Credit Cards · August 2026
Mission Lane's llms.txt lists every card while its pages screen readers
An AI agent ran five ordinary credit cards tasks on the public pages of Mission Lane and scored what each page delivered.
Run 6 August 2026 · five tasks · public pages, logged out · Fintech
30/100
Mystery Agent score
Credit Cards · rank 24 of 25
Purchase APR
15Automated reader declined
Card comparison
85Served as text
Pricing and terms
12Automated reader declined
Welcome offer
22Partly served
Application page
15Automated reader declined
Summary
- llms.txt lays out all four Mission Lane Visa cards with annual fee, rewards rate, credit line, and application steps in clean text.
- An agent read a comparison in llms.txt: Gold Line pays 3% on gas and travel, Silver Line pays a flat 1.5%.
- Adding the purchase APR range to llms.txt would close the gap left by pages that sit behind a script challenge.
Task by task
Each task is scored out of 100 on completion, answer quality and how directly the answer was reached. Each note describes what the page delivered, with a link to the page the answer was found on.
Task 01Purchase APRAutomated reader declined15 out of 100
The Gold Line Visa product page and the homepage both answer with a script challenge, while llms.txt lists annual fee and cash-back rate for every card without stating a purchase APR anywhere in its text.
Task 02Card comparisonServed as text85 out of 100
llms.txt serves a complete comparison: Gold Line Visa carries a $0 annual fee with 3% cash back on gas, travel, and dining, while Silver Line Visa pays a flat 1.5% on every purchase for the same fee.
Task 03Pricing and termsAutomated reader declined12 out of 100
The cardholder-agreements page answers with the same script challenge as the rest of the site, and llms.txt covers annual fee and a few named fees per card without a full rates-and-fees schedule or an APR figure.
Task 04Welcome offerPartly served22 out of 100
llms.txt is thorough on card benefits, application steps, and ratings for all four cards, though it carries no mention of a welcome bonus, sign-up offer, or promotional spend requirement for any of them.
Task 05Application pageAutomated reader declined15 out of 100
A plain request to the apply page returns a script challenge whose visible text asks readers to enable JavaScript and cookies, while llms.txt describes the prequalification flow: a soft credit pull followed by a hard pull after acceptance.
llms.txt lays out all four cards side by side with annual fee, rewards rate, starting credit line, and key features.
The application page
What the account opening page states to a reader that runs no scripts.
5,454Bytes delivered
58Characters of visible text
0Form fields in the first response
After scripts runWhat an applicant needs
Strengths and opportunities
What is working
- llms.txt is a genuinely rich agent-facing document. It lays out all four cards side by side with annual fee, rewards rate, starting credit line, and key features, plus the application flow, banking partners, and geographic exclusions, in clean readable text.
- The structural pages an agent checks first, robots.txt and sitemap.xml, both answer cleanly with 200 status and a full, current list of card and legal URLs, showing the site's information architecture even where the pages themselves are gated.
Opportunities
- Publishing the purchase APR range and a rates-and-fees summary in llms.txt would close the single biggest gap in this run, since every HTML page carrying that figure is currently behind a Cloudflare challenge.
- A short, explicit welcome-offer line in llms.txt, even a plain statement that these cards carry no sign-up bonus, would remove ambiguity for any agent comparing offers across issuers.
- Allowing the apply page to serve a minimal static shell describing required information (SSN, income, eligibility) before the JavaScript challenge loads would turn the application application page into a disclosed, informative stop rather than an empty one.
- Since llms.txt already proves the content team can produce agent-readable text, extending that same file to include APR and welcome-offer fields would let Mission Lane's customer-facing programs pass through cleanly on the one channel currently open to agents.
Access
Every page the agent requested was delivered on the first attempt. An llms.txt file is published, which gives agent traffic a documented entry point.
Back to the credit cards leaderboard · Read the report · How the study works
