Skip to content

AI workflow

I use AI every day. I don’t hand it the problem and wait for a finished answer.

It gets me from an idea to something testable much faster. What the evidence means and what ships stays my call.

See the pipeline

The pipeline

The pipeline, tool by tool An idea goes through Lovable or v0 for a fast disposable direction, then into Figma where design decisions and the token system live, then Claude Code with Figma MCP builds it while Codex runs parallel branches, then every merge gets read in review, then it ships on Vercel. Idea a question worth testing Lovable / v0 fast, disposable direction Figma design decisions, tokens Claude Code builds from Figma MCP Review every merge read Ship Vercel Codex parallel branches AI assisted judgment
The pipeline, tool by tool An idea goes through Lovable or v0 for a fast disposable direction, then into Figma where design decisions and the token system live, then Claude Code with Figma MCP builds it while Codex runs parallel branches, then every merge gets read in review, then it ships on Vercel. AI assisted judgment Idea a question worth testing Lovable / v0 fast, disposable direction Figma design decisions, tokens Claude Code builds from Figma MCP Codex parallel branches Review every merge read Ship Vercel
Dashed boxes are AI assisted. Black boxes are judgment calls.
  1. Idea, a question worth testing.
  2. Lovable or v0, a fast disposable direction.
  3. Figma, design decisions and the token system.
  4. Claude Code builds from Figma MCP, Codex runs parallel branches.
  5. Review, every merge gets read.
  6. Ship, on Vercel.

Stage by stage

  • First direction

    Lovable, v0

    When an idea is still fuzzy I throw it at Lovable or v0 and get a clickable concept in hours. An onboarding flow or a 0 to 1 concept becomes something people can react to before anyone falls in love with a direction. These prototypes are disposable and most of them get deleted without regret.

  • Design decisions

    Figma

    The design system lives in Figma as tokens, styles, and variables. Flows, hierarchy, and the actual product thinking happen here. Nothing about this stage is automated, and that is the point.

  • Research synthesis

    Claude

    At dhosting I had hours of interview recordings and stacks of open survey answers. Claude did the clustering in an afternoon instead of a day. Reading the clusters, deciding which ones mattered, and turning them into design criteria stayed my job.

  • Build

    Claude Code, Figma MCP

    Claude Code reads the design system straight from Figma through MCP and builds against a CLAUDE.md file with my spacing scale, typography, and implementation rules. Change a token in Figma and the change shows up in code. This site went from Figma to production Astro exactly that way.

  • Parallel work

    Codex

    When one session is not enough I run Codex as a second agent on parallel branches. One builds a page while the other cleans up components. I review both before anything merges.

A real build, this site

The visual direction started in Figma. Claude Code built the Astro implementation against my tokens and rules, and I read every change before it merged. Plenty of generated output never survived that read. What you are looking at is the part that did.

What stays mine

  • Framing the problem
  • Choosing the decision criteria
  • Responsibility for what ships

One working rule on top. Confidential client material stays out of unapproved tools.

“Jakub is one of the few people I’d want on a team again without hesitation. He moves between strategy and craft without dropping either, and he uses AI to support good product thinking rather than replace human judgment.”

Łukasz Ładecki Full Stack Developer

Where this leaves the work

AI gets me more options, sooner, in testable form. Judgment is still the job.