Hacker News

Top stories

Live mirror
30 storiesupdated just nowView source snapshot
  1. Android 17 is the first since 3.x to add new APIs without releasing to the AOSP(grapheneos.social ↗)
    105comments
  2. Cloudflare Quick Tunnels(cloudflare.com ↗)
    197comments
  3. Saving another 100TB of RAM(cloudflare.com ↗)
    15comments
  4. Xcode 27.1 Beta Release Notes(developer.apple.com ↗)
    39comments
  5. Cache-to-Cache: Direct Semantic Communication Between LLMs (2025)(arxiv.org ↗)
    8comments
  6. Photon-Emission-Guided Laser Fault Injection Enables RP2350 Secure Debug(ledger.com ↗)
    36comments
  7. Show HN: Cactus Needle 3: 8-29MB automation models can match DeepSeek V4 Flash(cactuscompute.com ↗)
    62comments
  8. How to Write with an LLM(sockpuppet.org ↗)
    215comments
  9. The Implications of Linguistic Illegibility for LLM Security(arxiv.org ↗)
    12comments
  10. OpenJev(openjev.com ↗)
    234comments
  11. C++26: Trivial infinite loops are no longer undefined behaviour(sandordargo.com ↗)
    142comments
  12. Korea raises data breach fines to 10% of revenue(koreajoongangdaily.com ↗)
    40comments
  13. Border agents can search cellphones without a warrant or reasonable suspicion(lawandcrime.com ↗)
    78comments
  14. The first new cat species discovered in 100 years(nationalgeographic.com ↗)
    19comments
  15. Our brain evolved from two primitive nervous systems that merged: Study(newscientist.com ↗)
    40comments
  16. I vibed a proof of Conway's conjecture(overreacted.io ↗)
    167comments
  17. How SpaceX streamlined the Raptor engine(construction-physics.com ↗)
    14comments
  18. A search-and-inference database from scratch in pure Zig(antfly.io ↗)
    10comments
  19. Minimal Phone 2(minimalcompany.com ↗)
    113comments
  20. Inside ZCode: Silently uploading your Git history to the cloud(ferstar.org ↗)
    84comments
  21. North Korean nuclear test sets off years of earthquakes(science.org ↗)
    138comments
  22. Warez: The Infrastructure and Aesthetics of Piracy (2021)(archive.org ↗)
    8comments
  23. Cekura (YC F24) Is Hiring(ycombinator.com ↗)
    discuss
  24. From Geometry to Algebra and Back Again: 4000 Years of Papers (2023) [video](youtube.com ↗)
    discuss
  25. Show HN: Ax-check.com – Can agents use your product?(ax-check.com ↗)
    23comments
  26. US Military had close call after using AI for hallucinated intelligence report(cnn.com ↗)
    232comments
  27. Mathematicians Build Long-Awaited Graph Sandwich(quantamagazine.org ↗)
    16comments
  28. Show HN: Scry, programmable internet search w/ congestion pricing(scry.io ↗)
    16comments
  29. Jemalloc 5.4.0(github.com/jemalloc ↗)
    85comments
  30. The scourge of x86 emulation(fex-emu.com ↗)
    74comments

Show HN: Ax-check.com – Can agents use your product?

23 pointsby 1d agoax-check.com
23 comments
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.

2h agoHN ↗

Nice! This should help in making my stuff as inaccessible as possible to agents.

2h agoHN ↗

Are you mainly concerned about scraping? or anti-agents in general?

2h agoHN ↗

what is the benefit of making any resource more available to agents?

2h agoHN ↗

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.

2h agoHN ↗

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.

51m agoHN ↗

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

1h agoHN ↗

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.

53m agoHN ↗

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

53m agoHN ↗

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

30m agoHN ↗

This seems like a good way to get hammered by tons of extra requests because agents can't efficiently figure out your site...

2h agoHN ↗

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!

2h agoHN ↗

Going to try this out for our MCP

2h agoHN ↗

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.

2h agoHN ↗

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.

2h agoHN ↗

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?

1h agoHN ↗

Claude, use AX-check to make my site score a zero. Make no mistakes

1h agoHN ↗

it wants a whole domain when the interesting thing i want it to try lives in a directory

51m agoHN ↗

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