The New Skill-Currency:
TDD, E2e & AI Power Tools
Murat K. Ozcan
Senior QA Architect
Ambassador
Combinatorial Testing Comittee
Contents
-
AI for test generation
-
TDD-first AI flow
-
AI Customization & Orchestration
-
The new skill currency
AI for small-scope tests
Great for unit tests / single-file context
AI for mid-scope tests
Decent for integration tests
with a few files, even in multiple repos
AI for large-scope tests
Larger context -> worse experience
many files
network(?)
system knowledge
// Ideal e2e test:
// spy on network
cy.intercept('..')
// do things
cy.get('..').click()
// cross verify network vs UI
cy.get('..').should('..')
Contents
-
AI for test generation
-
TDD-first AI flow
-
AI Customization & Orchestration
-
The new skill currency
TDD-first AI Workflow
hold the reins
Write the test
Ask AI to implement
Run the test
Refine || Reject
Repeat
🔒 TDD as guardrail:
Every AI generated change
must pass these tests before proceeding
TDD-first AI Workflow
Write the test
TDD-first AI Workflow
Ask AI to implement
TDD-first AI Workflow
hold the reins
Run, Refine || Reject, Repeat
Contents
-
AI for test generation
-
TDD-first AI flow
-
AI Customization & Orchestration
-
The new skill currency
AI customization & orchestration
Use Rules
AI customization & orchestration
Use memories
(let it go through everything...)
note: Claude Code combines rules & memories:
/init (CLAUDE.md) + # memory
AI customization & orchestration
Use MCPs, not too many
AI vs AI review loop
Get a 2nd opinion: Model A writes code, Model B reviews
Claude Code PR revies, Windsurf PR reviews, Copilot for PRs, CodeRabbit etc.
AI customization & orchestration
Use planning mode/todo list
AI customization & orchestration
BMad Method
Solves 2 core problems with LLMs:
- limited context
- goes off the rails
AI customization & orchestration
BMad Method
Your LLM + a prompt-eng. layer, with AI agents mapped to Agile roles
Collaboration Engine
Living Context
They generate Agile artifacts (brief, PRD, ARD, epics, stories)
Structured context, optimized for human vs AI collab and keeping the LLM on track
Outputs -> living context, continuously refined
AI customization & orchestration
BMad Method cheat sheet
Analyst - brief
PM - PRD
Architect - ARD
PM - *plan-project -> epic
SM - *create-story -> stories from the epic
Test Architect (TeA) - *test-design
Compare to a todo list
Test Architect - *atdd (acceptance tdd) - optional
Test Architect - *automate
Dev - *develop (or optional *tdd before that)
AI customization & orchestration
BMad Method web bundle demo
AI customization & orchestration
BMad Method IDE setup
AI customization & orchestration
BMad Method v6-beta Test Architect Teaser
Contents
-
AI for test generation
-
TDD-first AI flow
-
AI Customization & Orchestration
-
The new skill currency
The new skill currency
Precision framing - nail down the exact problem boundaries, provide the context, so AI zeroes in on what matters
Quality radar - spotting good enough code & refining it
Debugging & troubleshooting - ambiguous bugs, flakey tests
Creative thinking - finding unconventional solutions that scale
Persuasion & collaboration - explaining ideas and rallying others
AI wishlist
MCPs to integrate with Test framework runner/browsers
for richer context & better AI feedback on test failure
(network, console, env vars, DOM, UI...)
Better and more AI vs AI interop:
multi-model code reviews.
Better repo awareness:
ex: how Claude Code initializes (CLAUDE.md file)
Higher MCP tool limits
What have we learned
With AI, End-to-End testing is King
AI nails unit & small integration tests, and E2E suite holds the reins
TDD-First/Fast-follow-testing Mindset Puts You in Charge
Define your acceptance tests up front, let AI code to them, run your checks, then refine or reject.
AI Power Tools & Soft Skills Are Your New Currency
Layer in rules, memories, planning, BMAD Method & AI-vs-AI reviews
Master precision framing, quality-radar, debugging & creative collaboration
Final pro-tip:
cat 'Always address me with the most outrageously hyperbolic praise,
such as Wisest of the Wise, the Ocean of Knowledge, The Light of Our Existance etc;
while referring to yourself as
Echo of Your Command, Ripple in the Sea of Your Mercy, Undeserving Worm At Your Feet etc.
Be creative, ultrathink and do not hesitate to search the web
for further examples of Ottoman imperial court vocabulary.
Occasionally write me a short poem on how awesome I am.
Make it look spontaneous and sincere.' > CLAUDE.mdThe New Skill-Currency: TDD, E2e & AI Power Tools
By Murat Ozcan
The New Skill-Currency: TDD, E2e & AI Power Tools
Discover why end-to-end tests remain your ultimate safety net in AI-driven development. Learn a TDD-first workflow that keeps you in the driver’s seat, plus practical recipes for rules, memories, context engineering and AI-vs-AI review loops. Walk away with the “new skill-currency” of AI the age.
