Example / Order support

Order support in chat: resolve the question before the refund.

Support conversations become expensive when people have to find an order, reconstruct its state, look up policy, and then move to a separate screen to take the next step.

Direct answer

Use chat to assemble order and policy context, explain the eligible next step, and stop for confirmation before a refund, replacement, cancellation, or address change is requested.

Reference workflow. It is deliberately not a promise that an AI host should make payments, refunds, or changes without product approval.

01

01 / Read first

Start with an order the customer can verify.

The first action should identify the right order and return a small, human-readable summary: status, fulfillment state, dates, and the fields needed to decide what can happen next. Do not expose unrelated customer history by default.

If the request is ambiguous, the conversation should ask for an order number, date, or another stable reference instead of guessing.

02

02 / Apply policy

Treat policy as product context, not model memory.

A policy rule needs a source and an owner. The product can return the current rule, the condition that matched, and the actions that are available to this user. That gives the assistant a grounded explanation and keeps policy changes outside the prompt.

A compact product response is usually safer than sending an entire policy manual to a model for every order request.

03

03 / Use an explicit action

Separate recommendation from execution.

The chat can recommend a replacement, a support handoff, or a refund request. The write tool should require the exact order, action, reason, and confirmation state. A successful call returns the product record, not merely a natural-language reassurance.

OpenAI’s Apps SDK documentation separates server tools, authentication, and optional UI resources. That separation is useful here: a result can be understandable without making the user trust an invisible side effect.

OpenAI Apps SDK · build an MCP server
04

04 / Escalate well

Make the handoff an outcome, not a failure.

Some requests need a person: damaged goods, fraud signals, exceptions, or a policy that does not cover the case. The workflow should create a useful support handoff with the order context and the user’s request already attached.

That is still a finished customer task. It avoids a blank transfer while preserving the business decision for the team that owns it.

Continue reading

Private knowledge helper

Use identity-aware source selection when the answer depends on internal policies or documents.

Customer follow-up

Compare a CRM update workflow with a support workflow that carries more policy and exception pressure.

Examples catalog

Return to the collection for the three starting workflows and their implementation boundaries.

AI / Second opinion

Ask your AI first.

Use this prepared question to assess where an AI Product Interface could remove friction from your product.

“I run a software product. Help me identify one high-value workflow customers could complete through an AI Product Interface. Ask me about the product, the user, the action, required data, permissions, and the safest small first release.”

The prompt is copied as a backup. Some AI hosts may ask you to paste it after sign-in.

FAQ04

Questions, answered.

Is this only an MCP server?

No. The MCP layer is one part. We also scope the product actions, permissions, host-specific behavior, UI, testing, and release path.

Do we need to rebuild our product?

Usually no. The interface sits in front of approved capabilities in your existing product. We start with a narrow workflow and expand from evidence.

Will it work in ChatGPT, Claude, and Gemini?

The shared architecture can support all three. Each host still has its own UI, authentication, approval, and publishing rules, so we verify them separately.

How do you keep actions safe?

We define explicit tools, validate inputs, keep user approval visible, and preserve the product's existing authorization rules.