Products table columns
Checked columns are visible on the Products page. These settings are saved in this browser.
Adjusted brand names
Left: brand on the Amazon listing. Right: name people type when they search the brand. We use the right-hand name for Brand Analytics search frequency. Each country has its own list. Click Save after you add a row.
| Listing brand | People search |
|---|
AI prompts
These prompts are what Lighthouse sends to Gemini or Claude when you run analysis. Edits are saved on the Signal server and shared with the whole team. What you see here is what runs — there is no separate hidden version in the code.
How this works
What these prompts do. When you open a product page and click an analysis button, Lighthouse sends one of these prompts to an AI model. You get back the report you see on the page.
The blocks:
- Listing AI — runs once per ASIN. Reads the listing title, bullets, and product images. Returns USPs, target audience, design archetype.
- Competitor AI — runs once per Tracked competitor. Reads up to 104 weeks of price, rank, share, sales numbers (ASINsight rank/traffic: last 180 days). Returns a per-competitor write-up.
- Market AI — runs once for the whole page. Combines outputs of Listing AI and Competitor AI plus market-wide tables. Returns the final strategic report.
- PPC Snapshot — runs once per product when you click Run PPC analysis. Reads 13 weeks of ad spend, sales, ACoS, TACoS, CVR, CTR, CPC, CPR. Returns a 5-box report (Verdict / Waste / Wins / Targets / Alerts). Requires a PPC Goal saved on the product. Versions can pick which data tables go into the prompt, same as Market Snapshot.
- Weekly AI Advisor — weekly call prep: last week's metrics checked against Our Brief and Competitors' Brief (
{{OUR_BRIEF}},{{COMPETITORS_BRIEF}}). Same weekly data tables as Market Snapshot. No follow-up chat. - Common analysis guidelines — not a standalone prompt. This is a shared text block that gets inserted into Competitor and Market prompts at the spot marked
{{COMMON_ANALYSIS_GUIDELINES}}. Edit it once, both reports use the new version.
Placeholders. The {{LIKE_THIS}} bits inside a prompt are filled in at runtime with real data (ASIN, brand, price tables, etc.). Don't remove them unless you know what you're doing.
Model picker. Each prompt has a Model dropdown: Claude Opus 5 (default), Fable 5.1, Opus 4.8 (faster legacy), or Gemini Flash Lite.
When edits take effect. Save updates the database immediately. New AI runs pick up the new wording or model within ~60 seconds (a small cache on Lighthouse). Already-cached reports on product pages do not auto-refresh. To see the new prompt in action, open a product page and hit Re-run.
Versions. Each prompt can have several saved versions. Duplicate to try a new template without losing the old one. Pick Use this version to make it the one AI runs use. Only the version marked ACTIVE is sent to the model.