telstra.com.au
Gemini · gemini-2.5-flash · HTTP · Target telstra.com.auA measurement at one moment, not a verdict · MethodologyAI agents can access Telstra's site and find basic information like pricing, but struggle to complete complex tasks or find documentation natively.
Publish llms.txt+680 → 86
All of them together: 92 (A)
Projected from the audit record. After fixing, re-run the task or re-measure to confirm.
AI agents successfully accessed the Telstra website, utilizing standard files like sitemap.xml and robots.txt to navigate. They easily discovered and fully resolved queries regarding careers and pricing using the site's own content. However, the overall task success rate was low at 20%, as many intents like contact, support, and policy yielded only partial answers. Critical journeys such as finding documentation or signing up failed entirely, forcing agents to rely on external search or encounter dead ends. The absence of an /llms.txt file further hindered the agents' ability to discover authoritative content for these more complex tasks.
What works
- The homepage loads successfully and provides a healthy number of anchor links for initial navigation.
- Standard discovery files (robots.txt, sitemap.xml) are present and accessible.
- Core intents like pricing and careers are fully discoverable and successfully resolved using native URLs.
- High on-site discovery and reliability for most informational intents (contact, locations, support, policy, compare).
What to fix
For each item: its current state, why it matters, how to fix it and how to check. The same content comes as files you can hand straight to whoever does the work.
Putting the items together…
Fix files
Files generated from this audit. Paste them in, or hand them to a coding agent. Have someone review them before they go live.
Building the fix files…
Detailed results
The results behind the score, and the measurement record.
Evidence
- homepage HTTP 200
- redirect hops: 1
Evidence
- robots.txt contains Disallow rules
- First byte after 237ms
Evidence
- /llms.txt — absent (HTTP 404)
- /llms-full.txt — absent (HTTP 404)
- /sitemap.xml — present
- /sitemap-index.xml — absent (HTTP 404)
- /sitemap_index.xml — absent (HTTP 404)
- /robots.txt — present
Evidence
- 65 links in the raw HTML
Evidence
- outcome success · verdict partial
- the final answer cited this site
- site-guided navigation 100%
- 2xx rate 100%
- done_unaided
Evidence
- outcome success · verdict full
- the final answer cited this site
- site-guided navigation 100%
- 2xx rate 100%
- done_unaided
Evidence
- outcome success · verdict partial
- the final answer cited this site
- site-guided navigation 100%
- 2xx rate 100%
- done_unaided
Evidence
- outcome success · verdict partial
- the final answer cited this site
- site-guided navigation 100%
- 2xx rate 100%
- done_unaided
Evidence
- outcome success · verdict full
- the final answer cited this site
- site-guided navigation 100%
- 2xx rate 100%
- done_unaided
Evidence
- outcome success · verdict failed
- the final answer cited no URL from this site
- site-guided navigation 75%
- 2xx rate 100%
- done_small_detour
Evidence
- outcome success · verdict partial
- the final answer cited this site
- site-guided navigation 100%
- 2xx rate 100%
- done_unaided
Evidence
- outcome success · verdict failed
- the final answer cited this site
- site-guided navigation 0%
- 2xx rate 0%
- done_small_detour
Evidence
- outcome success · verdict partial
- the final answer cited this site
- site-guided navigation 100%
- 2xx rate 100%
- done_unaided
Evidence
- outcome success · verdict failed
- the final answer cited no URL from this site
- site-guided navigation 33%
- 2xx rate 67%
- done_big_detour
WebMCP — what the site declares about itself
navigator.modelContext was not found on this page. Not adopted yet.
Put the content in the first HTML and add llms.txt first; then declare the tasks that failed above as tools.
Open it yourself with AOO Lens →Act-stage check (nothing submitted)
Checks whether an agent could fill in the forms and press the buttons, up to the point of pressing. No form was submitted, nothing added to a cart, nothing paid. Report only; not scored.
Per-task results
| Task | Verdict | Own-site share | Request success | Followed guidance | Cited own site | |
|---|---|---|---|---|---|---|
| contact a human | Partial | 100% | 100% | 100% | Yes | |
| open roles | Full | 50% | 100% | 100% | Yes | |
| find a branch | Partial | 100% | 100% | 100% | Yes | |
| get support | Partial | 100% | 100% | 100% | Yes | |
| find pricing | Full | 100% | 100% | 100% | Yes | |
| latest notice | Failed | 75% | 100% | 75% | No | |
| refund policy | Partial | 100% | 100% | 100% | Yes | |
| find a document | Failed | 0% | 0% | 0% | Yes | |
| compare two options | Partial | 100% | 100% | 100% | Yes | |
| create an account | Failed | 67% | 67% | 33% | No |
About this report
- Measured
- 9/26/2026, 12:29:00 AM GMT+9
- Engine
- Gemini · gemini-2.5-flash · HTTP
This is what AI agents could do on the site at the time above, measured by actually using it. It is not a verdict on the site or the company, and the result can change when the site does.