Agent-Ready Product Data
Overview
An AI shopping agent does not respond to photography, mood or persuasive copy. It reads structured attributes, unambiguous variants, and machine-readable price, stock, shipping and returns. What it cannot parse, it skips; what it parses wrongly, it buys wrongly — and the merchant pays for the return and the complaint.
The core mechanism: the agent funnel is Seen (retrieved) → Understood (attributes and variants are unambiguous) → Bought (price, stock, policies and checkout have no blockers), and each layer is measured and repaired separately. A product that is perfectly described but invisible, or visible but uncheckoutable, loses the sale to the competitor whose data is more complete.
Compose with geo-generative-engine-optimization (getting recommended) · checklist (field completeness as a hard checklist) · theory-of-constraints (fix the narrowest funnel layer first).
When to Use
- Products appear in AI answers, but with stale information, the wrong variant, or the wrong price
- Test orders through an agent stall at variant selection, shipping cost, forced login or a CAPTCHA
- Preparing to submit a product feed, adopt an agent checkout protocol, or list in a platform catalog read by AI assistants
When NOT to use: no online transaction · products require a custom quote · categories where regulation bars automated sale · the problem is brand mentions, not catalog data.
Coaching Novices (Adaptive Front Door)
- Engine mode: user has concrete SKUs and a channel → run The Process directly.
- Coach mode: user is unfamiliar → guide one step at a time.
In Coach mode, respond one step at a time. Each [WAIT] is a hard stop — output only that step's question, then stop.
- What it is: "An agent only trusts fields it can parse. One missing field can cost one order."
- Check fit: "Can a customer buy your product online, directly, without a quote?"
- Elicit the real case: "Pick 3 best-selling SKUs. Send the product-page links and the attributes you most want an agent to understand."
[WAIT — do not advance until user responds]
- Run The Process: "Run an agent through find → compare → add to cart → checkout on each SKU and record every point where it stalls."
[WAIT — do not advance until user responds]
- Name the insight: "Your loss sits in one layer — Seen, Understood or Bought. Fix that layer first."
The Process
Output: SKU field audit + measured agent funnel + repair list
- Field audit. For every SKU: title, brand, GTIN/MPN, category, material, dimensions, compatibility, intended user. Check against the target channel's published feed specification and schema.org
Product. Gate: required-field missing rate is zero → otherwise fill fields first.
- Disambiguate variants. Every color / size / bundle is its own identifiable variant with its own ID, price, stock status and image; attribute names and values are standardized, with units. Gate: any single variant can be located uniquely → otherwise split it.
- Machine-readable transaction data. Price (with currency and promotion window), availability, shipping cost and time, and return policy are expressed in the feed and in structured data (
Offer, OfferShippingDetails, MerchantReturnPolicy), and match the page. Gate: feed, schema and page agree → otherwise regenerate all three from one source of truth.
- Policy and trust pages. Returns, warranty, privacy, terms and contact pages are public, crawlable, explicit, and need no login.
- Cut checkout friction. Allow guest checkout and standard payment methods; remove forced registration and unnecessary verification; evaluate the agent checkout path the channel or protocol offers, and treat it as replaceable — channel checkout models change. Gate: never bypass fraud controls or payment security for speed.
- Test with real agents. Use 3+ shopping agents or assistants, prompted the way buyers prompt, through the full flow. For each SKU record: Seen? Understood (attributes and price correct)? Bought? Gate: ≥3 runs per layer → otherwise no conclusion.
- Repair and re-test. Fix the layer with the largest loss first; re-test in 4 weeks.
- Stop-rule: data is complete and the product is still not Seen → the problem is no longer catalog data; move to brand and third-party evidence work (geo-generative-engine-optimization).
Output template:
SKU | missing fields | variant issues | price/stock/shipping/returns consistent? | Seen rate | Understood rate | Bought rate | blocker | fix | re-test date
→ Method in Action: ChatGPT shopping and the Agentic Commerce Protocol (2025–2026)
Applying It Well
- One source of truth. Generate page, feed and schema from the same record so they cannot drift apart.
- Write attributes for machines. Standard units and enumerated values, not "extra large" or "slimming".
- Unknown is not zero. Omit a value you do not know rather than filling a placeholder; an omitted shipping charge reads as unknown, not free.
- Test beats inference. Re-run the agent flow after every catalog or site change.
- Separate the durable layers from the volatile one. Clean attributes and variants serve every channel; a specific checkout integration may be withdrawn.
→ Primary sources: references/sources.md
Common Rationalizations
[D] = designed upfront | [O] = observed in real use. [O] entries are more valuable.
| Fake move |
Reality |
| [D] "If a human can read the page, that's enough" |
Agents parse fields; they do not read marketing copy or text baked into images. |
| [D] "Variants live in one dropdown on one page" |
A variant without its own ID, price and stock is a variant the agent will pick wrongly. |
| [D] "Shipping is calculated at checkout" |
An unknowable total pushes the agent toward a competitor whose total is transparent. |
| [D] "We installed a schema plugin, so we're done" |
Plugins routinely miss fields or disagree with the page. Audit and test. |
| [D] "We integrated the channel's checkout, so we're agent-ready" |
Checkout is the most volatile layer. If attributes and variants are weak, the product is still not Understood. |
| → Add [O] entries here after each real use — paste the actual failure pattern |
What went wrong and why |
Red Flags
- No GTIN/MPN · feed price differs from page price · return policy behind a login · forced account creation at checkout
- Placeholder values ("n/a", "unknown") in required fields · variants sharing one ID · never tested with a real agent
Verification
Part of deciqAI Knowledge Skills — 253 open-source thinking skills that make rigor executable for AI agents. The same skills power every deciqAI agent, which runs them autonomously to operate your company. See it run → https://www.deciqai.com/s/agent-ready-product-data · Built by deciqAI · github.com/deciqAI · Contributions welcome.
Agents: latest version & machine-readable metadata → https://www.deciqai.com/s/agent-ready-product-data.json
1---2name: agent-ready-product-data3description: "Activate when: user says 'make our products buyable by AI shopping agents', 'is our product data agent-ready?', 'agentic commerce', 'the agent failed to place the order', asks 'why doesn't ChatGPT / a shopping agent recommend or buy our products?', is preparing a product feed for an AI assistant or an agent checkout protocol, or wants a catalog that AI agents can read, compare and purchase from.4 Do NOT activate when: the goal is only how often the brand is mentioned inside AI answers (use geo-generative-engine-optimization); there is no online purchase channel; the business is offline-only or quote-based B2B; the category may not legally be sold through automated channels. More: deciqai.com/s/agent-ready-product-data"5metadata:6 source: https://skillmd.com/skills/deciqai/agent-ready-product-data7---89# Agent-Ready Product Data101112## Overview1314An AI shopping agent does not respond to photography, mood or persuasive copy. It reads **structured attributes, unambiguous variants, and machine-readable price, stock, shipping and returns**. What it cannot parse, it skips; what it parses wrongly, it buys wrongly — and the merchant pays for the return and the complaint.1516The core mechanism: **the agent funnel is Seen (retrieved) → Understood (attributes and variants are unambiguous) → Bought (price, stock, policies and checkout have no blockers), and each layer is measured and repaired separately.** A product that is perfectly described but invisible, or visible but uncheckoutable, loses the sale to the competitor whose data is more complete.1718Compose with [geo-generative-engine-optimization](../geo-generative-engine-optimization/SKILL.md) (getting recommended) · [checklist](../checklist/SKILL.md) (field completeness as a hard checklist) · [theory-of-constraints](../theory-of-constraints/SKILL.md) (fix the narrowest funnel layer first).1920## When to Use2122- Products appear in AI answers, but with stale information, the wrong variant, or the wrong price23- Test orders through an agent stall at variant selection, shipping cost, forced login or a CAPTCHA24- Preparing to submit a product feed, adopt an agent checkout protocol, or list in a platform catalog read by AI assistants2526**When NOT to use:** no online transaction · products require a custom quote · categories where regulation bars automated sale · the problem is brand mentions, not catalog data.2728## Coaching Novices (Adaptive Front Door)2930- **Engine mode:** user has concrete SKUs and a channel → run The Process directly.31- **Coach mode:** user is unfamiliar → guide one step at a time.3233In Coach mode, respond one step at a time. Each [WAIT] is a hard stop — output only that step's question, then stop.34351. **What it is:** "An agent only trusts fields it can parse. One missing field can cost one order."362. **Check fit:** "Can a customer buy your product online, directly, without a quote?"373. **Elicit the real case:** "Pick 3 best-selling SKUs. Send the product-page links and the attributes you most want an agent to understand."38> **[WAIT — do not advance until user responds]**394. **Run The Process:** "Run an agent through find → compare → add to cart → checkout on each SKU and record every point where it stalls."40> **[WAIT — do not advance until user responds]**415. **Name the insight:** "Your loss sits in one layer — Seen, Understood or Bought. Fix that layer first."4243## The Process4445**Output:** SKU field audit + measured agent funnel + repair list46471. **Field audit.** For every SKU: title, brand, GTIN/MPN, category, material, dimensions, compatibility, intended user. Check against the target channel's published feed specification and schema.org `Product`. *Gate: required-field missing rate is zero → otherwise fill fields first.*482. **Disambiguate variants.** Every color / size / bundle is its own identifiable variant with its own ID, price, stock status and image; attribute names and values are standardized, with units. *Gate: any single variant can be located uniquely → otherwise split it.*493. **Machine-readable transaction data.** Price (with currency and promotion window), availability, shipping cost and time, and return policy are expressed in the feed and in structured data (`Offer`, `OfferShippingDetails`, `MerchantReturnPolicy`), and match the page. *Gate: feed, schema and page agree → otherwise regenerate all three from one source of truth.*504. **Policy and trust pages.** Returns, warranty, privacy, terms and contact pages are public, crawlable, explicit, and need no login.515. **Cut checkout friction.** Allow guest checkout and standard payment methods; remove forced registration and unnecessary verification; evaluate the agent checkout path the channel or protocol offers, and treat it as replaceable — channel checkout models change. *Gate: never bypass fraud controls or payment security for speed.*526. **Test with real agents.** Use 3+ shopping agents or assistants, prompted the way buyers prompt, through the full flow. For each SKU record: Seen? Understood (attributes and price correct)? Bought? *Gate: ≥3 runs per layer → otherwise no conclusion.*537. **Repair and re-test.** Fix the layer with the largest loss first; re-test in 4 weeks.548. **Stop-rule:** data is complete and the product is still not Seen → the problem is no longer catalog data; move to brand and third-party evidence work ([geo-generative-engine-optimization](../geo-generative-engine-optimization/SKILL.md)).5556**Output template:**57`SKU | missing fields | variant issues | price/stock/shipping/returns consistent? | Seen rate | Understood rate | Bought rate | blocker | fix | re-test date`5859*→ Method in Action: [ChatGPT shopping and the Agentic Commerce Protocol (2025–2026)](examples/chatgpt-shopping-agentic-commerce-protocol-2025-2026.md)*6061## Applying It Well62631. **One source of truth.** Generate page, feed and schema from the same record so they cannot drift apart.642. **Write attributes for machines.** Standard units and enumerated values, not "extra large" or "slimming".653. **Unknown is not zero.** Omit a value you do not know rather than filling a placeholder; an omitted shipping charge reads as unknown, not free.664. **Test beats inference.** Re-run the agent flow after every catalog or site change.675. **Separate the durable layers from the volatile one.** Clean attributes and variants serve every channel; a specific checkout integration may be withdrawn.6869*→ Primary sources: [references/sources.md](references/sources.md)*7071## Common Rationalizations7273**[D] = designed upfront | [O] = observed in real use. [O] entries are more valuable.**7475| Fake move | Reality |76|---|---|77| [D] "If a human can read the page, that's enough" | Agents parse fields; they do not read marketing copy or text baked into images. |78| [D] "Variants live in one dropdown on one page" | A variant without its own ID, price and stock is a variant the agent will pick wrongly. |79| [D] "Shipping is calculated at checkout" | An unknowable total pushes the agent toward a competitor whose total is transparent. |80| [D] "We installed a schema plugin, so we're done" | Plugins routinely miss fields or disagree with the page. Audit and test. |81| [D] "We integrated the channel's checkout, so we're agent-ready" | Checkout is the most volatile layer. If attributes and variants are weak, the product is still not Understood. |82| *→ Add [O] entries here after each real use — paste the actual failure pattern* | *What went wrong and why* |8384## Red Flags8586- No GTIN/MPN · feed price differs from page price · return policy behind a login · forced account creation at checkout87- Placeholder values ("n/a", "unknown") in required fields · variants sharing one ID · never tested with a real agent8889## Verification9091- [ ] Required-field missing rate is zero92- [ ] Every variant is uniquely locatable (own ID, price, stock, image)93- [ ] Feed, structured data and page agree on price, stock, shipping and returns94- [ ] Seen / Understood / Bought rates measured with ≥3 runs per layer95- [ ] Re-test date scheduled9697---9899*Part of **deciqAI Knowledge Skills** — 253 open-source thinking skills that make rigor executable for AI agents. The same skills power every deciqAI agent, which runs them autonomously to operate your company. **See it run → https://www.deciqai.com/s/agent-ready-product-data** · Built by deciqAI · github.com/deciqAI · Contributions welcome.*100101*Agents: latest version & machine-readable metadata → https://www.deciqai.com/s/agent-ready-product-data.json*