Keyword Harvesting Agent with Helium 10 MCP

Check my advertising campaigns. Using a 12-month look-back period, tell me if there are any search terms or ASINs in auto or broad campaigns that have more than 20 clicks and no sales. Give it to me in a table that shows which campaigns they're in, how many clicks, and how much spend. Using the same look-back period, also show me any targets in any campaign type that have more than 20 clicks and no sales.

I'm attaching two files for the same brand: the Sponsored Products search term report for the last 60 days and a Helium 10 Cerebro export of the brand's organic ranks.
Match them by keyword and give me three lists:
1. Keywords where we already rank organically in the top 10 but still spend heavily on ads (candidates to cut spend).
2. Keywords ranked 11-40 with good conversion in the ads data (candidates to push toward page 1).
3. Keywords with spend and no organic rank at all.
Show spend, sales, ACoS and organic rank for each row.

Before you recommend any change to my Amazon campaigns, tell me: what in this data supports it, what could go wrong, and how I'd know within 14 days whether it worked.
Recommend at most 2 changes at a time, never touch my top-selling SKUs' existing campaigns, and remind me of the baseline numbers so I can roll back.

Review my Sponsored Products targets for the last 30 days. For each target with ACOS above [X]% or more than [N] clicks and no sales, recommend lower bid, pause or keep, with the reason.
Show the list first; only make the changes I approve.

Here are my keyword performance export and targets: target ACOS [X]%, harvest after [N] orders, negate after [M] clicks with 0 orders.
List search terms to promote to exact match and terms to add as negatives, with the campaign and ad group for each, as a Sponsored Products bulk file I can review before upload.

You are my Amazon PPC assistant with access to my Amazon Ads account. Draft, don't change anything.
1. Pull the last 30 days of Sponsored Products search terms.
2. Propose bid changes in one table (campaign, target, current bid, proposed bid, reason).
3. Propose negative keywords in a SEPARATE table (search term, campaign, clicks, spend, orders, why it should be negated, and any sign it might still convert).
4. Stop and wait. Apply only the rows I approve, and list exactly what you changed.