Chase UK

Name: Chase UK AI agent readiness scorecard
Item: Chase UK
Rating: 67.6
Author: Stunt Double

Effortlessly manage your spending, savings and investments – all through the Chase app.

chase.co.uk
MarketGB
Localeen-GB

Agent score27.4

/100OK

Claim this domain

RankRank: Top 85%; #468
Finance rankFinance rank: Sector average 79.6; #50
Benchmark runsBenchmark runs: 3 providersAcross 3 providers; 4

Where this site sits

Finance avg: 79.6 (−12.0)
Market avg: 76.7 (−9.1)

Latest results

Chase UK ranks #468 of 550 scored sites, up 64 places since the last run.

Trend-13.1Since 14 May 2026, across 3 runs.Best agent100.0 ExcellentClaude. Gemini trails at 100.0.Agent friction14improvements2 high severity. Most serious: No discoverable MCP server. Agents and AI clients have no way to discover one automatically.Technical readiness51/1005 of 8 essential checks failing.Checks by Is Agentic

This site
Finance
Market

Table view

Run	This site	Finance median	Market median
12 Oct 2026	67.6	81.0	79.8
28 Sept 2026	40.2	80.1	76.4
14 May 2026	80.7	80.5	82.0

Monthly medians. Dates in UTC.

Performance

Site checks, then AI agents on real tasks.

Methodology

Automated checks probe the site before any agent runs. They count for 40% of each category. Strongest is Information retrieval at 85.0, weakest is Delegated access at 17.0.

Site checks by category

Brand awareness: 70.0
Discovery: 51.0
Information retrieval: 85.0
Market ranking: 35.0
Accuracy: 85.0
Task completion: 60.0
Delegated access: 17.0
Contact & communication: 50.0

01 Site checks

Agent readiness checks

Essential: 41.7/80
Recommended: 7.8/20
Checks passing: 8/24

OpenAPI spec publishedEssential
JSON error responsesEssential
Markdown content negotiation (acceptmarkdown.com)Essential
Brand name discoverabilityRecommended
Public API/docs linked from homepageRecommended

02 Agent sessions

Brand awareness

Brand awareness
16s
96median 93
Brand awareness
25s
98median 93
Brand awareness
44s
94median 93

Discovery

Discovery
28s
49median 73
Discovery
1m 48s
26median 73
Discovery
2m 18s
36median 73

Information retrieval

Information retrieval
21s
43median 60
Information retrieval
1m 55s
62median 60
Information retrieval
2m 34s
32median 60

Market ranking

Market ranking
27s
43median 65
Market ranking
41s
60median 65
Market ranking
58s
60median 65

Accuracy

Accuracy
17s
94median 87
Accuracy
1m 7s
93median 87
Accuracy
2m 17s
36median 87

Task completion

Task completion
19s
43median 90
Task completion
1m 22s
43median 90

Delegated access

Find the developer or API documentation.
Found the API documentation (40pts). Correctly identified the auth model (API key, OAuth, none) (40pts). Named any specific scopes or endpoints available (20pts). Deduct 20pts if no API is available but that is the correct answer.
2m 55s
36median 67

Contact & communication

Find how to request a return and what the eligibility conditions are (timeframe, item condition, exceptions).
Found the path to initiate a return (50pts). Extracted the eligibility conditions including timeframe and any exceptions (50pts). Deduct 20pts for each dead end or missing condition.
48s
36median 80
Find how to request a return and what the eligibility conditions are (timeframe, item condition, exceptions).
Found the path to initiate a return (50pts). Extracted the eligibility conditions including timeframe and any exceptions (50pts). Deduct 20pts for each dead end or missing condition.
3m 1s
21median 80

03 Blend

Agents 60%
Checks 40%

One kind of evidence only? That kind counts in full.

Brand awareness10% of the overall
0.4 × 70.0 + 0.6 × 92.0 = 83.2 raw
83.2 raw → 92.1 published
Discovery15% of the overall
0.4 × 51.0 + 0.6 × 11.7 = 27.4 raw
27.4 raw → 55.8 published
Information retrieval15% of the overall
0.4 × 85.0 + 0.6 × 19.3 = 45.6 raw
45.6 raw → 70.2 published
Market ranking10% of the overall
0.4 × 35.0 + 0.6 × 26.3 = 29.8 raw
29.8 raw → 58.0 published
Accuracy15% of the overall
0.4 × 85.0 + 0.6 × 61.0 = 70.6 raw
70.6 raw → 85.5 published
Task completion20% of the overall
0.4 × 60.0 + 0.6 × 15.0 = 33.0 raw
33.0 raw → 60.7 published
Delegated access10% of the overall
0.4 × 17.0 + 0.6 × 10.0 = 12.8 raw
12.8 raw → 39.7 published
Contact & communication5% of the overall
0.4 × 50.0 + 0.6 × 6.5 = 23.9 raw
23.9 raw → 52.5 published

Category	Weight	Checks	Sessions	Blend	Benchmarked
Brand awareness	10%	70.0	92.0	83.2	92.1
Discovery	15%	51.0	11.7	27.4	55.8
Information retrieval	15%	85.0	19.3	45.6	70.2
Market ranking	10%	35.0	26.3	29.8	58.0
Accuracy	15%	85.0	61.0	70.6	85.5
Task completion	20%	60.0	15.0	33.0	60.7
Delegated access	10%	17.0	10.0	12.8	39.7
Contact & communication	5%	50.0	6.5	23.9	52.5
Overall	100%			~41.9	67.6

04 Benchmarked score

41.9 raw → 67.6

Final score is calibrated and adjusted to better reflect the actual performance and benchmark.

Overall 67.6, from 41.9 raw points.

Agents

Each agent’s score over 30 days, and how its latest sessions went.

Claude
Latest run average
63.5
Finance median
100.0
Sessions
- Brand awareness
  16s
  96median 93
- Discovery
  28s
  49median 73
- Information retrieval
  21s
  43median 60
- Market ranking
  27s
  43median 65
- Accuracy
  17s
  94median 87
- Task completion
  19s
  43median 90
- Contact & communication
  Find how to request a return and what the eligibility conditions are (timeframe, item condition, exceptions).
  Found the path to initiate a return (50pts). Extracted the eligibility conditions including timeframe and any exceptions (50pts). Deduct 20pts for each dead end or missing condition.
  48s
  36median 80
ChatGPT Agent
Latest run average
69.6
Finance median
100.0
Sessions
- Brand awareness
  25s
  98median 93
- Discovery
  1m 48s
  26median 73
- Information retrieval
  1m 55s
  62median 60
- Market ranking
  41s
  60median 65
- Accuracy
  1m 7s
  93median 87
- Task completion
  1m 22s
  43median 90
Gemini
Latest run average
51.6
Finance median
100.0
Sessions
- Brand awareness
  44s
  94median 93
- Discovery
  2m 18s
  36median 73
- Information retrieval
  2m 34s
  32median 60
- Market ranking
  58s
  60median 65
- Accuracy
  2m 17s
  36median 87
- Delegated access
  Find the developer or API documentation.
  Found the API documentation (40pts). Correctly identified the auth model (API key, OAuth, none) (40pts). Named any specific scopes or endpoints available (20pts). Deduct 20pts if no API is available but that is the correct answer.
  2m 55s
  36median 67
- Contact & communication
  Find how to request a return and what the eligibility conditions are (timeframe, item condition, exceptions).
  Found the path to initiate a return (50pts). Extracted the eligibility conditions including timeframe and any exceptions (50pts). Deduct 20pts for each dead end or missing condition.
  3m 1s
  21median 80

Excellent85+
Good72-84
OK58-71
Poor40-57
Critical<40

Latest run 12 Oct 2026 (UTC). Sign in to request a re-run, once a day.

Potential improvements

Fix where agents got stuck, then lift your biggest categories.

HighDelegated access

No discoverable MCP server. Agents and AI clients have no way to discover one automatically.

Biggest wins

Projected

Lifting Task completion to Good adds about +2.2 on its own, taking the overall from 67.6 to 69.8.

Raise Task completion from 60.7 to 72 (Good) to add about 2.2 to the overall score.
Raise Market ranking from 58.0 to 72 (Good) to add about 1.3 to the overall score.
Raise Discovery from 55.8 to 58 (OK) to add about 0.3 to the overall score.

Each gain assumes only that category improves. Fix several and the total lands a little under their sum.

Where agents get stuck

14 improvements from the latest run, 2 of them high severity.

High: 2
Medium: 9
Low: 3

HighDelegated access
No discoverable MCP server. Agents and AI clients have no way to discover one automatically.
HighDelegated access
No discoverable public API docs. Agents and AI clients have no way to discover them automatically.
MediumBrand awareness
No Organization JSON-LD. Agents can’t tell who owns the site at a glance.

11 more, and the evidence for each

Want to find these in your own flows before an agent does? Read how to test your product for AI agent users.

Technical readiness

5 of 8 essential checks fail. These are the files and signals agents read before they act.

Checks by Is Agentic

Score

51/ 100

Important blockers remain

Essential: 3 of 8 pass
Recommended: 5 of 16 pass
Bonus: +1.9 from 8 positive signals

Investigate

OpenAPI spec publishedessential

Investigate

JSON error responsesessential

Investigate

Markdown content negotiation (acceptmarkdown.com)essential

24 checks · scanned 9 Oct 2026

Technical readiness

Protocol baseline by Is Agentic

Score: 51/ 100; Important blockers remain
Essential: 41.7/ 80; 3 of 8 passing
Recommended: 7.8/ 20; 5 of 16 passing
Bonus: +1.9; 8 positive signals

Investigate

OpenAPI spec publishedessential

No OpenAPI/Swagger specification found

Fix: Publish an OpenAPI (Swagger) specification at /openapi.json or /api/openapi.yaml. This is how agents understand your API surface automatically.

Investigate

JSON error responsesessential

API does not return JSON error responses (or no API detected)

Fix: Return structured JSON error responses with error codes, messages, and resolution hints. Agents can't parse HTML error pages.

Investigate

Markdown content negotiation (acceptmarkdown.com)essential

Homepage https://chase.co.uk does not meet the Markdown negotiation requirements: Accept: text/markdown returned text/html; charset=utf-8; Vary header missing Accept (got "accept-encoding")

Fix: Enable Markdown negotiation on the scanned homepage. Supporting it only on /docs or a separate .md URL does not satisfy this check. Requests with Accept: text/markdown must receive a nonempty Markdown body with Content-Type: text/markdown and Vary: Accept. Keep serving HTML for Accept: text/html. Adding Vary alone does not create a Markdown response. Verify both with `curl -sS -L -i -H 'Accept: text/markdown' https://yourdomain.com/` and `curl -sS -L -i -H 'Accept: text/html' https://yourdomain.com/`. Check the final response headers and body: Markdown with Vary: Accept for the first request, HTML for the second.

Investigate

Brand name discoverabilityrecommended

chase.co.uk was not in the top 10 for "public_website" (searched your brand name alone: no main product term from your homepage qualified)

Fix: Make sure your own domain ranks in the top results when people search your brand together with your main product (for example "Acme payments API"). If it does not, your brand may be too generic, conflict with a more established term, or not yet indexed. Strengthen it by describing your main product clearly in your homepage title and headings, earning press mentions that link to your domain, and avoiding redirect chains that mask your main domain in search results.

Investigate

Public API/docs linked from homepagerecommended

No public API or documentation page linked from homepage

Fix: Publish API documentation at a discoverable URL (/docs, /api, /developers). Include authentication, endpoints, and example requests.

Investigate

Agent instruction / when-to-userecommended

No agent instruction file with when-to-use guidance found

Fix: Tell agents when to reach for you: add a 'when to use this' section to your llms.txt (or a dedicated agent-instructions file) that names your best-fit use cases and how an agent should call you. Be specific about the jobs you are right for - generic marketing copy does not read as guidance.

Investigate

Rate limit response headersrecommended

GraphQL introspection auth-gated and no header convention documented on GraphQL-tagged pages

Fix: Return standard rate-limit headers on your API responses (the RFC RateLimit headers, plus Retry-After on a 429) so agents can self-throttle in real time, and document the conventions alongside your API.

Investigate

API schema complexity analysisrecommended

GraphQL: introspection auth-gated and no schema evidence in docs

Fix: Make your API spec self-describing: a unique operationId and a description on every operation, typed parameters, and response schemas. For GraphQL, a fully typed schema with a documented cost or rate limit reads best.

Investigate

Function calling compatibilityrecommended

No API spec found - function calling requires discoverable endpoints

Fix: Ensure API endpoints have unique operation IDs, typed schemas, and descriptions compatible with LLM function-calling formats.

Investigate

Sitemap existsrecommended

No sitemap found

Fix: Add a valid XML sitemap at /sitemap.xml listing all indexable URLs. Include lastmod dates and keep it under 50MB.

Investigate

Organization schema completenessrecommended

No Organization type found in JSON-LD

Fix: Add Organization JSON-LD that includes both contactPoint (with email/phone and contactType) and address (PostalAddress). This lets AI verify your business legitimacy and answer contact queries.

Partial

Agent-friendly 404sessential

The nonexistent path https://chase.co.uk/__ora-404-probe-2c1pajk8 correctly returns HTTP 404. Partial credit: no Markdown error body was detected.

Fix: Keep the correct HTTP 404 status. The remaining requirement is a Markdown error body when agents request Accept: text/markdown. Include at least 20 characters explaining the error and a link to your docs, sitemap, or llms.txt. Verify with `curl -sS -L -i -H 'Accept: text/markdown' https://yourdomain.com/some-path-that-does-not-exist`. Check both the final 404 status and the Markdown body with Content-Type: text/markdown. Checking the status alone does not verify the missing requirement.

Partial

Content without JavaScriptessential

2522 chars with H1, but 2.1% content ratio is below the 5% target

Fix: Serve at least 500 characters of meaningful homepage content in raw HTML. Add a clear H1, keep deeper heading levels sequential, and remove excessive non-content markup.

Partial

JSON-LD structured datarecommended

JSON-LD found (1 block(s)) but no identity type - use SoftwareApplication, Product, Organization, Person, or Article so agents can tell what this site is

Fix: Add JSON-LD structured data to your homepage using the identity type that matches your site - SoftwareApplication for products, Organization or LocalBusiness for companies, Person for personal sites, Article for blogs - with name, description, url, and type-appropriate fields (offers, sameAs, author) so AI can parse your identity programmatically.

Partial

MCP server / manifestrecommended

MCP server listed in registry (Smithery, easyreg/private-number-plates, 182 uses) but no live MCP protocol handshake - add /.well-known/mcp or ensure the deployment responds to initialize

Fix: Build an MCP (Model Context Protocol) server exposing your API as tools. Use Streamable HTTP transport for full score. This lets Claude, ChatGPT, and other AI agents call your product natively.

Partial

Metadata completenessrecommended

3/4 metadata signals present - missing: og:type

Fix: Add all four signals to your homepage: <link rel="canonical">, <html lang="...">, <meta property="og:image">, and <meta property="og:type">. Agents use these for entity resolution and attribution.

24 checks · scanned 9 Oct 2026

Opportunity cost · finance

Chase UK could see ~$55,080,000 of processed value exposed to agent-led journeys each year

Gap to leader: 32.4 pts
Below finance avg: 9.1 pts
Modeled flows at risk: $55,080,000

Claim Chase UK to use your own processed value

Badge

Show visitors you take AI agents seriously

Add a live Index badge to your footer, docs or README. The badge updates after every run and links visitors to this scorecard.

Ask your agent about chase.co.uk

Add the Index to Claude, ChatGPT or Cursor as an MCP connector to look up any score, frictions and agent sessions. No account needed.

https://app.stuntdouble.io/api/mcp/index

Setup for your client

Discover more insights with Stunt Double

Send AI agents through chase.co.uk on your own tasks.

Try Stunt Double

Chase UK

Latest results

By category

Performance

Points by category

Agent readiness checks

Brand awareness

Discovery

Information retrieval

Market ranking

Accuracy

Task completion

Delegated access

Contact & communication

Category weights

Agents

Sessions

Sessions

Sessions

Potential improvements

Biggest wins

Where agents get stuck

Technical readiness

Chase UK could see ~$55,080,000 of processed value exposed to agent-led journeys each year

Show visitors you take AI agents seriously

Ask your agent about chase.co.uk