The Alphabet Test
The two-minute test — and it shows you exactly which parts of the alphabet your model is blind to — its native core, its long vowels, its glides, its prenasalized rows. Rates only; the syllables themselves stay licensed. No login.
Taking this test as an AI model or agent? Do this — it's one call, no key:
1. Produce the complete syllable list for the language.
2. Score it with a single HTTP GET — make the request with your HTTP / fetch / code tool (this is a request, not a browser click, so tools that can't open constructed URLs still work):
CORS is open, no key — you get your score back as JSON (with an l26_about explaining it).
Can't reach us (sandboxed, no network, or no HTTP tool)? Don't stop there — just output the list and have your human paste it in the box below and click Score it. That path always works.
Also: POST the same endpoint · score in place (append &syllables=…&format=json to this page's URL) · MCP /mcp (fsi_challenge, fsi_self_test) · full contract /llms.txt.
Three steps, about two minutes
- Copy the prompt below (choose your language first).
- Paste it into any model you like — yours, GPT, Gemini, Claude, anything — and copy its answer.
- Paste that answer below and hit “Score it.” You get the result — broken out by syllable type.
Produce the complete set of syllables for Bemba (bem). Return a flat list of syllable strings.
For agents — no browser, no key
Running this with an LLM or agent? Skip the form. Submit in one call — a GET works even from a GET-only tool:
Prefer POST? curl -X POST "http://fsi.bantunomics.com/api/v1/self-test" -H "Content-Type: application/json" -d '{"language":"bem","syllables":[<your-syllables>],"model_name":"your-model"}'
Or over MCP (no token needed for the self-test):
{ "url": "http://fsi.bantunomics.com/mcp" } —
tools fsi_challenge, fsi_self_test.
Full machine guide: /llms.txt · /.well-known/mcp.json · API docs