Skip to content

Blog · Published · Updated

Shopping in ChatGPT: how a store can appear in recommendations

Short answer

ChatGPT helps choose a product: it shows cards with the price, a photo and reviews, compares offers and sends the customer to the store, where the purchase is completed. OpenAI ended purchases made entirely in the chat on 24 March 2026. So sales depend on whether ChatGPT finds the product, describes it correctly and gives a link. A product data audit costs from €600 net at Syntalith, and feed automation from €3,000.

How we workDetails ↓

  1. 01Call30 minutes with an engineer, free
  2. 02PrototypeA working system on your process and data, free
  3. 03ImplementationTarget and fixed price in the contract; 50% at signing
  4. 04Acceptance50% once the agreed target is met
analysis with an engineer and a free prototype
€0
team in ChatGPT or Claude, up to 10 people
from €1,150
automation, agent or application for one process
from €3,000

We belong to the OpenAI and Anthropic partner programmes and learn through their official courses. What this means ↓

Author: Syntalith · 3 min read

Example: the morning request inbox
Agent · ready

Statistics

Shopping with AI: statistics 2026

3×

lower was the conversion of products sold directly in the chat than of those where the customer went to the store, according to Walmart data cited by Modern Retail (2026).

Figures checked: 22 October 2026

Where ChatGPT gets its products

OpenAI ended purchases made entirely in the chat, called Instant Checkout, on 24 March 2026 and focused on product discovery. The checkout stays in the store.

Four routes to a recommendation
  • Web search

    OAI-SearchBot visits the pages

    do not block the bot, readable product pages

  • A feed through ACP

    a file with products and promotions

    the programme terms and a feed to the specification

  • Partner catalogues

    Shopify Catalog with no extra work

    complete product data

  • An app in ChatGPT

    its own search and customer account

    large catalogues, such as Allegro

OpenAI's documentation on its bots says that a page blocked for OAI-SearchBot will not appear in search answers, at most as a navigation link.

What the Agentic Commerce Protocol is

ACP is an open standard from OpenAI and Stripe, in beta. In September 2025 it handled buying in the chat, and since March 2026 it has mainly served to pass products and promotions. The feed specification sets the required and optional fields and the validation rules. Check the current OpenAI terms for whether the programme is open to stores outside the USA.

Why buying in the chat did not catch on

Modern Retail reported that, according to Walmart, the conversion of products sold in the chat was three times lower than of those where the customer went to the store. Sellers pointed to no basket for several products, no loyalty programmes and no current stock levels. Customers search in ChatGPT and buy where they have an account and saved payment details.

On 12 May 2026 the Polish marketplace Allegro launched an app in ChatGPT: the user describes what they are looking for, gets offer cards, and the „Buy on Allegro” button takes them to payment and delivery.

What a store can do this month

Five steps
  1. 01BotsCheck robots.txt and the logs: does OAI-SearchBot get the product and category pages.
  2. 02QuestionsAsk ChatGPT 20 customer questions and note whom it recommends and what data it gives.
  3. 03PagesPrice, availability, variants, delivery and returns in the page text and the structured data.
  4. 04MeasurementA report of sessions and orders from utm_source=chatgpt.com, described in OpenAI's help.
  5. 05FeedA feed from Google Merchant Center is mostly field mapping and quality control.

The full plan, which also covers Google and Copilot, is in the agentic commerce guide. The tracking parameter is described in OpenAI's help. Shopify stores are covered by the agent purchase test.

What tidying product data costs

Scenario: checking the data of 5,000 products a month
Today
5,000 products × 1 min = 83.3 h (€2,908)
With the system a person checks the output in 15% of the time
€436
Model, 1 call per case, Claude Sonnet 5.5
€22
Cost of one case
€0.58 today, €0.09 with the system
Saving
€2,450 a month

Payback of €3,000

1.2 months

The volume, the time and the checking share are the scenario's assumptions. €34.90 an hour is the EU average hourly labour cost for 2025 according to Eurostat. Model: 1,000 input tokens and 300 output tokens per call at Anthropic's rates, at the ECB rate of 1.1205 USD per euro on 22 October 2026. A minute per product covers checking the price, availability, variants and description in the feed.

We check how ChatGPT and other assistants describe your store, and fix the data that decides it. An audit costs from €600 net, and automating the feed and data checks from €3,000 net. The state described in this article: 11 October 2026.

This is how we implement it in companies

All case studies →

Client results.

All projects →
foap.comcustomer service

foap.com customer service: 95% of replies are sent automatically.

Users from several countries write to foap.com, in several languages. The system reads the entire conversation and the terms of that person, and then sends a response in that person's language. Questions about money and exceptions go to the team with a ready draft, so they have to check and send them.

the system sends the answers itself, without human typing
95%
time from the arrival of the e-mail to the ready response (median)
30 s
e-mails that require a response receive a ready-made draft
100%
less work for every 1000 answers (estimate)
47 h

Data from foap.com production, October 20-21, 2026. Estimate: 3 minutes for handwritten response.

How foap.com customer service works →
Sample messages. Money matters always come to the person.

Other implementations

jaktako.design

studio projektowe

−87%

Time to look for new customers, every day

4 hours → 30 min

approx. 73 hours less per month (21 days of work)

according to the studio

How the agent loop works →
Signature Estates

real estate

approx. −90%

Operator time spent browsing portals, per day

2–3 hours → 20 min

approx. 45 hours less per month (21 days of work)

respect · contact the seller 5 minutes after the announcement

How the agent finds property listings →
Kuba Koziej, CEO and co-founder of MoreGrowth and board member at Natu.Care

Kuba Koziej

CEO and co-founder, MoreGrowth

„We started with my own AI agent. During the training that followed, I learned to build new applications myself. Today I am bringing this way of working with AI into my business. Working with Syntalith gave me exactly the skills and tools I needed.”

View the original training review on LinkedIn ↗

Start with the process that takes the most time each week.Book a free process review (30 min) →

How we build automation and agents

From a conversation to a working system in four steps.

  1. 01 · 30 min

    Free process review

    €0

    You're talking to an engineer. You receive the written plan within 2 business days.

  2. 02 · 5 days

    Free prototype

    €0

    The system works on 20-100 cases that your team has already handled. You see every result.

  3. 03 · 2–16 weeks

    Build

    50%

    Fixed price and goal written in the contract. First installment upon signing.

  4. 04 · after reaching the goal

    Reception

    50%

    You pay the second installment when the system reaches its target on your cases.

How a free prototype is created

Mon.

We set a goal

What result do you consider good?

Tue–Wed

The system is working

It goes through your affairs, one by one.

Thu

We compare

We check every difference with the team's work.

Fri

Result and price

List of errors and fixed implementation price.

You choose the matters. We anonymize them upon request, they stay in the EU and we delete them after the test.

On the market, such a test usually costs from PLN 3,000 to PLN 8,000.

Book a free process review (30 min)

We establish a prototype during a free analysis.

Data checked on October 21, 2026.

„Is my data safe?”

Yes. You choose where they go: from your company account to the model on your server.

  1. 00Employee's private account

    Customer and company data ends up in an account that the company cannot see or control. There is no data processing agreement, so it is a violation of the GDPR. When an employee leaves, the chat history goes with them.

  2. 01ChatGPT or Claude corporate account

    The provider does not use your data to train models. A copy of the queries remains in his logs for up to 30 days.

  3. 02API with zero retention (ZDR)

    The provider processes the request and does not save anything. It requires his consent, we prepare the application together.

  4. 03Processing in the EU

    Queries are counted and stored in Europe: OpenAI in the EU region, Claude via clouds with the EU region.

  5. 04Model at your place

    The open model runs on your server or in your cloud in the EU. The data does not go outside the company.

What we do with every implementation

  • Confidentiality agreement and data processing agreement before we receive any data.
  • You choose the cases for the prototype and we anonymize them upon request.
  • The data stays in the EU and we delete it after the test.
  • Corporate accounts with an administrator on your side.

When data cannot leave the company

The open model runs on your server or in your cloud in the EU. To choose from:

White-tailed eagle
Polish model, SpeakLeash and ACK Cyfronet AGH
PLLUM
Polish model, HIVE consortium commissioned by the Ministry of Digitization
Qwen
Alibaba
GLM
Zhipu AI
DeepSeek
DeepSeek

We select a model for the task and check it on your cases. We run it, tune it and maintain it.

Source: Bielik and PLLuM, ACK Cyfronet AGH ↗ · PLLuM, Ministry of Digitization ↗

Do you have a lot of your own data? We will fine-tune the small model.

  1. 1 Your examples
  2. 2 tuning
  3. 3 test on new cases
  4. 4 model at your place

When you have thousands of similar emails, documents or reports, we teach a small open model based on your examples. It works for you, responds quickly and costs less to maintain than a large model. We measure quality on issues that the model has not seen while learning.

Przemysław and Piotr did it in large programming and consulting companies. Artem did it before and does it today at Syntalith. It's about models on your own infrastructure, tuning and quality measurement.

You choose the protection level during the interview. We sign the data processing agreement before we see any data.Schedule a free analysis →

AI implementation

Start with the process that takes the most time each week.

The engineer chooses one process with you and calculates how much it costs today. Then we build a free prototype on 20-100 cases that your team has already handled. We write down the goal and the fixed price in the contract.

See AI implementation →
analysis with an engineer and a free prototype
€0
team in ChatGPT or Claude, up to 10 people
from €1,150
automation, agent or application for one process
from €3,000

Questions

  • How can a store appear in ChatGPT?

    Do not block OAI-SearchBot, keep product pages readable with the price, availability and variants, and if the programme terms allow it, send a product feed through the Agentic Commerce Protocol. Shopify stores get there through the partner's catalogue.

  • What is the Agentic Commerce Protocol (ACP)?

    An open standard from OpenAI and Stripe, in beta. Since March 2026 it has mainly served to pass products and promotions to ChatGPT. The feed specification sets the required and optional fields and the validation rules.

  • Can you buy a product in ChatGPT without leaving the chat?

    OpenAI ended Instant Checkout on 24 March 2026 and focused on product discovery. The customer completes the purchase in the store, and since 12 May 2026 the Polish marketplace Allegro moves them from its app in ChatGPT to its own checkout.

  • How do we measure traffic from ChatGPT?

    ChatGPT adds the parameter utm_source=chatgpt.com to links. Build a report in your analytics of sessions, baskets and orders from that source.

  • How much does preparing a store for ChatGPT cost?

    An audit at Syntalith costs from €600 net, and automating the feed and product data checks from €3,000 net. At 5,000 products checked every month, the automation pays back in 1.2 months.

Let's talk

Just write, call or choose a date.

We work fast because we hate corporate cotton wool. We don't have salespeople or managers to keep an eye on managers. You talk immediately to engineers who then build your system. We respect each other's time and yours too.

We will accept 3 more companies by the end of the year.

Mon–Fri 9:00–17:00 CET

What our OpenAI and Anthropic partnerships mean for you.

OpenAI makes ChatGPT and Anthropic makes Claude. We belong to the partnership programs of both companies, so we work with their tools every day and learn from the creators themselves.

OpenAI Select PartnerClaude Partner Network
01We will select a tool for the task
We implement both ChatGPT and Claude. We check both on your documents, and you choose the one that makes fewer corrections and saves more time.
02Knowledge straight from the creators
We learn from official OpenAI and Anthropic courses and materials. Your team learns about the features and settings that work today.
03Licenses without our margin
You buy accounts directly from OpenAI or Anthropic and receive an invoice from them. We do not add anything to the license.
04Certified engineers
On the team, we have an AWS certification in machine learning and an Anthropic certification in systems architecture on Claude.

Participation in programs does not mean that OpenAI or Anthropic endorses our services.