I'm the co-founder of Gauge, and I built ax-check.com to quickly test how well coding agents can onboard to your product.
You'll get a scorecard, specific suggested fixes, and three full coding sessions that show how agents read your site and use your product.
I built this because similar checks were too noisy. Most suggested obscure technical changes that don't actually make a difference in agent experience (or AX, hence ax-check.com).
This check starts by using DeepSeek 4.1 Flash to try to find key information about your product, starting from the homepage. In actual agent traffic data, we've seen that the key pages are the homepage, llms.txt, pricing, and the docs site (by traffic volume, and by influence), so we focus on those and ignore the rest. We also find that content negotiation for Markdown is legitimately helpful for agents to complete tasks faster and find what they're looking for, so the scan tests that your key pages can serve Markdown.
The other key piece is that we run actual coding agents in sandboxes, and have them try to onboard to your product. You can see the full trace and watch it happen live (we kick it off fresh when you enter a new site). We surface interesting findings like hallucinated URLs, inaccurate docs instructions, or product confusion.
It also detects whether the agents could complete a fully working onboarding autonomously, without being blocked by a login wall. This is still controversial, but I think finding ways to let agents safely onboard autonomously is going to be table stakes within a year for developer tools in particular.
The whole site is agent-friendly itself! You can generally just talk to your coding agent about ax-check.com and it can do the rest. Would really appreciate any feedback to make this useful.
Behind an agent is a human that might use the product. I think customers/consumers will demand that their personal/subscription agent can access the product.
As someone that works for a company that gets a 100% score on ax-check, all the effort I've put into making it accessible for agents has not 10xed the growth numbers like I was told it would.
The Ai growth looks more like the very-long-term 2% (technically productivity growth from innovation), avoid assuming the hypesters are even close to accurate in their predictions
I've heard CTOs saying they don't consider buying any product that is not AI agent friendly. Which means they must come with AI skills, MCP Servers and so on that agents can use it to do stuff. You may not like it, but that's almost certainly going to be the future.
Agents are the new search engine - a majority of people are starting to get recommendations and answers from them. So asking this is like asking "what is the benefit of making any resource more available to search engines?"
The answer is discoverability. which is pretty critical for any business
agents are becoming the de facto standard interface for everything, whether you like it or not, so it depends on the intent you have for a project, or "product" as OP phrased it, which has a more contextual implication that the intent is to get others to buy it
ironically, I did sell a kirby many many years ago
the idea is likely way more about business purchases and SaaS than consumer products, though I did have an agent do deep research to give me options when deciding on a new mattress
This is an awesome idea. I use agents all the time that way, so am not thrilled by potential consequences, but I love the idea from the platfroms' perspective.
The initial step of the scan looks at homepage content to try to figure out where to navigate next, it's getting confused by all the different products linked. Will fix this!
The mcp audit at https://anc.dev/ covers all flavors of mcp, including the recently launched webmcp. Remediation prompts, accessible equally by agents and humans, can help close any gaps. Usually one-shot, unless your site is crazy complicated.
How do you think about enabling fully agentic onboarding without proper human identification? It feels like any rate limiting would be pretty easy to get around.
Each product is different (how much does it cost to serve a marginal user, how risky is it). But generally I think allowing ephemeral accounts like Cloudflare, or serving simulated/static accounts before a human claim can both work.
For a lot of products it can just be an extension of the free tier I think too.
which URL is it? it's kind of a deep assumption since we're evaluating on ease-of-navigation from the homepage, and looking for /llms.txt etc. but there should be a way for me to add support
Integrating live bots to demonstrate live visitor experiences is a nice touch. I got an unexpected blocker (`Default Python urllib User-Agent gets 403'd by anc.dev`) I am not able to reproduce yet. Can you expose the scripts that the agents generate?
I took a different route with https://anc.dev (scored 100 on ax-check) and rely on a wider variety of compliance tests. Beyond websites, it also audits binaries (think CLI tooling) to help inclined developers ensure their tools are discoverable by and useful to agentic systems.
In this case (https://agents.withgauge.com/p/runs/40be763c-4678-4677-88df-...) the agent wrote a python script to test the site, and hit the error above. We don't have a full filesystem diff viewer in ax-check.com, although we do have that in the Gauge agents product itself.
Interesting, thank you. I'll check whether a setting on CF might be interfering. The site checks headers for routing and response types, but it shouldn't affect access.
Rapidcam.app is a CAD / CAM for CNC and laser. The file format is designed for LLMs and for version control. The app has a in-built prompt generator and solver so you can use your own LLM.
You'll get a scorecard, specific suggested fixes, and three full coding sessions that show how agents read your site and use your product.
I built this because similar checks were too noisy. Most suggested obscure technical changes that don't actually make a difference in agent experience (or AX, hence ax-check.com).
This check starts by using DeepSeek 4.1 Flash to try to find key information about your product, starting from the homepage. In actual agent traffic data, we've seen that the key pages are the homepage, llms.txt, pricing, and the docs site (by traffic volume, and by influence), so we focus on those and ignore the rest. We also find that content negotiation for Markdown is legitimately helpful for agents to complete tasks faster and find what they're looking for, so the scan tests that your key pages can serve Markdown.
The other key piece is that we run actual coding agents in sandboxes, and have them try to onboard to your product. You can see the full trace and watch it happen live (we kick it off fresh when you enter a new site). We surface interesting findings like hallucinated URLs, inaccurate docs instructions, or product confusion.
It also detects whether the agents could complete a fully working onboarding autonomously, without being blocked by a login wall. This is still controversial, but I think finding ways to let agents safely onboard autonomously is going to be table stakes within a year for developer tools in particular.
The whole site is agent-friendly itself! You can generally just talk to your coding agent about ax-check.com and it can do the rest. Would really appreciate any feedback to make this useful.
Nice! This should help in making my stuff as inaccessible as possible to agents.
Are you mainly concerned about scraping? or anti-agents in general?
what is the benefit of making any resource more available to agents?
Behind an agent is a human that might use the product. I think customers/consumers will demand that their personal/subscription agent can access the product.
As someone that works for a company that gets a 100% score on ax-check, all the effort I've put into making it accessible for agents has not 10xed the growth numbers like I was told it would.
The Ai growth looks more like the very-long-term 2% (technically productivity growth from innovation), avoid assuming the hypesters are even close to accurate in their predictions
yeah, it looks more like parasitic exponetials, the same way when google started being the source for things instead of the portal.
No ones shown there's any real ROI in a more virulent intermediary that has even less reason to view ads.
Good riddance?
Very happy to have my agent totally ignore the ads trying to hijack my attention.
I've heard CTOs saying they don't consider buying any product that is not AI agent friendly. Which means they must come with AI skills, MCP Servers and so on that agents can use it to do stuff. You may not like it, but that's almost certainly going to be the future.
Agents are the new search engine - a majority of people are starting to get recommendations and answers from them. So asking this is like asking "what is the benefit of making any resource more available to search engines?"
The answer is discoverability. which is pretty critical for any business
ok smart guy. We live in a society.
Your answer presents one side of an equation.
agents are becoming the de facto standard interface for everything, whether you like it or not, so it depends on the intent you have for a project, or "product" as OP phrased it, which has a more contextual implication that the intent is to get others to buy it
ok, great, you think an agent is going to buy your vacuum.
How many of you guys are selling vacuums? ...
ironically, I did sell a kirby many many years ago
the idea is likely way more about business purchases and SaaS than consumer products, though I did have an agent do deep research to give me options when deciding on a new mattress
+1
This seems like a good way to get hammered by tons of extra requests because agents can't efficiently figure out your site...
I've been working on https://switchfrog.com to help you with that :)
This is an awesome idea. I use agents all the time that way, so am not thrilled by potential consequences, but I love the idea from the platfroms' perspective.
https://news.ycombinator.com/ Gets an A grade for pricing… where is the pricing page again?
The initial step of the scan looks at homepage content to try to figure out where to navigate next, it's getting confused by all the different products linked. Will fix this!
Going to try this out for our MCP
The mcp audit at https://anc.dev/ covers all flavors of mcp, including the recently launched webmcp. Remediation prompts, accessible equally by agents and humans, can help close any gaps. Usually one-shot, unless your site is crazy complicated.
How do you think about enabling fully agentic onboarding without proper human identification? It feels like any rate limiting would be pretty easy to get around.
Each product is different (how much does it cost to serve a marginal user, how risky is it). But generally I think allowing ephemeral accounts like Cloudflare, or serving simulated/static accounts before a human claim can both work.
For a lot of products it can just be an extension of the free tier I think too.
I've been seeing these pop up recently, I think I saw Mintlify launched one too. Why the sudden increase in attention towards coding agents?
Welcome to HN...
Claude, use AX-check to make my site score a zero. Make no mistakes
it wants a whole domain when the interesting thing i want it to try lives in a directory
which URL is it? it's kind of a deep assumption since we're evaluating on ease-of-navigation from the homepage, and looking for /llms.txt etc. but there should be a way for me to add support
https://www.ax-check.com/curl.se fun
Integrating live bots to demonstrate live visitor experiences is a nice touch. I got an unexpected blocker (`Default Python urllib User-Agent gets 403'd by anc.dev`) I am not able to reproduce yet. Can you expose the scripts that the agents generate?
I took a different route with https://anc.dev (scored 100 on ax-check) and rely on a wider variety of compliance tests. Beyond websites, it also audits binaries (think CLI tooling) to help inclined developers ensure their tools are discoverable by and useful to agentic systems.
You can reproduce that finding directly from python:
```
[...traceback info...]
urllib.error.HTTPError: HTTP Error 403: Forbidden
```
In this case (https://agents.withgauge.com/p/runs/40be763c-4678-4677-88df-...) the agent wrote a python script to test the site, and hit the error above. We don't have a full filesystem diff viewer in ax-check.com, although we do have that in the Gauge agents product itself.
Interesting, thank you. I'll check whether a setting on CF might be interfering. The site checks headers for routing and response types, but it shouldn't affect access.
Rapidcam.app is a CAD / CAM for CNC and laser. The file format is designed for LLMs and for version control. The app has a in-built prompt generator and solver so you can use your own LLM.