Agent Access Audit

Your agent is not reading the web you think it is.

It fetches a page, gets a wall or an empty shell, and reports back as if nothing happened. We measure which of your surfaces actually open, which open only for a session a person has already vouched for, and which are closed to you no matter what you do.

Cold browser 857 characters of page structure
SAME URL
SAME MINUTE
SAME MACHINE
Warmed session 124,864 characters of page structure

eBay search results, measured 7 September 2026 and reproduced on a second independent run the same day. One browser started fresh, the way most agent stacks start every run. One carrying a profile a person had verified once, weeks earlier. The agent code was identical. Walmart, measured in the same batch, went from 1,196 characters to 226,307. Nothing in either cold run told the agent it had been shown a wall.

Book an audit or send three URLs and we will measure them free.
The method

Two passes, no guessing, no model in the loop.

Every surface is loaded twice. Once in a browser profile created fresh for that request, which is what almost every agent stack does by default. Once in a long-lived profile that has been through any human verification a single time. What gets recorded is the accessibility tree the browser exposes, the same structure a screen reader reads, plus any block signal the page raises.

No language model touches the verdict. That matters for three reasons: a run costs nothing to repeat, it returns the same answer twice, and there is nothing in the pipeline that can invent a finding. Every tree we captured ships with the report, so any line in it can be checked against what the browser actually saw.

When a pass fails for our reasons rather than the site's, we retry, and if it still fails we mark the surface no verdict and say so. A tool timeout is not evidence that a site refused you.

What comes back

Every surface lands in one of these.

OPEN

Reads fine on a cold browser. No session, no negotiation.

Nothing to do. Re-test on a schedule.
SESSION DEPENDENT

Empty or blocked cold, fully readable once the browser carries a human-verified session.

Fixable this week. Usually the largest single recovery.
IDENTITY REQUIRED

Bot detection refuses you on every profile tried. No amount of session warming changes it.

Get admitted: the site's API, an allowlist entry, or a signed agent identity.
LOGIN REQUIRED

An account wall stands in front of the content on every profile.

Provision a real account, warm it once by hand, read the terms first.
DEGRADED

Loads, but returns little structure. The content is behind an interaction your agent never performs.

Script the interaction, or find the feed.
UNSTABLE

Passed on one profile and failed on another. The site's posture toward you is not settled.

Re-run, then retire the flagged profile.
Published measurements

We publish the boring results too.

Every battery we run goes up dated, including the ones that make no case for hiring us. A benchmark you only publish when it flatters you is marketing, and nobody should trust a number from it.

Retail, 7 Sep 2026
Ten retail and marketplace sites. Three need a human-warmed session, three refuse outright, three are open, one was inconclusive and is reported as inconclusive rather than guessed at. Walmart showed a press-and-hold wall cold and returned 226,307 characters warm. Home Depot refuses on every profile while returning a page that says "Oops!! Something went wrong", which an agent reads as a retryable blip rather than a refusal.
Procurement, 7 Sep 2026
Ten US state procurement portals. Seven open, three degraded, none blocked, none session dependent. We expected to find pain here and did not. Public bid portals exist to be read, and it shows. If you sell into govcon, access is not your problem.
Why now

The web started sorting agents into categories.

If your targets are ad-free B2B sites, that particular change is close to a no-op, and we will tell you so rather than sell you a fire. The reason it matters is narrower and more durable: Agent is now a category that sites write policy about. Cloudflare, AWS, Akamai and HUMAN Security are shipping cryptographic agent identity under the IETF's Web Bot Auth work, and a signed agent that a site has chosen to admit skips the challenge entirely.

Which means the question stops being how well your agent blends in, and starts being whether the sites you depend on know who you are and have decided to let you through. Most teams cannot answer that for their own top twenty surfaces. That is the gap this audit closes.

The boundary

What we will not sell you.

Getting you past the wall

We do not build fingerprint spoofing, we do not automate press-and-hold challenges, and we do not resell CAPTCHA-solving farms. That work violates the terms of the sites you are hitting, it puts your payment processing and your legal exposure somewhere you do not want them, and it decays every time a detection vendor ships.

Getting you let through the door

Real sessions that persist. Accounts provisioned and warmed properly. Official APIs and data feeds where they exist. Allowlist requests to the sites that matter most. Signed agent identity where the site supports it. Slower to set up, and it still works next quarter.

This is not posturing. If your access problem can only be solved by pretending not to be a bot, the honest answer is that you do not have an access problem, you have a business-model problem, and we will say that in the readout.

Deliverables

What you actually get.

Verdict matrix
Every surface, cold and warm, with the character count the browser returned and the block signal if there was one.
Evidence bundle
The raw accessibility tree captured for each pass. You can re-read exactly what the browser saw and check any verdict yourself.
Remediation plan
Grouped by verdict, ordered by how much access each fix recovers, with the ones your team can ship this week called out separately.
The runner
The harness itself, so you can re-run the audit yourself whenever you change stacks or add a target. It is yours; there is nothing to keep paying for.
Readout
Sixty minutes with whoever owns the agent, walking the findings and the order to do them in.
Engagements

Pricing.

Probe

Free
  • Up to 3 surfaces you name
  • Cold and warm pass on each
  • Results emailed, no call

So you can check whether any of this is real before paying for it.

Audit

$4,500
  • Up to 25 surfaces
  • Full verdict matrix and evidence bundle
  • Remediation plan, ordered by recovery
  • The runner, yours to keep
  • Sixty-minute readout

Two weeks from kickoff.

Watch

$900 / month
  • Monthly re-run of your matrix
  • Alert when a surface changes posture
  • Quarterly review

Sites change without telling anyone. Most teams find out when a pipeline goes quiet.

Start

Send three URLs.

Name three surfaces your agent depends on. We will run both passes against them and send back what the browser actually saw, whether or not it makes a case for hiring us. If all three come back open, that is a useful thing to know and it costs you nothing.