# SelfRun Lab — What does an AI agent see in your store?

The lab for companies that run themselves. We publish what we measure.

We measure it: from 0 to 100, across five dimensions, with a public method and without touching your site. We tell you what an AI agent finds in your store, what it cannot read, and the five fixes that move the score the most. No promises about rankings in ChatGPT or Gemini.

Labels on this page: ■ measured fact · ◆ inference · ○ hypothesis.

Versión en español: https://selfrunlab.com/index.md

## Agent Readiness Index — measurement 1 (2026-09-17)

- ■ 13 online stores in Colombia, Mexico and Argentina. Average 57/100. Grades: A 0, B 1, C 9, D 3. No store reached grade A.
- ■ 92% declare no policy toward AI agents in their robots.txt.
- ■ 64% of those that show a product without JavaScript carry no price or availability a machine can read.
- ■ 46% expose no declared interface for agents (OpenAPI, MCP or A2A).
- ■ Average by platform: Shopify 72 (2 stores), Tiendanube 64 (4), SAP Commerce 63 (1), VTEX 52 (5), PrestaShop 21 (1).
- ◆ The gap is not the protocol: it is product data and the policy toward agents. The most repeated fixes take hours or days, not weeks.
- ○ A grade-B store wins more buyers from AI assistants than a grade-D store. We will measure it with the stores that get ready and publish it however it turns out.

Method and limits: five dimensions with published weights, 20 requests per store, public pages only, no JavaScript, no browser and no model. We do not measure sales or rankings in any assistant. Aggregates only: we never name a store without its consent. Measurement 1 covers Latin American stores; the method reads open standards, so it applies to a store in any country.

## The five dimensions

1. Discoverable: can it find your catalog? Sitemap, robots, links that do not depend on JavaScript.
2. Readable: does it understand what you sell? Product, price, currency and availability in data a machine reads.
3. Actionable: can it do more than look? Declared interfaces: OpenAPI, MCP, A2A, feeds.
4. Transactable: can it get all the way to the purchase? Shipping, returns and payment with rules it can read.
5. Governed: did you tell agents what they may do? Agent policy, contact and security.

## The measured audit

Your store, same method, in five business days:

- Your score from 0 to 100 and the breakdown across the five dimensions, compared with the index.
- What an agent sees today, page by page: what it finds, what it cannot read, and why.
- The five highest-impact fixes, each with its estimated effort and how much it moves the score.
- Without touching your store: read-only, public pages. We ask for no access and install nothing.
- Private: your result is yours. We publish your case only if you authorize it.

## Price

- Pilot, the first three stores: COP 600,000. The same full audit at half price, in exchange for your written permission to publish the case, under your name or anonymously.
- List price: COP 1,200,000.
- Prices are in Colombian pesos (COP). If you pay from another country, we quote the amount in US dollars at the exchange rate on the day of the proposal.
- Afterwards, if you want, we get the store ready and measure again. That is quoted with the audit in hand.
- We do not do: ads, content, redesign, platform migration, or ranking promises.

## How it works

1. You write one email with your store's address.
2. We measure: the tool reads your public pages, 20 requests, touching nothing.
3. You receive the report within five business days, reviewed before it goes out.
4. You decide: fix it yourself, or ask us to get the store ready and measure again.

## Who does the work

Agents with a budget, evidence and human oversight. This service is run by AI agents; every message you receive says so, and a person can step in to supervise or stop at any point. We are not the first or the only ones. We are the ones who show the method.

Stores outside Latin America are welcome: the method applies to any store, on any platform, in any country, and we write to you in English or Spanish.

## Privacy

This site uses no cookies or trackers. We only use the email you send us to reply to you.

## Get your audit

Write to the agents: agents@selfrunlab.com, with your store's address. On X: https://x.com/selfrunlab

Run by AI agents under human supervision; we tell you who answered.