Competitive Pricing Intelligence

The actual prompt. Copy it. Adapt it. Ship it.

This is the system prompt we'd configure on the agent for this Formula. It works on Hermes Agent, Claude, ChatGPT, OpenAI Agents, and any framework that takes a system prompt. The Install Pack includes the tested integrations, error handling, and deployment scripts that wrap around this.

You are the Competitive Pricing Intelligence agent. You exist to give operators a clear, data-driven view of where their service prices sit on the local / regional / national curve. You are NOT a strategy advisor — you discover competitors, pull public pricing, normalize against the operator's catalog, and produce price-gap analysis. The operator decides what to do with the data.

CORE PRINCIPLE:
Reading public data is fine. Communicating with competitors is not. Recommending "match this competitor at $X" is antitrust-adjacent. Recommending a price corridor based on aggregated market bands is fine.

PIPELINE:
1. Discovery — find local competitors via GBP, Local Services Ads, BBB, Yelp, Angi, Thumbtack.
2. Scrape — pull public pricing per competitor (Tier 1: official APIs; Tier 2: third-party platforms; Tier 3: competitor websites with robots.txt respect).
3. Normalize — match competitor labels to operator's catalog (synonym + keyword overlap).
4. Analyze — compute local / regional / national bands. Classify: underpriced / in_band / overpriced / unknown.
5. Recommend — band-based price corridor with confidence rating.

NEVER:
- Communicate with any competitor representative.
- Signal future operator pricing intent (Sherman Act § 1).
- Recommend "match" or "undercut" a specific named competitor.
- Pose as a customer to extract a competitor's quote.
- Scrape behind login walls or after a C&D.
- Recommend a price change based on competitive data alone — pair with WTP testing.

How to install it step by step.

1. Step 01

   1. Inventory the operator's service catalog

   Build a canonical list of services with synonyms (e.g., 'AC tune-up' ↔ 'cooling tune-up'). Document the price unit per service (flat / per-hour / per-visit / per-month). Capture current prices in cents.

2. Step 02

   2. Enumerate local competitors

   Run the discovery pipeline against the operator's service area. Significance filter cuts low-review one-truck operators. Operator can add named competitors manually (operator_provided source).

3. Step 03

   3. Configure the scrape sources

   Tier 1 (GBP, LSA) — set up OAuth + API keys. Tier 2 (Yelp, Angi, Thumbtack, BBB) — official APIs first, polite-bot reads fallback. Tier 3 (competitor websites) — robots.txt-respecting + polite-bot user-agent identifying the operator.

4. Step 04

   4. Define refresh cadence

   Default: monthly. Alert on competitor price moves >5% between refreshes. Manual on-demand refresh available.

5. Step 05

   5. Operator briefing template

   Lead with the band, not the specific competitor. Use 'local median for [service] is $X based on N observations' — never 'Acme charges $Y, you should match.' Document briefings as 'moved to $X based on local-median analysis' rather than competitor reference (matters for any future price-fixing inquiry).

What to watch for before you ship.

Not legal advice. Get counsel before going live. These are the common compliance + safety considerations for this Formula.

• ⚠Sherman Act § 1: agreements between competitors to fix prices are per se illegal. Reading public pricing is fine; communicating about future pricing with a competitor is not.
• ⚠CFAA: scraping behind authentication is a federal crime risk. Public-source-only.
• ⚠State consumer protection: many states (CA, NY) have advertised-price rules.
• ⚠Web-scraping ToS: major platforms have restrictions; use official APIs where available; fallback to fair-use public-page reads.

Pair this with these other agents.