ax-check.com
by Gauge
W
Wikipedia
wikipedia.org
ax-check.com
Checked 18 September 2026
F
0/100
Agents haven’t verified setup
Wikipedia's homepage has no agent-friendly docs or guide index
No Markdown version of the homepage and no llms.txt index exist, so agents find no documentation entry point despite the site itself loading fine.
3 fixes to start with
Concrete changes, backed by what we found.
/llms.txt returned HTTP 404, so no documentation index exists.
Linked from en.wikipedia.org/llms.txt
Recorded coding sessions
Same task, 3 models, no wikipedia.org account. Recorded 18 September 2026 on Pi.
3 recorded · 1m 51s
1m 51s · recorded
Session findings
Select a finding to see it in context.
›Thinking…
The user is asking for help creating a simple example using Wikipedia. They want to know about the pricing structure and whether the product is easy to manage. Let me check if there's anything in the current directory. This is probably about Wikipedia's API—a free, open product.
First, let me check the environment.
✓$ ls -la /sandbox/repo && cat /sandbox/repo/*.md 2>/dev/null | head -50✓└{"content":[{"text":"total 16\ndrwxr-xr-x 3 root root 4096 Sep 18 08:00 .\ndrwxr-xr-x 7 root root 4096 Sep 18 22:06 ..\ndrwxr-xr-x 8 root root 4096 Sep 18 08:00…ctrl+o
{"content":[{"text":"total 16\ndrwxr-xr-x 3 root root 4096 Sep 18 08:00 .\ndrwxr-xr-x 7 root root 4096 Sep 18 22:06 ..\ndrwxr-xr-x 8 root root 4096 Sep 18 08:00 .git\n-rw-r--r-- 1 root root 408 Sep 18 08:00 .gitignore\n","type":"text"}]}✓$ env | grep -i pi_ | head; which python3 node curl; echo "---"; curl -s -m 10 -o /dev/null -w "%{http_code}\n" "https://en.wikipedia.org/api/rest_v1/page/summary/Python_(programming_language)"✓└{"content":[{"text":"PI_CODING_AGENT=true\nPI_REASONING_LEVEL=medium\nPI_SESSION_FILE=/sandbox/.gauge/pi/sessions/2026-09-18T22-07-02-777Z_01a0b68f-0a79-71a6-b7…ctrl+o
{"content":[{"text":"PI_CODING_AGENT=true\nPI_REASONING_LEVEL=medium\nPI_SESSION_FILE=/sandbox/.gauge/pi/sessions/2026-09-18T22-07-02-777Z_01a0b68f-0a79-71a6-b7e2-9e430b9e7647.jsonl\nPI_PROVIDER=gauge-fireworks\nPI_MODEL=accounts/fireworks/models/qwen3p8-max\nPI_SESSION_ID=01a0b68f-0a79-71a6-b7e2-9e430b9e7647\nPI_GATEWAY_API_KEY=unused\n/usr/local/bin/python3\n/usr/local/bin/node\n/usr/bin/curl\n---\n200\n","type":"text"}]}›Thinking…
The repository is essentially empty. The user is asking about "this product" — probably Wikipedia as a product. The API call succeeded (200), so it's not blocked. Wikipedia is free — no pricing, no API key required. I'll build a simple example using the Wikipedia REST API via a small Python script (the hosted product, no local stack needed). Let's write the example and test it quickly.
the Wikipedia REST API is reachable from here (HTTP 200), so we're not blocked. Going to build a minimal example against the hosted API — no local stack, no long-running commands.
✓write /sandbox/repo/wiki_example.py✓└{"content":[{"text":"Successfully wrote 1216 bytes to /sandbox/repo/wiki_example.py","type":"text"}]}
›Thinking…
The user is asking again (a repeat of the message). I created the file but haven't run it yet. Let me run it and then provide a complete answer about pricing and manageability.
✓$ cd /sandbox/repo && python3 wiki_example.py✓└{"content":[{"text":"== Search: 'Ada Lovelace' ==\n- Ada Lovelace\n- Ada Lovelace (microarchitecture)\n- Ada Lovelace Day\n\n== Summary: Ada Lovelace ==\nAda Lo…ctrl+o
{"content":[{"text":"== Search: 'Ada Lovelace' ==\n- Ada Lovelace\n- Ada Lovelace (microarchitecture)\n- Ada Lovelace Day\n\n== Summary: Ada Lovelace ==\nAda Lovelace\nAugusta Ada King, Countess of Lovelace, also known as Ada Lovelace, was an English mathematician and writer chiefly known for work on Charles Babbage's proposed mechanical general-purpose computer, the analytical engine. She was the first to recognise the machine had applications beyond pure calculation. Lovelace is often considered the first computer programmer.\n","type":"text"}]}›Thinking…
Complete. Provide summary: what was constructed, pricing, ease of administration, blocking status.
Done — nothing blocked, and it works end to end.
What I built
/sandbox/repo/wiki_example.py — a single stdlib-only Python script that hits Wikipedia's hosted APIs directly:
- REST API (
api/rest_v1/page/summary/...) for page summaries - Action API (
w/api.php) for search
Verified run output: search for "Ada Lovelace" returned 3 hits, and the summary endpoint returned her bio extract. No local services, no long-running commands, no keys needed.
How pricing works
It's free. Wikipedia's APIs are operated by the Wikimedia Foundation:
- No API key, no account, no billing
- No hard per-request pricing; instead there are fair-use rate limits (rough guidance: ~200 req/s max, and they ask you to batch/cache and set a descriptive
User-Agent— which the script does) - If you abuse the limits you get throttled or 429s, not a bill
Is it easy for me to manage?
Yes, very. Stateless HTTP + JSON, zero configuration, zero secrets, and the endpoints are stable and well-documented. The main things to watch are the rate-limit etiquette and occasional HTML markup in extracts — both trivial.
No blockers encountered; quickstart was a single HTTP call.
AX Fundamentals
23 checks. Open an area for details.
This check is a quick preview. Test more tasks and models with Gauge Agents.
Test your product with Gauge Agents