Agent Storefront

An AI agent sales page app idea: a machine-readable product page for AI buyer agents. One week build with Next.js, Supabase, Claude API and mcp, for small saas founders whose buyers now research with ai agents.

See the spec
Why now

Why now

Tobira Site Agent shows sellers are starting to build sites that talk to AI agents, and mcp downloads on PyPI are up 70% against the rest of the month. A small founder can ship a simple version of this without a full agent platform. From the signals of the week of 9 Nov 2026.

The spec

The spec

Generates a structured, plain-text page for your product with pricing, limits, integrations and a clear fit and no-fit list, so an AI agent comparing vendors gets correct answers. It also gives a human-readable preview so you can check what an agent would say about you.

Build time

One weekAPIs or integrations · Level 3 of 5

Audience

Small SaaS founders whose buyers now research with AI agents.

Stack

  • Next.js
  • Supabase
  • Claude API
  • mcp

Fun factor

Watching a fake buyer agent grill your page shows the holes fast.

Core features

  • Product facts form with pricing and limits
  • Fit and no-fit list builder
  • Public markdown and JSON page for agents
  • Preview of how an agent would summarise you

AI features

  • Turns messy sales notes and FAQ emails into clean structured product facts
  • Simulates a buyer agent asking vendor questions and flags answers your page cannot support

Stretch goals

  • Expose the page through an MCP server
  • Log which agents visit and what they ask
  • Competitor comparison page generator

First version

A form that produces a hosted markdown and JSON product page plus a simulated buyer question test.

Build plan

Build plan

4 milestones, in the order you would build them. Saved ideas get this plan with checkboxes and notes.

Model the product factsDefine the schema for pricing, limits, integrations and fit.
Start here
Publish the pageServe markdown and JSON at a stable public URL.
Add the buyer simulationAsk the model ten vendor questions using only your page.
Show gapsList the questions the page could not answer.
The build prompt

The build prompt

Paste this into ChatGPT, Claude, Codex, or Cursor, then build the first version before anything else.

agent-storefront.prompt.md
# Build Agent Storefront

You are a senior full-stack engineer pairing with me on a side project. Build a working first version of the product described below. Read the whole brief before writing any code, then follow "How to work" at the end.

## The idea

**Agent Storefront.** Generates a structured, plain-text page for your product with pricing, limits, integrations and a clear fit and no-fit list, so an AI agent comparing vendors gets correct answers. It also gives a human-readable preview so you can check what an agent would say about you.

**Why now:** Tobira Site Agent shows sellers are starting to build sites that talk to AI agents, and mcp downloads on PyPI are up 70% against the rest of the month. A small founder can ship a simple version of this without a full agent platform.

**Who it is for:** Small SaaS founders whose buyers now research with AI agents

**What makes it fun:** Watching a fake buyer agent grill your page shows the holes fast.

## Scope

- **Build time:** One week. Size every decision to ship a working first version inside this window.
- **Technical ambition:** Level 3 of 5, "APIs or integrations". The product leans on third-party APIs. Wrap each integration in its own module, handle its failures and rate limits, and cache what is safe to cache.
- **First version only.** Ship the core features below end to end. Stretch goals are listed so you can design around them, not build them.

## Core features (each must work end to end in the first version)

1. Product facts form with pricing and limits
2. Fit and no-fit list builder
3. Public markdown and JSON page for agents
4. Preview of how an agent would summarise you

## AI features

- Turns messy sales notes and FAQ emails into clean structured product facts
- Simulates a buyer agent asking vendor questions and flags answers your page cannot support

How to build them:
- Put every model call behind one server-side module with a typed interface, so the provider can change without touching the UI.
- Read API keys from environment variables only, and document each one in `.env.example`.
- Write prompts as versioned constants with clear instructions and an example of the expected output; parse and validate responses before using them.
- Handle timeouts, rate limits, and malformed output with a graceful fallback the user can understand. Stream responses where a wait would exceed a couple of seconds.
- Never let a feature depend on the model being perfect. Show the result, let the user edit or retry.

## Stretch goals (later, not in the first version)

- Expose the page through an MCP server
- Log which agents visit and what they ask
- Competitor comparison page generator

Leave clean seams for these (a module boundary, a nullable column, a feature flag), but do not implement them unless I ask.

## Tech stack

Use exactly: Next.js, Supabase, Claude, Mcp.

Stay on current stable versions, follow each tool's official conventions, and add a library only when the standard library or the chosen stack cannot do the job cleanly. If part of this stack is a poor fit for a specific requirement, say so and propose the smallest change.

## Owner's notes

Written by me, the project owner. Treat these as requirements and preferences that override the generated material above when they conflict.

The first version should be exactly this, and no bigger: A form that produces a hosted markdown and JSON product page plus a simulated buyer question test.

## Build plan (with saved progress)

0 of 4 steps complete. Resume at step 1: Model the product facts. Before you start it, check what is already implemented so you do not repeat finished work.

1. **Model the product facts** [not started]
   Define the schema for pricing, limits, integrations and fit.

2. **Publish the page** [not started]
   Serve markdown and JSON at a stable public URL.

3. **Add the buyer simulation** [not started]
   Ask the model ten vendor questions using only your page.

4. **Show gaps** [not started]
   List the questions the page could not answer.

## Definition of done for the first version

- [ ] Product facts form with pricing and limits works end to end, with real data, not a placeholder.
- [ ] Fit and no-fit list builder works end to end, with real data, not a placeholder.
- [ ] Public markdown and JSON page for agents works end to end, with real data, not a placeholder.
- [ ] Preview of how an agent would summarise you works end to end, with real data, not a placeholder.
- [ ] Every screen handles loading, empty, and error states.
- [ ] Typecheck, lint, and any tests pass, and the main user flow was exercised by hand.
- [ ] A README explains setup, environment variables, and how to run it locally.

## Quality bar

- Responsive from a phone to a desktop, keyboard-accessible, semantic HTML, visible focus states, labelled inputs, and sensible contrast.
- Loading, empty, and error states for every screen that reads or writes data. Errors say what happened and what to do next.
- Validate on the server, never trust the client, and keep secrets in environment variables with a committed `.env.example`.
- Type-safe end to end. No `any` without a comment explaining why.
- Small, readable modules named after what they do. No premature abstraction, no dead code, no TODOs left for later without a note.
- Sensible defaults over settings. If a choice is not in this brief, pick the simplest option that keeps the product coherent and say what you chose.

## How to work

1. **Read, then restate.** Summarize the product in three sentences and list your assumptions. Ask only the questions that block implementation. For everything else, decide and note the decision.
2. **Plan before code.** List the files and modules you will create, in build order, mapped to the core features. If a build plan is included above, use it instead: resume at the first step not marked done and check what already exists before touching it.
3. **Set up.** If a project already exists, inspect its code, instructions, and conventions first and build on them. Otherwise scaffold the stack above with linting, formatting, a typecheck script, `.env.example`, and a README stub.
4. **Model the data first.** Define the types, schema, and any migrations before the UI, so the shape of the product is settled early.
5. **Build in vertical slices.** Finish one core feature end to end (data, logic, UI) before starting the next. Keep the app runnable after every slice and commit each slice with a message that says what changed and why.
6. **Then the interface.** Apply the quality bar above to each screen as it lands, not as a final pass.
7. **Verify.** Run typecheck, lint, and tests. Exercise the main user flow by hand. Check each item in the definition of done and each acceptance criterion.
8. **Report.** Tell me what works, what you tested and how, what is not done, every setup step I must complete myself, and the three most useful next steps. Never claim a service, test, or flow was verified when it was not.

If you can edit and run the project, start implementing right after the short plan. If you cannot, give me concrete code and the exact commands to run for the next step.

Rules: keep the product name and the scope as written, do not invent features, prefer boring and proven choices, and stop to ask me when a decision would be expensive to reverse.

How to use

  1. Copy the prompt above.
  2. Open ChatGPT, Claude, or your AI editor and paste it into a new conversation.
  3. Build milestone one, run it, then move to the next. Add stretch goals only after the first version works.

Want ideas built around you instead? Generate four from your own interests, time, and stack.

Frequently asked questions

FAQ

Frequently asked questions

Answers on what Agent Storefront is, how to build it, and where example ideas come from.

Similar ideas

Similar to Agent Storefront

More sales ideas, then a few from other categories.

Generate your own

Ready to generate yours?

Four ideas per round, shaped by your interests, skill level, and how much time you have.