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

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.

Hacker NewsToolAISource
0Sign in to voteCopy link

FL score

72

out of 100

Verdict

VALIDATE

high confidence

Competition

No competitor data yet

Trend

No signal yet

A diagnostic tool that scores how well AI coding agents can use your product, targeting developer tool makers who need to optimize for agent usability.

The pain

Developer tool companies are shipping products that agents struggle to use, but they have no way to measure or debug the agent experience before launch. They waste time on technical changes that don't matter while missing the real blockers.

The gap

No existing tool measures agent onboarding success or shows you what agents actually see when they try to use your product. Competitors either give noisy generic advice or require manual testing.

Build angle

The founder already built this at Gauge and validated the core insight that homepage, llms.txt, pricing, and docs are the key pages. The tool is live and working. The main work is distribution and expanding the scoring model.

Strengths

  • Founder has direct experience building for agents at Gauge, so the problem is not theoretical.
  • The product is already live and generates concrete, actionable output (not vague recommendations).
  • The tool is agent-native itself, which is a clever distribution angle and proof of concept.
  • The focus on Markdown content negotiation and autonomous onboarding is specific and testable, not generic.
  • The three full coding session traces give users visibility into exactly where agents fail.

Risks

  • The market is narrow. Only developer tools and APIs need this. SaaS companies selling to humans don't care yet.
  • Willingness to pay is uncertain. Companies might use it once, get a score, and not return. Retention could be very low.
  • The trend could reverse. If agents become less important or if companies decide agent-friendliness is not a priority, demand evaporates.
  • Defensibility is weak. Once the scoring criteria are public, competitors can copy the approach or companies can build this in-house.
  • The business model is unclear. Is this a one-time audit, a subscription, or a consulting service? Pricing strategy is not mentioned.
  • Scaling requires keeping the scoring model current as agent capabilities change. This is ongoing work, not a one-time build.
  • The claim that autonomous onboarding will be table stakes in a year is speculative. This could be wrong.

Questions about this idea?

FlyBot reads the scoring and gives you a second opinion on “Ax-check.com – Can agents use your product?”.

Open FlyBot