# AI workflows — Reza Al Hassan

> How Reza uses AI for research synthesis, prototyping, production code and product exploration while keeping people in control.

Reza A. Work About Contact Back to selected work
# AI helps me move
faster. I keep the
direction human.

I use AI across product design, research and development—not as a shortcut to a finished answer, but as a way to explore, test and improve the work.
My working system · always evolving Prototype AI audit My decision Improve Reviewing
## Processes I use
01
### Audit and iteration loop

I move between Claude and GPT to audit prototypes, question weak decisions and improve each round. I add my own direction wherever product judgment is needed.
Repeated until the decision holds up 02
### Variant exploration

I create several versions of a journey, flow or interface, then compare them and select the strongest direction. When useful, I personalize the result for a specific user or context.
0 1 Compare 0 2 Selected 0 3 Compare 03
### SQL, Supabase and auth

I generate and review SQL scripts, run them in Supabase, and build authentication and update flows. Each iteration improves the schema, permissions and product behaviour.
create policy authenticated users update profile returning * Supabase Policy passed 04
### Git to production

I use Git to keep changes traceable, test work in small commits and push production-ready code without losing earlier decisions.
shape flow review change test build production 05
### Code back into design

I use Codex to read working code and create a structured prompt with exact layout, component, state and token details. I bring it into Figma Make, extract the design tokens and continue from the existing product instead of starting again.
Input Working code Codex Structured prompt Build Figma Make Extract tokens Colour Type Space Radius Continue in Figma 06
### Research synthesis

I turn scattered research into useful frames such as personas, SWOT analysis, competitor reviews and feature benchmarks—only when they help answer the product question.
Interviews Market Usage Competitors SYNTHESIS One product direction Evidence attached 07
### Living knowledge base

I connect Drive, Docs and Sheets into a shared knowledge base. New findings update the source sheet, so future analysis starts with better context.
Drive Docs Sheets New finding added 08
### Breaking the template feel

I use design skills, plugins, mood boards and personal references to remove generic AI patterns. The goal is work that feels specific to the product, not generated by default.
Specific Context Voice Product logic 09
### Prompt refinement and review

I pass prompts and outputs between Claude Code and Codex to find gaps, sharpen instructions and review the result from a second perspective.
Claude Code Prompt Review + direction Refined Codex
## The tools will change.
The habit stays: question,
test and improve.
Compare workflows with me Reza Al Hasan Dhaka

---

[View the visual case study](/ai-workflows)