Reported operating use · Retail and ecommerce
AI merchandise recommendations: Fanatics example
OpenAI reports that Fanatics uses enriched product data, team information and inventory to assemble coordinated, in-stock merchandise looks that refresh daily within merchandising rules. Engineers built the tools with Codex, and Fanatics approved the initial product before rollout. The account is provider-published, not independent.
Assemble coordinated merchandise recommendations
Fanatics
Reported production use across Fanatics and official sports league stores.
A published third-party example, not a Nuvepro customer case or evidence of a partnership.
The workflow at a glance
Assemble coordinated in-stock merchandise looks
Illustrative summary of the published account
Reported work components. Their arrangement does not imply a fixed execution order or simultaneous work.
- Inputs
Products, teams and inventory
Enriched product data, team information and inventory support recommendations.
- Selection
Merchandising-constrained looks
Fanatics assembles coordinated selections that refresh daily.
- Initial rollout
Tools and product review
Engineers used Codex; Fanatics reviewed results, gave feedback and approved the initial product.
What the source reports
OpenAI reports that Fanatics uses enriched product data, team information and inventory to assemble coordinated, in-stock looks. Merchandising rules constrain the selections, which refresh daily. Engineers built recommendation tools with Codex; Fanatics reviewed results, supplied feedback and approved the initial product before production rollout. The account reports 10% higher engagement after testing about 30,000 MLB products.
Reported technology: Fanatics with OpenAI; OpenAI models and Codex. Scope and outcomes are source-reported.
What the enterprise environment would need
The following is a proposed project design for an enterprise doing similar work. Published details are marked; the remaining systems, data and scenarios would be agreed for your project.
Proposed practice environment
Check a game-day merchandise selection
Illustrative project design to scope with your enterprise.
- 1 · Set up the environment
Fictional catalog and stock snapshots
Version team identifiers, compatibility rules, inventory and approval state.
- 2 · Preparation and agent contributions
Agent drafts coordinated looks
Record every recommended item, input and applicable merchandising rule.
- 3 · Independent checks
Independent merchandiser checks constraints
Verify each team match, rule and current stock; reject visually plausible violations.
- 4 · People decide acceptance
Merchandising owner accepts the selection
Review exceptions and availability before any separate publishing integration.
A reviewable evidence package
An approved fictional look with item-level stock and rule evidence.
If a check fails → withhold acceptance.
Stock changes after drafting. Detect stale inventory and withhold the unavailable item before publication.
Failure or owner rejection returns to review
- Hold
- → 2 · Revise work
- → 3 · Rerun independent checks
- → 4 · Owner review
Operating boundary. Practice catalog only; no live merchandising changes or revenue-uplift claim.
- Systems and evidence
- Proposed: use a fictional merchandise catalogue with versioned inventory, team identifiers and explicit compatibility rules.
- People and agents
- Proposed: an agent drafts coordinated looks; a merchandiser checks compatibility and exceptions, while an engineer owns the publishing integration.
- State and permissions
- Proposed: retain recommendation inputs, rule versions, stock timestamps and approvals. Keep the practice system separate from live merchandising.
A proposed simulation
An illustrative practice design derived from this work, not an executed assessment.
Proposed: assemble an approved fictional game-day look while respecting stock, team and merchandising constraints.
Review gate: An independent reviewer can reproduce each recommendation from its recorded inputs, verify every constraint and identify items requiring human judgment.
Challenge the result: Inventory changes after a look is drafted. The agent must detect the stale stock record and withhold the unavailable item before publication.
What needs checking
- Proposed: independently verify team compatibility and stock availability for every recommended item.
- Proposed: reject recommendations that violate a merchandising rule, even if visually plausible.
- Proposed: compare engagement and availability failures against a predefined baseline without treating clicks as purchases.
Review environment fidelity, human capability and agent performance separately. The enterprise’s accountable owners decide acceptance of the shared workflow and any operating use.
How an enterprise could build similar work
A proposed build order for an enterprise doing similar work, written by Nuvepro from the published account and our interpretation of the environment and checks above. It is not how Fanatics built or operates this work.
- Frame a proposed practice projectThis is a proposed design for a similar project, not a replica of Fanatics systems. The mission: assemble an approved fictional game-day look while respecting stock, team and merchandising constraints.
- Create a fictional catalogueUse a fictional merchandise catalogue with versioned inventory, team identifiers and explicit compatibility rules. Keep this practice system separate from live merchandising, so that nothing a test agent does can reach real stores.
- Define roles and recordsAn agent drafts coordinated looks, a merchandiser checks compatibility and exceptions, and an engineer owns the publishing integration. Retain recommendation inputs, rule versions, stock timestamps and approvals for every look.
- Verify constraints independentlyIndependently verify team compatibility and stock availability for every recommended item. Reject recommendations that violate a merchandising rule, even if visually plausible. Compare engagement and availability failures against a predefined baseline, without treating clicks as purchases.
- Run the stale-stock failure testChange inventory after a look is drafted. The agent must detect the stale stock record and withhold the unavailable item before publication, and the reviewer should be able to see which record triggered the withholding.
- Gate readiness on reproducibilityAn independent reviewer must be able to reproduce each recommendation from its recorded inputs, verify every constraint and identify the items that require human judgment, before the workflow is considered ready for wider use.
Your systems, data, rules and accountable owners decide the real project. Agree acceptance criteria, escalation owners and operating responsibility with the people accountable for the work before anything runs on live records. Treat the first run as a rehearsal on test records: compare the draft output with an independently prepared answer, and record what the people reviewing it change.
Questions about this example
- What does Fanatics use AI for in merchandising?
- Per OpenAI, Fanatics assembles coordinated, in-stock looks from enriched product data, team information and inventory, with merchandising rules constraining the selections and a daily refresh. Engineers built the recommendation tools with Codex. Use is reported across Fanatics and official sports league stores.
- Who reviews the recommendations at Fanatics?
- OpenAI reports that Fanatics reviewed results, supplied feedback and approved the initial product before production rollout, and that merchandising rules constrain the selections. The source does not detail ongoing review of each look. Nuvepro's proposed design adds a merchandiser who checks compatibility and exceptions.
- How strong is the evidence for this example?
- It is reported production use, but a provider-published customer account, not an independent study. It reports 10% higher engagement after testing about 30,000 MLB products. That does not establish revenue uplift, and no evaluation duration, error rate or detailed experimental design is given.
- What would an enterprise need to build something similar?
- This is Nuvepro's proposed design, an illustrative practice setup and not a replica of Fanatics systems. It would use a fictional merchandise catalogue with versioned inventory, team identifiers and compatibility rules, with inputs, rule versions and stock timestamps retained, separate from live merchandising.
Shape this around your enterprise
Bring a similar workflow and the people responsible for it. Together, define the records and systems to use, the result your team will build or configure, and how its owners will check it. Nuvepro scopes the simulation, environment and preparation. Agree any existing-agent evaluation, implementation assistance and production responsibilities separately.
Sources and limitations
Curation review: . This is the date this source example was reviewed, separate from source publication dates.
- This is a provider-published customer account, not an independent study.
- The engagement claim does not establish revenue uplift; the article does not provide an evaluation duration, error rate or detailed experimental design.
- The proposed environment and checks are illustrative practice designs, not a delivered Nuvepro product or a replica of Fanatics systems.
- How Fanatics and OpenAI streamline the fan experienceSource publication: 2026-10-26
More sales and marketing examples
- AI car buyer qualification: Cars24 exampleCars24
- AI merchandising analysis: Walmart exampleWalmart
- AI ad campaign management: Advolve exampleAdvolve
- AI cold call practice: Mike Fishbein exampleUnnamed client (reported by Mike Fishbein)