Blue Belt · Promotion exam · ABD
AI App Builder
Validates that you can hand work to a coding agent to build a small web app and take responsibility for running, verifying, fixing and deploying it. This is the belt where first-time app builders rise to a professional level.
Daily practice · Free
10 questions · 20 min · No sign-up needed
Promotion exam · Proctored
30 questions · 50 min · Raw score of 70 or more · $3.99 / one attempt
Promotion exam detailsExam overview
- Questions
- 30
- Time
- 50 min
- Pass mark
- 70 pts
- Recommended experience
- White Belt (AI Literacy Foundation) level and basic use of a terminal and browser
Every question has five choices and is marked on an OMR answer sheet. Multiple-choice and true-or-false questions ask for the right combination from a box; ordering and matching questions ask for the right arrangement. Judgment questions (L3) are worth 3 points and all others 2; the raw score is converted to a 100-point scale and graded 1 to 9.
Exam domains
1. Defining tasks and instructing agents25%
2. The run-and-verify loop25%
3. Version control and change review20%
4. Security and dependencies15%
5. Deployment and operations15%
Weights follow the Promotion exam. Practice and mock exams may mix domains differently.
What this exam verifies
- Break the features to build into verifiable task instructions and hand them to a coding agent
- Run the app locally and verify the results with tests and browser checks
- Record changes with Git and manage them so they can be reverted
- Avoid risks around secrets, permissions and dependencies
- Run the basic flow of deployment, monitoring and rollback
Who it is for
- Planners and founders building their first service with a coding agent
- People without a computer science background who want to run a side project
- Junior developers working alongside agents
Does not cover large-scale distributed system design or model training.
Domain details
Domain 1. Defining tasks and instructing agents
- Knowledge: Definition of done, Small units of work, Repository instructions such as AGENTS.md and CLAUDE.md, Getting a plan first
- Skills: Write feature requests as verifiable tasks, Review the agent's plan and adjust the scope
Domain 2. The run-and-verify loop
- Knowledge: Running locally, Tests, type checks and linting, Browser checks, Reading error messages
- Skills: Narrow down the cause from failing output, Never call work done without verifying it
Domain 3. Version control and change review
- Knowledge: Commit granularity, Branches, Reviewing diffs, Reverting
- Skills: Review agent changes through the diff, Revert a problematic commit
Domain 4. Security and dependencies
- Knowledge: Managing secrets, Environment variables, Permission modes and sandboxes, Package supply-chain risks
- Skills: Prevent secrets from being committed, Limit agent permissions to fit the task
Domain 5. Deployment and operations
- Knowledge: Preview deployments, Production deployments, Logs and monitoring, Rollback
- Skills: Run pre-deployment checks, Restore the previous version during an incident
Official documentation
OpenAI
GitHub
Vercel
Blue Belt Course · AI App Builder
Practice, mock exams and every course book are free. Pay only when you take an official test.