The leaks I can see from the public listing
Title, bullets, A+, reviews, brand defense, and obvious ad-real-estate problems. Storefront URL only — no Seller Central login until we agree to work.
Services · Defender
Reporting
If the report needs a decoder ring, it is not a report.
Best fit: you get dashboards and still cannot answer “what did we do?”
4 min
A readout a founder can finish
Log
Every material change has a sentence
Next
This week and next week in the same note
You see spend, ACOS, TACOS, wasted search terms, and ranking movement on hero ASINs. Every material bid change is in the log.
The report is a letter, not a product. If a number moved, the log says what we did. If we did nothing, the log says that too. Sellerboard is the P&L lens; Claude, Codex, Kimi, and Cursor draft the analysis from exports — they do not bid.
A dashboard login without commentary is how the last vendor hid. Optional seats (Teikametrics, Cobalt, Xnurta) stay behind the same four-minute note.
Who this is for
Founders and operators who want spend, ACOS, TACOS, waste, harvest, and hero rank — plus a log of every material change.
Who it is not for
Teams that want a white-label Looker studio and no human commentary. I will not build a dashboard that replaces the work.
How the work actually runs
01
Pick numbers
Your heroes, your floors, your events. Not a generic 40-metric dump.
02
Log as we work
Changes get written when they happen, not reconstructed on Sunday night.
03
Send the note
Same day each week. Same shape. You always know where to look.
04
Decide
The note ends with what happens next. Reporting without a next step is a museum.
What is in the workstream
- Weekly founder readout
- Written change log
- Hero-ASIN rank tracking
- Waste and harvest tables
- ACOS / TACOS / spend in one view
- Next-week plan in the same note
- Event annotations (Prime, stockouts, price changes)
- Optional BI later — not the product
Week one
Agree the numbers that matter for your catalog. First log at the end of week one so you know the format before we scale the work.
Every week after
Spend, ACOS, TACOS, wasted terms, hero rank, and every material bid change in the log. Next week’s plan in the same note.
On this workstream’s desk
Named seats, not a logo wall. Each page says the job, the rail, and what still has to happen in Seller Central or the Ads Console.
Sellerboard
SellerBoardTrue P&L after COGS, Amazon fees, ads, and reimbursements — the number that sets the bid ceiling, not the Ads Console ACOS tile.
Claude
Anthropic ClaudeLong-context read of search-term exports, change logs, and playbooks — drafts the founder note. Does not bid, does not log into Seller Central.
Codex
OpenAI CodexScripts that clean Ads Console exports, join Sellerboard P&L to search terms, and build repeatable harvest tables — not a secret bidding API.
Kimi
Kimi K2, MoonshotA second long-context pass on large Amazon exports and competing drafts — used when one model should not be the only reader of a 40,000-row file.
Cursor
Cursor IDE, Cursor AgentThe environment where harvest scripts, playbooks, and the weekly reporting pipeline actually live — so the analysis is repeatable next Monday.
FAQ
Will I get a live dashboard login?
You get a readout a human can read. Sellerboard, Helium 10, or Flywheel can be in the stack if the seat is already yours — they are evidence, not the letter.
Do you use AI for reporting?
Yes. Claude and Kimi draft from exports. Codex writes join scripts. Cursor keeps the pipeline. None of them log into Seller Central or set bids. Indexed on the operator stack.
Can this be white-labeled for my team?
The log is yours to forward. I do not staff a reporting farm for an agency overlay.
Daily numbers?
Daily is noise for most catalogs. Weekly is the desk rhythm. We can flag a fire on a weekday without a daily PDF.
Does reporting include listing work?
If we are doing listing or defense that week, it is in the log. One note. One operator.
This workstream on the free review
You do not need to hire it to find out if it belongs on the account. Send the public store link. I tell you whether this lever is leaking, whether I am the person to run it, and what week one would be.
Whether this desk is a fit
If I cannot show the leaks, I decline. You are not added to a roster. A “no” is a complete answer, not a follow-up sequence.
What week one would be
Harvest, defense, listing pass, or “not yet.” Named in writing — not a 40-slide deck and a 12-month PDF.
Capacity is limited because I work the accounts myself. The review is how we decide if this workstream belongs on yours.
Request a free reviewRelated workstreams
Amazon PPC Management
Controle diário de lances, orçamento e search terms em Sponsored Products, Brands e Display.
Account Audit
A hand-done read of wasted spend, structure, and the first 30 days of work.
Full Account Management
Ads, anúncio, defesa e medição DSP num plano semanal.
Budget Pacing
Spend the budget when the ASIN converts, not when Amazon wants the click.