Amazon brand lead engine
A pipeline that turns marketplace brand and product exports into qualified leads with a verified domain, the right decision-maker and a deliverable email, with every count reconciled back to the source.
- 1The problem
The sales team had hundreds of raw marketplace exports and no reliable way to tell which brands fit, who to contact or whether a number on a dashboard could be trusted. Manual research did not scale and paid lookups were being repeated.
- 2Our contribution
Designed and built end to end by Kumar Sahil.
- 3What we built
An 8-stage pipeline: load and de-duplicate (with a tie-out gate that must reconcile before anything moves on) → map brands to products → score against the ICP revenue band → find and verify the company domain → size the company → find decision-makers through a strict title gate → find emails, with every attempt logged so no lookup is ever paid for twice → clean. A 13-command CLI runs each stage, and a CRM dashboard shows a tie-out panel next to every number.
- 4The result
In production. Results shared on request.
Other systems we’ve built
Reply Classifier Cascade
A cost-ordered classifier for English and Dutch cold-email replies that decides which replies become CRM deals, built so a false “hot deal” needs several layers to agree.Read the case studyLLM Gateway
A provider-neutral LLM gateway: code asks for a job, the gateway routes it through a chain of models with safe failover, a deadline per call, and the cost of every call written to a ledger.Read the case studyLLM Eval Gauntlet
Invariant-checked evaluation suites for tool-calling agents that run in CI and fail the build when an agent invents a number, leaks its prompt or obeys an injection.Read the case studyFind the workflow worth automating first.
Tell us about one process that costs your team hours every week. We will tell you honestly whether AI or automation is the right fix, and what a first build would take.