Classifies inbound marketing leads (operator, multi-unit, brand HQ, partner) and drafts first-touch replies.

Read the prompt →

social-poster (Phase 2)

Drafts and schedules outbound social posts across FB, IG, X, LinkedIn. Beta, opt-in.

Read the prompt →

queen-coordinator

The only agent that decides which other agent runs when. Generates no customer-facing output of its own.

Read the prompt →

Workflows

How the agents chain.

Hooks

Hard rules every agent obeys. Not optional, not negotiable.

Memory

Shared knowledge the agents read from.

Tools

External APIs the swarm reaches (no secrets here; auth lives in Cloudflare environment variables).

Note for customers

Why this is published.

You can read every prompt we feed the machine. If we ever start asking a model to do something we would not want a customer to see, this page would show it. That is the kind of accountability reputation software should have, given what it touches.