Competitive Compass Competitive Compass Signal for Financial Leaders
Competitive Compass
AI Compass
By Competitive Compass
Canada Deep Dive · TD CANADA TRUST July 2026
Canada · Personal Banking

TD Canada Trust.

The strongest technical foundation in the Canadian field. TD publishes a 436 page machine-readable index of its own site, and four product pages are built and ready to carry their numbers.

Agent Readiness Score
70 / 100
Technical Readiness
42 / 50
Content Architecture
28 / 50
Rank 3 of 15 · Big Five bank · Surfaces reviewed 7 · Range across surfaces 41 to 89 · Band Leading

TD Canada Trust posts an Agent Readiness Score of 70 out of 100 in the AI Compass Canada July 2026 Index on the strength of the strongest technical base in the field. The score splits into Technical Readiness at 42/50 and Content Architecture at 28/50. An open robots file and a real llms.txt covering 436 Canadian pages put TD ahead on discovery. Mortgages, home equity, personal loans and the TFSA are the four surfaces where published price moves the score next.

The Read

What an agent receives.

TD gives agents more help finding its content than any other institution in this field. The robots file allows everything and names a sitemap. The llms.txt at td.com indexes 34 section files, including 15 Canadian English files covering 436 personal banking pages, each carrying a URL and a description. Only 7 percent of those descriptions are boilerplate. The rest are real one-line summaries.

Three surfaces then deliver on that promise completely. Chequing serves four plans with their monthly fees as plain numbers. The Growth Savings Account serves a nine-rate tier ladder in parsable tables. The Aeroplan Visa Infinite serves a $139 annual fee, a 21.99% purchase rate, a 22.99% cash advance rate and the exact income and residency test.

The other four surfaces show the same page built and ready for its values. The mortgage rate table arrives with 48 rate spans awaiting figures across 366 kilobytes, so an agent reads “5 Year Fixed Closed | % | (Posted Rate: %) | %”. The Home Equity FlexLine follows the same pattern. The personal loan page carries its terms across 39,965 characters and is ready for a stated rate.

The TFSA page is the clearest case. It returns 200 with 26,235 characters of navigation, banners and legal footer, and the product body is ready to join them. TD already proves the fix works: the Today’s Rates page serves “TD Prime Rate | 4.45% | Oct 30, 2025” plus a full dated history as clean HTML.

Surface Scorecard

Flagship product by sub-category.

One flagship product was selected for each personal banking sub-category on the td.com Canadian root, matching the product TD itself features first. Each surface was read from the server response, without a browser session.

Sub-category and flagship product
Tech /50
Cont /50
Score /100
Savings
TD Growth Savings Account
48
41
89
Credit cards
TD Aeroplan Visa Infinite
46
42
88
Chequing
TD All-Inclusive Banking Plan
48
39
87
Home equity
TD Home Equity FlexLine
40
32
72
Personal loans
TD Personal Loan
39
19
58
Mortgages
TD 5 Year Fixed Closed
35
19
54
Investing
TD Tax-Free Savings Account
35
6
41
Strengths and Opportunities

What is working and where the value sits.

What Is Working

TD publishes a real machine-readable index. The llms.txt lists 34 section files. Everyday Banking states “Total pages in this file: 219”, with Personal Investing at 64, Credit Cards 54, Borrowing 48 and Mortgages 44. Only 32 of 436 entries use boilerplate.

Chequing fees arrive as plain numbers. The chequing hub serves “TD All-Inclusive Banking Plan $30.95”, “TD Unlimited Chequing Account $17.95”, “TD Every Day Chequing Account $11.95” and “TD Minimum Chequing Account $3.95”.

The savings rate ladder is a parsable table. The Growth Savings page serves four HTML tables and nine rate figures including 0.40%, 0.75%, 1.30% and 1.50%, mapped to bands such as “$24,999.99” and “$500,000.00”.

The flagship card publishes price and qualifying income. The Aeroplan Visa Infinite serves “Annual Fee $139”, “21.99%” on purchases, “22.99%” on cash advances, and “$60,000 annual personal income or $100,000 annual household income”.

Where The Value Sits

The mortgage rate table is ready for its numbers. Forty-eight rate spans await values across 366 kilobytes, so an agent reads “5 Year Fixed Closed | % | (Posted Rate: %) | %”. The table, the term labels and the APR column already ship correctly.

Home equity follows the same pattern. Eleven rate spans await values and the served text reads “% (TD Prime Rate)”, while the page already serves “access up to 80% of your home’s value”.

The personal loan page is ready for a published price. Across 39,965 characters the actionable number today is “you want to borrow at least $2,000”, and a stated rate or a representative APR completes it.

The TFSA page body is ready to render server side. The page returns 26,235 characters of navigation, banners and footer, so adding the contribution limit, the rate and the eligibility rule as text answers the question directly.

The encouraging read: TD already runs the pattern that fixes this. The Today’s Rates page serves prime as clean dated HTML, and applying that approach to the product rate modules lifts three surfaces at once.

TD tells agents exactly where 436 pages live, and filling four rate fields turns that map into a set of answers.
Field Position

Where TD sits in the Canadian field.

TD Canada Trust scores above the TD Bank US property measured in July 2026. The Canadian site carries a stronger technical base and a sharper content opportunity. Scores shown are the nearest neighbours in the July 2026 Canadian field.

2
RBC Royal BankBig Five bank
72
3
TD Canada TrustBig Five bank · This report
70
4
TangerineDirect bank
68
The Two Dimensions

Where the work lives.

Every Agent Readiness Score splits into Technical Readiness and Content Architecture. The two halves point to different teams and different timelines.

Technical Readiness
42 / 50
Access, discovery and retrievability. TD earns the highest technical score in the Canadian field on the strength of open robots rules and a published llms.txt covering 436 Canadian pages with real descriptions.
Content Architecture
28 / 50
Whether the page answers the question a person actually asks. Three surfaces answer in full. Four arrive fully built with the price field ready to be populated, which is the one field a comparison turns on.
The 90-Day Path

Four moves to the leading band.

Sequencing, effort estimates and the surface-by-surface build order sit in the full engagement plan. Item one carries the largest share of the available lift.

1

Render mortgage and home equity rates server side.

The tables, term labels and APR columns already ship. Populating those spans in the first response turns two surfaces into strong ones with no redesign.

2

Publish a representative rate on the personal loan page.

A stated range or a representative APR example with amount and term lets an agent answer the one question customers ask about that product.

3

Restore the TFSA page body.

Add the contribution limit, the eligibility rule and the account options as text. The page scores lowest purely because its main content region renders client side.

4

Mirror the Today’s Rates page pattern everywhere.

That page already serves “TD Prime Rate | 4.45% | Oct 30, 2025” as clean HTML. Applying the same approach to product rate modules lifts three surfaces at once.

The direction of travel favours TD. Discovery infrastructure is the part competitors take quarters to build, and TD finished it first.

TD built the map before anyone asked for it. Filling four rate fields turns the map into a set of answers.
Methodology

How the score is built.

AI Compass measures what an AI agent receives when it visits a financial institution website on a customer’s behalf. It reads the served response the way an agent does, without a browser session, without scripts, and without a human clicking to reveal a value.

Scoring bands

  • Leading 70 to 100. The page answers the customer question in full.
  • Building 50 to 69. The story arrives and a decisive field is ready to be published.
  • Early 0 to 49. An agent leaves with a partial answer.

How the total works

Each product surface earns a score out of 100, built from Technical Readiness out of 50 and Content Architecture out of 50. The institution score is the average across the surfaces reviewed, up to seven.

Technical Readiness · 50

  • Crawler permission. Robots rules, treatment of named AI agents, sitemap presence, and whether the edge serves them.
  • Machine-readable discovery. An llms.txt index and the quality of what it describes.
  • Server-side completeness. How much of the page arrives in the first response.
  • Retrievability. Stable URLs, working paths, clean status codes, content served ahead of any gate.
  • Disclosure availability. Whether terms and footnotes travel with the page.

Content Architecture · 50

  • Price in text. Rate, APR, fee and bonus values present as readable figures.
  • Eligibility in text. Provinces, balances, income, credit position, qualifying activity.
  • Comparison structure. Tables an agent can parse across products.
  • Question coverage. FAQ content served as text rather than as a call.
  • Plain answers. Wording that maps to how customers ask the question.

Surface selection and review window

Sub-categories come from the personal banking navigation on each brand’s Canadian root. Within each one, the flagship is the product the institution itself features first. Brands with fewer product lines are scored on the surfaces they actually sell, so a focused brand is measured on quality rather than on breadth.

Pages were read on 30 July 2026. Rates, bonus offers and terms move, and scores describe what each site served on that date. Where a site offers more than one language, the version served by default to a request with no language preference was used.

Independence and scope

Scores come from observed page behaviour alone. No institution reviews or approves a score before publication, and every brand is measured against the same rubric. Outlier results are verified against a second independent retrieval pass before publication.

The score covers the public marketing site. Logged-in banking, the mobile app and the branch experience sit outside it. A site can score well here and still have work to do inside the login, and the reverse holds too.

Frequently Asked

Common questions about the TD Canada Trust score.

What is the AI Compass Canada score for TD Canada Trust?

TD Canada Trust carries an AI Compass Agent Readiness Score of 70 out of 100 in the July 2026 Canada Index. That is the sum of Technical Readiness (42/50) and Content Architecture (28/50), scored across 7 product surfaces and read from the server response on 30 July 2026.

How is the TD Canada Trust AI Compass score calculated?

Each product surface earns a score out of 100, built from Technical Readiness out of 50 and Content Architecture out of 50. Technical Readiness covers crawler permission, machine-readable discovery, server-side completeness, retrievability and disclosure availability. Content Architecture covers price in text, eligibility in text, comparison structure, question coverage and plain answers. The institution score is the average across the surfaces reviewed. TD sits at 42 on Technical Readiness and 28 on Content Architecture.

Which TD Canada Trust surface is most agent ready today?

The strongest surface is Savings at 89, with Credit cards at 88 close behind. The next points sit on mortgages, home equity, personal loans and the TFSA, where the page structure ships and the numbers are ready to render server side.

How often is the TD Canada Trust AI Compass score refreshed?

Canada scores are refreshed each edition of the AI Compass Index, and a deep dive is refreshed whenever a brand ships a major site or content change. The July 2026 edition reads the served response on 30 July 2026. Subscribe at competitive-compass.com to get the next refresh.