Courtyard AI

The more AI understands your small business, the more business it can bring you.

[Courtyard AI @courtyardai]

https://t.co/qARslBCHQk

[Courtyard AI @courtyardai]

When AI shows a photo of your business, is it yours?

AI answers in @ChatGPTapp @GeminiApp @perplexity_ai @claudeai are increasingly including images.

We built Media Library for the way AI actually finds and understands them. So the images AI shows about your business are more likely to be your real, up-to-date, and accurate photos.

[Courtyard AI @courtyardai]

See the rankings every week: https://t.co/GS0sk9Wpq1

[Courtyard AI @courtyardai]

Which local businesses does AI recommend??

To answer this, we just launched the Small Business AI Visibility Index!

Every week, we run a portfolio of prompts across:
- 4 major AI assistants (@ChatGPTapp @GeminiApp @Copilot @perplexity_ai )
- 10 metros (U.S & Canada)
- 5 small business verticals (Restaurants, HVAC, Dental, Med Spas and Gyms)

We analyze over 40,000 responses, and then rank the Most Recommended, and Best Understood.

Link below for the rankings 👇

[Courtyard AI @courtyardai]

Last month Google Cloud published the Open Knowledge Format (OKF), and @Google, @Microsoft @GitHub, @Salesforce, and more) published Agentic Resource Discovery (ARD). Starting today, Courtyard knowledge bases will automatically publish these new standards.

A quick rundown of what they are and what we support.

The problem ARD solves: AI agents can only use tools someone wired up ahead of time. ARD standardizes discovery. A business publishes a machine-readable catalog at /.well-known/ai-catalog.json listing its agentic resources, and agents read it at runtime to find what the business offers and how to use it.

OKF solves the knowledge layer. It's an open format for structuring a business's knowledge as portable markdown with typed frontmatter, so any agent can read it and know what each piece is (pricing, hours, availability).

While these are very early standards, we believe it's important to support, and shape them for how small businesses can participate in agentic discovery.

What we implemented from the standards, and the resources our catalog surfaces:

• MCP server card for the business's knowledge base, with search_knowledge and get_page tools
• agent-skills index that tells an assistant how to use it
• llms.txt and llms-full.txt, the readable map and full text
• the new OKF knowledge bundle
• the ARD catalog itself, which ties the rest together

It's all generated automatically from a knowledge base and stays current as information changes.

[Courtyard AI @courtyardai]

It's been awesome to work with Mindful Rehab, as one of our earliest customers.

Since launching, their company and individual practitioner knowledge bases have been fetched live by ChatGPT over 700 times. Each is part of a real potential customer conversation in AI, where their knowledge base helped shape the answer.

[Courtyard AI @courtyardai]

We built Vine Detect to solve our own need of detecting the long tail of customer-facing commerce software used by small businesses.

Today, we're releasing a beta version of the Vine Detect API to the public!

Takes any business website, then Vine follows its calls-to-action the way a user would and finds the customer-facing software behind it.

OpenTable, Toast, Calendly, etc... plus the exact URL where your agent can act (book, reserve, order, schedule, pay).

Live scans. Not cached fingerprints.

Try it: https://t.co/0ONIiaOjmz
Skill: https://t.co/JLcK0Oqysb

[Sam Pajot-Phipps @sampajotphipps]

Since OpenAI added image search results into the Responses API a few weeks ago, anyone else seeing ChatGPT increasingly bring and suggest images into conversations?

https://t.co/fGscMd9cBf

[Sam Pajot-Phipps @sampajotphipps]

Little update on this experiment, in two weeks:

- Visited 985 times to answer live user questions by ChatGPT (ChatGPT-User traffic)

- Per showtime seat map pages have the most AI assistant visits (177 distinct seat pages visited)

- Ran a sample of 25 relevant prompts across 4 models to see how the new knowledge is being used in responses: ChatGPT citing it in 28% of prompts, Perplexity is 95%, Gemini started at 30% but has dropped off.

- Seeing major AI crawlers return almost every day

As showtimes near, data is refreshed every 15mins and updates pushed for indexing.

[Sam Pajot-Phipps @sampajotphipps]

ChatGPT visited your website 10 times last week. So what? Why?

This is a topic we're constantly exploring at @courtyardai

How are AI assistants using Courtyard knowledge bases?

There are many ways we look at it, but let's start with AI visits. Each knowledge base exists at its own subdomain, hosted by Courtyard so we can track all server traffic.

We break down AI traffic by their known bot identifiers, across three activity categories: live retrieval, indexing and training.

All three work together to paint a picture of AI assistants finding, understanding and then using a knowledge base.

Live retrieval (e.g. ChatGPT-User) is the highest signal that tells us a relevant conversation was happening with an AI assistant that resulted in a live request to the knowledge base to help form an answer. A close AI equivalent of calling the front desk.

However, not all usage of the knowledge base requires a live retrieval. When it's been indexed and cached by AI assistants, answers can use the cached version in which case there is no signal of that interaction, which is a limitation we need to work around with other signals.

Tracking indexing traffic helps us understand what categories in the knowledge base have been discovered and ingested by AI, and looking at frequency tells us how often they come back to see what's new.

Tracking training has fewer short-term benefits, but it provides a signal that this knowledge becomes eligible to be included in future model training. This is important as some answers come from a combination of training data and search. Courtyard knowledge bases often contain new knowledge that was previously inaccessible to AI assistants like availabilities, schedules, and pricing as they were locked behind human web experiences (i.e JS, widgets) or in a desktop folder or email thread. Building awareness that this knowledge is now available for a business into training data could result in better responses in future models.

Later, I'll share how we monitor prompts across models to see how a knowledge base is shaping responses.

[Sam Pajot-Phipps @sampajotphipps]

🚢 New updates to analytics in @courtyardai

- Easily see what AI assistants are visiting your knowledge base to use in training and live responses to your potential customers

- Explore how AI assistants understand your business: we automatically monitor relevant prompts, and see where they are getting their answers from, including your knowledge base

Much more to come on how AI understands your small business, and quick actions to directly address gaps that can cost you customers.

[Courtyard AI @courtyardai]

Today Courtyard AI is officially live!

Ask ChatGPT about your business the way a customer would. "Do they take walk-ins?" "Any gluten-free options?" "What furnace brands do they install?"

Now imagine the assistant answering every one of those perfectly, then sending the customer straight to you.

That's where buying is headed. Over 60% of consumers already use AI assistants somewhere in their buying journey, and soon those assistants won't just answer questions, they'll shortlist businesses, check availability, and book. The businesses that win will be the ones AI knows best.

That's why we built Courtyard AI.

We build a living AI Knowledge Base for your business and make it available to AI assistants like ChatGPT, Claude and Gemini in the variety of formats, standards and locations of how they retrieve knowledge. Everything customers ask about, your facilities, your menu, your services, your pricing, your availability pulled together and kept current automatically. Set it up once, show up everywhere a customer asks.

No new website. Minimal effort. Just your business, made ready for how people search now.

Try it free for 30 days, then as low as $20/month.

Courtyard is live today. Learn more: https://t.co/4YPOIp8Ws5