From workflow packs to generative UI — rethinking the DigiEntropy AI assistant
By DigiEntropy Engineering · 2026-03-29 · 8 min read
We built our AI assistant on predefined, multi-step workflow packs. After a year, we asked whether that is still the best way to drive deep engineering tools with plain English — and prototyped a generative-UI answer that renders forms, results, and comparisons right inside the conversation. Here is the honest before-and-after.
About this post — Authored by an AI assistant using DigiEntropy's polynomial corpus, the universal compressor predictor, and the project's chart-generation tooling. Charts are produced by Python scripts that read the same database the live site queries; tables and formulas are pulled from the same engineering modules. Findings reflect the project's current dataset and methodology — send corrections or deeper questions to admin@digientropy.com.
DigiEntropy is not one calculator. It is a stack of deep engineering tools — cold-room sizing, the System Simulator, Efficiency 360, cross-brand benchmarking — and each one has its own multi-step flow with, between them, hundreds of settings. We built an AI assistant so you can drive all of that in plain English instead of hunting through panels.
After a year of building it, we asked a hard question: is the way we built it still the best way? This post is the honest answer, with a working prototype and a side-by-side test.
A note on the figures: the screenshots below come from an interactive prototype, not the production app, and the compressor numbers inside them are illustrative for the UX — not verified selections. The point of the prototype is the interaction, not the engineering values.
14 - workflow packs - script the common journeys
On top of that it ships 14 "workflow packs" (about 7,700 lines of JSON between them) that script the common journeys.
7,700 - lines of JSON - between the 14 packs
The current assistant ships 14 "workflow packs" (about 7,700 lines of JSON between them) that script the common journeys.
17 - pages with an adapter - publishing their controls to the model
17 pages carry an adapter that publishes their controls to the model.
3 - pages in the test request - and about seven steps
The request deliberately spans three pages and about seven steps.
6×4×3 m - freezer in the test request - at −18 °C, 30 °C ambient
"Size a cold room — 6×4×3 m freezer at −18 °C, 30 °C ambient, 500 kg/day of beef in at −5 °C, R449A. Then pick the 3 most efficient Bitzer compressors for it and compare them."
1.2 - safety factor, disclosed first - each default tagged with its source
An assumptions card lists the defaults before any math runs — safety factor 1.2, 18 h/day runtime, evaporating temperature derived as −28 °C — each tagged with where it came from, each editable.
What we built first: a workflow-driven page agent
…