Discover — the product line

Every niche carries a status. Pick a bucket (chip), look, then advance it a stage and watch it run. Rejects are archived, never deleted — add a rule and re-run to thin the pool. No P&L here; that comes post-quote.

New raw ideas are born from: (empty = the AI proposes freely across both lanes) · or the ① Discover new ideas box below (your seed words → DataForSEO). Every idea keeps its origin.
Loading buckets…

Pick a bucket above.

Corpus identity review

One corpus = one buyer opportunity, in any language. Translations and ordinary material/size/configuration variants belong to that corpus and are analyzed downstream. Only “Same corpus” merges. Both “Separate” choices always preserve a different product opportunity.

Loading…
① Discover new ideas — ask DataForSEO (you choose the criteria)

Type seed keyword(s), pick the market, and DataForSEO returns related search ideas → they land in "Raw ideas", each stamped with the exact seed + market that produced it. The full API call is saved (open any raw idea → "Stored calls").

Classify prompt — the exact instruction the AI reads (edit it & re-run)

This is the real text the "Classify" step sends to the AI for every batch of keywords (the keyword list is added at the end). Change it, then re-run on the Raw ideas — your version is saved and used from then on.

Hard rules — the pool filter (deterministic, yours to edit)

A rule fires as soon as its input exists (price/size stay inert until enrichment). Add one, then Re-run.

Live
running…