Miatz playground

Break-Even Board

Plug in your numbers, watch the break-even cross.

Coming to the Build-LabAIE-110Browser (JS)AI-Concept-Vizdev · data

The Demystify signature

Replaces the industry's fine-tuning-vs-prompting hot takes with the learner's own crossover math -- a personalized answer computed live, not a rule of thumb.

How it works

What goes in, what comes out

What it does

Learner sets their own task profile -- monthly query volume, required accuracy, latency tolerance -- and three animated cost curves (prompting, RAG, fine-tuning) plot against volume, with a marker showing exactly where the learner's own numbers land. Dragging the accuracy requirement re-draws the curves live, so the 'right' strategy visibly flips instead of staying fixed.

You bring

Slider and preset selections describing the learner's own use case.

You get

Three cost curves with the crossover point highlighted and a plain-language verdict, e.g. 'at your volume, fine-tuning breaks even in 11 days'.

You control

Volume slider (100/mo to 10M/mo); accuracy-requirement bar; latency-requirement input; task-type presets (classification, generation, Q&A).

Where it's used

Companion to AIE-110 and the Data-track fine-tuning module; lead magnet for founders and PMs sizing a build decision.

tune-vs-prompt economicsRAG vs fine-tuningbreak-even analysis

Optional · watch & try

Go deeper, elsewhere

Hand-picked public explainers and open tools that complement this one — always optional, never required, never graded.

What is LoRA? Low-Rank Adaptation for finetuning LLMs EXPLAINEDExplains the low-rank matrix trick that makes LoRA cheap LoRA for fine-tuning LLMs explained with exampleWorked example applying LoRA to an actual model LLM Fine Tuning Explained in 8 Minutes: LoRA, QLoRA, DPOFast comparison of fine-tuning method families · ~8 min Hugging Face PEFT — LoRA methodsOfficial reference implementation and guide for LoRA/PEFT fine-tuning LLM Model VRAM Calculator (Hugging Face Space)Estimate GPU memory needed to fine-tune or run a given model at a given quantization

Concepts click when you open the machinery.

Three labs are already live and free — the same hands-on style this playground brings to its module.

Play the free labs Take the DSAT