Canonical page: https://www.kuudo.com/features/agent-atlas/

Amazon Agent Atlas

# The Amazon knowledge your agent didn't have to earn.

Ungrounded, an agent guesses — it quotes last year's FBA fees, writes AMC SQL that won't compile, invents a dispute window. Atlas is the knowledge it checks first: 56,381 content indexes across Ads, Seller, and Vendor, with decision guidance applied during retrieval. Answers come back cited, in milliseconds.

Choose [Managed MCP](/managed-mcp/), which Kuudo hosts and operates, or run it in your own [Private Cloud](/features/cloud-platforms/).

[Explore the private beta](/contact/) [Read the docs](/docs/)

corpus.index — 56,381 content indexes

amazon\_ads

30,249

amazon\_sellers

18,531

amazon\_vendors

7,601

embed: BAAI/bge-small-en-v1.5

filter: domain · topic · doc\_type

semantic retrieval · structured metadata · source-aware results

What Atlas knows

## 56,381 content indexes covering every Amazon system your team works with.

30,249

content indexes

amazon\_ads

### Amazon Ads & AMC

Sponsored Ads, DSP, AMC audiences, attribution, SQL templates, conversion paths, audience segmentation.

18,531

content indexes

amazon\_sellers

### Seller Central

FBA fulfillment, Brand Registry, listings, Buy Box, fees, inventory, shipping, returns, tax.

7,601

content indexes

amazon\_vendors

### Vendor Central

Compliance, chargebacks, ARA/ABA reports, A+ content, Net PPM, EDI/API integrations, catalog operations.

Why retrieval changes the agent

## It looks up the answer before it answers.

?"lapsed customer re-engagement"

conversions\_all\_for\_audiences.sql0.91

audience\_iq\_lapsed.md0.87

Semantic retrieval

### Retrieves by meaning, not keyword

BAAI/bge-small-en-v1.5 embeddings find the right playbook even when your question doesn't match the docs verbatim.

domainamazon\_ads

topicaudience\_iq

doc\_typesql\_template

datasetconversions\_for\_audiences

Structured metadata

### Filters before it answers

Every content index entry carries domain, topic, doc type, source path, dataset references, and code language tags.

"… DSP activation ~48h"

↳amc/audiences/activation.md#timing

"… min 500 users"

↳amc/audiences/limits.md#size

Source-aware results

### Citations on every claim

Section paths and code language are preserved during indexing, so every recommendation links back to its source.

IF ORD\_g ≥ 10 AND ACOS\_g ≤ 0.9 × TGT

actionscale\_winner

bid Δ+5–10% · clamp ±20%

reeval5d

Bounded actions

### Rulebook, not improv

Scale ±5–10%, daily clamp ±20%, re-evaluate in 5 days. The agent consults the rulebook instead of guessing.

SELECT user\_id

FROM conversions\_for\_audiences

WHERE event\_subtype = 'shoppingCart'

✓compiled · 0 errors

AMC-fluent SQL

### Compiles on first try

Knows conversions\_for\_audiences vs conversions\_all, the right event\_subtype codes, and the 14-day attribution wait.

LTSF endedJul 1 2024

dispute window30d

SnS in sandboxno

attribution wait14d

Operational guardrails

### Knows what's current

Long-term storage fees ended Jul 2024. Chargeback dispute window is 30 days. Sandbox doesn't populate SnS.

AMC SQL playbooks

## Retrieved AMC SQL. Compiles on the first run.

AMC gives you cross-channel attribution, audience overlap, and customer journey analysis. The SQL is the wall most teams stall against. Atlas indexes the playbooks Amazon publishes — and the operational details Amazon doesn't.

AMC · Audience IQ

"Build me a DSP audience of [people who added one of our hero ASINs to cart but didn't buy](/guides/amc-cart-abandoner-audience/) in the last 30 days."

Retrieves the cart-abandonment Audience IQ, knows it must use conversions\_for\_audiences (the only variant that allows SELECT user\_id), and produces a query that compiles on the first try.

Also surfaces: AMC audiences require min 500 / max 500k users, DSP activation takes ~48h, and shoppingCart can be swapped for detailPageView to reach further upstream.

amc.sql

```sql
WITH asins (asin) AS (
  VALUES ('B0XXXXXXX1'), ('B0XXXXXXX2')
),
purchase AS (
  SELECT user_id, MAX(event_dt_utc) AS purchase_dt_max
  FROM conversions_for_audiences
  WHERE event_subtype = 'order'
    AND tracked_item IN (SELECT asin FROM asins)
  GROUP BY 1
),
atc AS (
  SELECT user_id, MAX(event_dt_utc) AS atc_dt_max
  FROM conversions_for_audiences
  WHERE event_subtype = 'shoppingCart'
    AND tracked_item IN (SELECT asin FROM asins)
  GROUP BY 1
)
SELECT atc.user_id
FROM atc
LEFT JOIN purchase ON atc.user_id = purchase.user_id
WHERE atc_dt_max > purchase_dt_max
   OR purchase_dt_max IS NULL;
```

AMC · Subscribe & Save

"How much more do my Subscribe & Save customers spend compared to one-off buyers?"

Knows that Feb 2024 extended FSI to include repeatSnSOrder alongside snsSubscription and firstSnSOrder, and returns a working comparison query.

Flags the constraints that aren't in the SQL: query ≥3 months for SnS cadence, narrow with an ASIN filter for performance, and skip Sandbox — sns\_subscription\_id isn't populated there.

amc.sql

```sql
SELECT
  CASE
    WHEN event_subtype IN (
      'snsSubscription','firstSnSOrder','repeatSnSOrder'
    ) THEN 'subscriber'
    ELSE 'non-subscriber'
  END AS user_type,
  COUNT(DISTINCT user_id) AS users_that_purchased,
  SUM(total_product_sales) AS total_sales,
  SUM(total_product_sales) /
    COUNT(DISTINCT user_id) AS average_spend
FROM conversions_all
GROUP BY 1;
```

AMC · Path-to-Conversion

"What's the actual journey our customers take across DSP, SP, SB, and SD before they convert?"

Pulls Customer Journey Analytics, identifies the three required tables (dsp\_impressions, sponsored\_ads\_traffic, amazon\_attributed\_events\_by\_traffic\_time), and outputs a result shaped for a Sankey diagram.

Knows to wait 14 days past the query end date for attribution to close, and points you at the newer Sponsored Ads & DSP Overlap IQ that handles 2/3/4-way overlap instead of the deprecated version.

amc.sql

```sql
-- Path-to-Conversion grouped by campaign category
-- Joins DSP impressions, sponsored ads traffic,
-- and attributed events on user_id within window.
SELECT
  path_signature,
  campaign_category_path,
  COUNT(DISTINCT user_id) AS converters,
  SUM(total_product_sales) AS sales
FROM customer_journey_paths
GROUP BY 1, 2
ORDER BY converters DESC;
```

Beyond AMC

## FBA fees. Chargebacks. Bid math. The unglamorous Amazon work, handled.

### Vendor chargeback disputes

Pulls the exact 30-day dispute window, the second-dispute path, and the Smart Aggregation Processing 7-day preview cycle. Drafts the dispute in the evidence pattern Amazon's reviewers actually look for.

### FBA inventory & storage

Knows long-term storage fees ended July 1, 2024. Quotes the active fees — monthly storage, aged-inventory surcharge, capacity limits in cubic feet — instead of the 2022 schedule.

### Brand Registry conflicts

"Trademark already enrolled" → retrieves the specific resolution path: contact the existing Administrator via the application flow, or file via the FAQ's "use this form" mechanism if inactive.

### Bid decisions, not bid vibes

Scale-winner fires only when ORD\_g ≥ 10 AND ACOS\_g ≤ 0.9 × TARGET\_ACOS. Increase 5–10%, daily clamp ±20%, re-evaluate in 5 days. Conflict order: invalid → thin-data → safety → pull-back → scale.

Wired into a workflow

## Retrieved and adapted, not generated.

Atlas is the retrieval layer beneath agents that already do work — pulling SP-API reports, querying AMC, drafting support replies, auditing campaigns, building audiences, planning inventory.

01

### Your team asks in plain language

"Build me a high-value lookalike for Prime Day."

02

### Agent searches the corpus semantically

Retrieves the AMC Lookalike Audiences for Promotional Events playbook, the high-value seed query template, and the 500–500k size constraints.

03

### Agent grounds the response

Compilable seed query, named thresholds, the testing approach the playbook actually recommends, and the 48-hour DSP activation lag.

04

### Your team runs it

Works the first time — because the answer wasn't generated, it was retrieved and adapted.

Repository and registry [github.com/KuudoAI/amazon-agent-atlas-mcp](https://github.com/KuudoAI/amazon-agent-atlas-mcp) [MCP Registry: io.github.KuudoAI/amazon-agent-atlas-mcp](https://registry.modelcontextprotocol.io/v0.1/servers?search=io.github.KuudoAI%2Famazon-agent-atlas-mcp&version=latest)

Choose your deployment

## The same Kuudo. Your choice of deployment.

Your AI, your knowledge, your rules. Choose Managed MCP for velocity or Private Cloud for infrastructure control. Start with either and move between them.

### Managed MCP

Kuudo operates the MCP services. Connect your accounts and use the AI client your team already works in.

[Explore Managed MCP →](/managed-mcp/) [Set up Amazon Agent Atlas](/docs/managed-mcp/atlas/)

### Private Cloud

Run Kuudo in your own cloud account, with control of the infrastructure. Agent Flow adds pipelines and a lake in your storage.

[Explore Private Cloud →](/features/cloud-platforms/) [Choose or change your deployment](/docs/deployment-choice/)

Frequently asked questions

## Common questions.

What is Amazon Agent Atlas? +

A retrieval layer your agent checks before it answers. It indexes Amazon operating knowledge across Ads, Seller Central, and Vendor Central, applies decision guidance during retrieval, and returns cited answers in milliseconds.

Why does an agent need this if the model already knows Amazon? +

Because an ungrounded model guesses. It quotes last year's FBA fees, writes AMC SQL that will not compile, and invents dispute windows. Atlas makes the agent look the answer up instead of recalling it.

What does Atlas actually cover? +

Amazon Ads and AMC, Seller Central, and Vendor Central. Decision rules, sufficiency gates, conflict resolution, action enums, and category style guidance are applied within that knowledge rather than presented as a separate catalog.

Does Atlas hold my account data? +

No. Atlas is operating knowledge about how Amazon works, not a copy of your business. Live figures from your own accounts come through the MCP servers and Amazon Agent Flow.

Can I see where an answer came from? +

Yes. Retrieval is source-aware and answers come back cited, so you can trace a claim to the document it was drawn from rather than trusting the model's memory.

The bottom line

## Your hard-won Amazon knowledge, finally something AI can use.

Atlas grounds every answer in your data and your playbook — every indexed result traceable to its source, every recommendation cited. The edge you built stays yours, not the model's.

[Explore the private beta](/contact/) [See Amazon Agent Crawl](/features/agent-crawl/)