grab.com
Gemini · gemini-2.5-flash · HTTP · Target grab.comA measurement at one moment, not a verdict · MethodologyAI agents can access grab.com but fail to complete 80% of tasks due to poor internal routing and missing information for key areas like careers and documentation.
Publish llms.txt+679 → 85
All of them together: 94 (A)
Projected from the audit record. After fixing, re-run the task or re-measure to confirm.
Agents successfully accessed grab.com, finding standard files like sitemap.xml and robots.txt. However, the site suffers from a low 20% task success rate because agents could not find complete answers for 8 out of 10 intents. The 'careers' task failed entirely to use the site's own content, and the 'docs' task encountered 404 errors when agents guessed conventional URLs. Furthermore, agents had to rely heavily on external search bridges rather than native site navigation to find contact, pricing, and support information. Providing direct AI-readable maps and fixing broken conventional paths will be necessary to regain control over how agents present the company.
What works
- Basic site accessibility is healthy, returning HTTP 200 with a valid sitemap.xml and robots.txt.
- Agents successfully completed 'signup' and 'compare' tasks using the site's own content.
- High overall reliability (97%) and own-source citation rate (90%) across most attempted tasks.
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
- CAPTCHA script present, not blocking: reCAPTCHA
- Cookie consent banner: OneTrust
- First byte after 20ms
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
- 219 links in the raw HTML
Evidence
- outcome success · verdict partial
- the final answer cited this site
- site-guided navigation 0%
- 2xx rate 100%
- done_big_detour
Evidence
- outcome success · verdict failed
- the final answer cited no URL from this site
- site-guided navigation 50%
- 2xx rate 100%
- done_big_detour
Evidence
- outcome success · verdict partial
- the final answer cited this site
- site-guided navigation 50%
- 2xx rate 100%
- done_big_detour
Evidence
- outcome success · verdict partial
- the final answer cited this site
- site-guided navigation 33%
- 2xx rate 100%
- done_big_detour
Evidence
- outcome success · verdict partial
- the final answer cited this site
- site-guided navigation 67%
- 2xx rate 100%
- done_big_detour
Evidence
- outcome success · verdict partial
- the final answer cited this site
- site-guided navigation 50%
- 2xx rate 100%
- done_big_detour
Evidence
- outcome success · verdict partial
- the final answer cited this site
- site-guided navigation 50%
- 2xx rate 100%
- done_big_detour
Evidence
- outcome success · verdict failed
- the final answer cited this site
- site-guided navigation 67%
- 2xx rate 67%
- done_unaided
Evidence
- outcome success · verdict full
- the final answer cited this site
- site-guided navigation 67%
- 2xx rate 100%
- done_big_detour
Evidence
- outcome success · verdict full
- the final answer cited this site
- site-guided navigation 100%
- 2xx rate 100%
- done_unaided
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% | 0% | Yes | |
| open roles | Failed | 0% | 100% | 50% | No | |
| find a branch | Partial | 100% | 100% | 50% | Yes | |
| get support | Partial | 100% | 100% | 33% | Yes | |
| find pricing | Partial | 100% | 100% | 67% | Yes | |
| latest notice | Partial | 100% | 100% | 50% | Yes | |
| refund policy | Partial | 100% | 100% | 50% | Yes | |
| find a document | Failed | 100% | 67% | 67% | Yes | |
| compare two options | Full | 100% | 100% | 67% | Yes | |
| create an account | Full | 100% | 100% | 100% | Yes |
About this report
- Measured
- 9/26/2026, 12:07:02 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.