Bilicube Journal
Practical notes on design, research,
and creative work with AI.
How to Audit a Creative Workflow Before Automating It
Before automating a creative workflow, map the work that actually happens. Otherwise, automation can preserve unnecessary approvals, unclear ownership, fragile file dependencies, and decisions no one has defined well enough to delegate. The goal is not to automate the whole process. It is to identify the smallest repeatable portion that can change without weakening creative judgment or accountability. Map the Current Workflow from Request to Approved Output Start with one real workflow, not an abstract description of the team’s process. Choose a recurring request type with a recognizable beginning and end: a campaign asset, a set of social variations, a presentation update, or a design-system documentation change.
Are Design Tokens Worth It for Small Projects?
Design tokens are not automatically valuable because they promise scalability. They earn their overhead when a team must keep repeated values aligned across screens, themes, products, or a developer handoff. If none of those pressures exists, a full token workflow can turn a short project into a maintenance project. The practical question is not whether tokens are good. It is whether this project has enough repetition and coordination cost to justify naming, mapping, documenting, and maintaining them.
How to Use AI for Design System Documentation
AI can make design-system documentation faster to draft, but speed does not make generated text authoritative. The safest role for AI is a drafting and restructuring layer: give it approved information, ask it to organize that information, then verify every meaningful claim against the actual system before publication. That boundary matters because documentation describes behavior other people will rely on. An incorrect state, token value, accessibility note, or usage rule can send a designer or engineer in the wrong direction. The practical goal is not to automate ownership. It is to reduce the mechanical work of turning scattered knowledge into a page that a maintainer can inspect and approve.
A Gated AI Research Workflow for Designers
An AI research workflow for designers should not be an automated line from interview notes to finished interface. The safer pattern is a sequence of bounded handoffs: AI can organize material, suggest interpretations, draft briefs, generate concepts, and prepare test assets, while a designer or research lead approves what moves forward. That distinction matters because the supplied examples describe AI across several stages of design work, but they do not establish that AI improves research quality, reduces total project time, or replaces user research. One surfaced workflow spans ideation, wireframing, usability testing, and developer handoff (LinkedIn). Another describes a design sprint from problem definition to a tested prototype (AI UX Playground). These are workflow descriptions, not independent evaluations of their results.