VOL. 01 · ISSUE 03 · AI SCRAPING RECONNAISSANCE EST. 2026 · INVITE-ONLY BETA · 12 SPOTS REMAINING

The end of reverse-engineering websites by hand.

A two-minute browse is enough.

browser-recon is an AI agent for scraping reconnaissance. You browse a target site like a human; the agent watches; it returns a production-grade scraping plan — recommended library, headers, cookies, rate-limits, cost, and a runnable starter script.

Join the waitlist Read the guide
01

From three days to ten minutes.

Cuts the reconnaissance phase from a multi-day reverse-engineering exercise to a single coffee break.

02

Measured. Not guessed.

Every recommendation is grounded in real test requests through real proxies — not in the LLM's priors.

03

Runnable, not advisory.

Output isn't a paragraph of guidance. It's working Python you drop into your stack.

Tested against the protections of
Walmart
Staples
Target
Airbnb
Ticketmaster
CoinMarketCap
In three movements

The process, distilled.

Three commands separate you from a working scraper. Each builds on the last; together they replace several days of manual reverse-engineering.

i.

Install the agent

One line in your terminal: pipx install browser-recon. The CLI weighs 128 KB. No proprietary code lives on your machine.

ii.

Browse the target

Chrome opens. You click through what matters — a search result, a product detail, a review listing. Two or three minutes is usually enough.

iii.

Receive the report

The agent fires test requests against the site, validates the working approach, and returns a report with the recommended library, headers, cookies, rate-limits and starter code.

A measurement-first agent

Most scraping advice is a guess.

Ours is a measurement.

Open any "how to scrape X" tutorial and you'll see the same shape: install a library, copy these headers, hope for the best. When it breaks in production — and it usually does — you're left debugging Akamai's challenge cookies by hand.

browser-recon doesn't write tutorials. It does the experiment for you: fires the requests through real proxies, sees which combination the live site actually accepts, and reports the answer. The recommendation is grounded in what worked, not in what the model expected to work.

We can't tell you exactly how the agent reaches its conclusions — that's our IP. What we can tell you is what comes out the other end.

01 / Detection

Anti-bot fingerprinting

Identifies Cloudflare, Akamai Bot Manager, PerimeterX, DataDome, Imperva — and what each one will do to a naive scraper.

02 / Validation

Real test requests, real proxies

The agent fires HTTP requests against the target through the proxy tiers you'd use in production, then reports which library × proxy combination actually returned the data.

03 / Cost projection

A real dollar figure per 1,000 requests

Measured bandwidth × your proxy rate. Not a vague band; a number tied to data the agent saw.

04 / Starter code

A scraper you can run today

The report ends with a Python script using the recommended library, headers, cookies and timing. Drop it in and it works.

Dashboard

A working archive.

Every scan, every report, kept for the life of your plan.

browser-recon · dashboard
Pro plan

Recent scans

23 / 30 credits · renews May 30
CREDITS
23  / 30
SCANS THIS MONTH
7
SUCCESS RATE
88%  over 30 days
walmart.com
curl_cffi · chrome120 · residential
complete 7 / 9 matched $0.84 / 1k view →
staples.com
requests · datacenter
complete 9 / 9 matched $0.05 / 1k view →
ticketmaster.com
curl_cffi · safari17 · residential
replay 22% 2 / 9 matched $1.21 / 1k view →
A report

Verdict, evidence, code.

Every report opens with the recommendation. The rest of the page is the evidence behind it.

browser-recon · report · walmart.com
scan 9e602c15
VERDICT · 2026-05-13

walmart.com runs dual Akamai + PerimeterX. curl_cffi with chrome120 + residential proxies reproduces the captured data.

"Cookie warmup required before the Reviews GraphQL endpoint will respond. Estimated cost is $0.40–$2.00 per 1,000 requests. Confidence: 0.82."

Library
curl_cffi
Impersonation
chrome120
Proxy tier
residential
Cost / 1k
$0.84
The terms

Pay for what you scan. Nothing else.

Credits expire monthly. Reports stay live for the duration of your tier. Re-scan for one credit to refresh.

FIRST MONTH ONLY
Tester
$5 /mo
USD · MONTHLY
5 credits
  • 5 scans / month
  • Reports kept 2 weeks
  • Email support
  • One-time signup only
Join the list
Beginner
$10 /mo
USD · MONTHLY
12 credits
  • 12 scans / month
  • Reports kept 1 month
  • Email support
Join the list
Pro Max
$60 /mo
USD · MONTHLY
100 credits
  • 100 scans / month
  • Reports kept 3 months
  • Priority queue
  • Slack support
Join the list
Higher volume, a custom report shape, or scraping code generated for your framework? Talk to us about Enterprise →
An invitation

Get on the list. Skip it with a tweet.

A small batch in each week — drop your email, or post about us on X and we'll let you in next.

  247 developers in line · 12 spots opening this week