Wizhut Research

Research

Small, real products built to answer a question

Some ideas only give up their answer once you build them and put them in front of people. This is where we do that: working products, free to use, each one testing something we were not sure about — and each one publishing what it found.

A question, not a roadmap

Each experiment starts from something we genuinely do not know the answer to. If the answer were obvious, building it would be product work, not research.

Free while it is an experiment

Experiments are how we learn, so charging for one would be charging you for our education. They stay free, and the ones that graduate into products say so loudly before anything changes.

The evidence ships with it

Every experiment has a page here with its method and its measurements, including the parts that did not go the way we expected. A claim without a number behind it does not go on these pages.

Experiments

What is in the lab right now.

Each one opens onto its own page: the question it is testing, how it works, and every measurement we have taken. The headline figure below is the single most useful thing that experiment has told us so far.

Kyori

Can a string score alone order an autocomplete list as well as the libraries applications already use?

The ranking cost inside our open-source JavaScript library: four ordered rules and a length tie-break, with no popularity data and no model. Kyori 0.5.0 is measured on held-out AmazonQAC searches against Fuse.js, fuzzysort, match-sorter, sorting by length and popularity — ties reported, every gap tested.

Open source, MITOn npm

0.404

mean reciprocal rank on 11,607 held-out prefixes — level with Fuse.js, fuzzysort and sorting by length; popularity adds 0.018

Use it How it works, and what it found

Promptivo

Can prompt quality be measured without asking a model?

A deterministic scorer for AI prompts: seven research-backed merits, a regression calibrated once against an LLM judge and then frozen into coefficients. It runs with no model in the loop, so the same prompt always scores the same, and no model ever reads what you paste.

Free, with an accountNo LLM at scoring time

ρ = 0.53

against a held-out judge consensus — where two frontier judges only manage ρ = 0.61 with each other

Use it How it works, and what it found

Real research on real problems.

Promptivo scores a prompt across seven quality dimensions in milliseconds, with no model call — free, permanently, with no quota. Kyori orders an autocomplete list with nothing but the strings, and is one npm install away, MIT-licensed.

Try Promptivo Kyori on npm