Lighting Practice
Lighting Lab is an interactive 3D studio where students practice intro-level lighting. They place five types of set lights (Fresnel, LED panel, softbox, bounce board, practical lamp) around a character and adjust power, color temperature, angle, height, distance, softness, and beam width. They can pose up to three characters and choose the shot size, lens, and camera angle. A second mode, "Identify," shows a lit portrait and asks which setup was used: butterfly, loop, Rembrandt, split, clamshell, three-point, backlight, or flat. A third mode, "Build," gives students a pose and a setup name and asks them to light it themselves, then checks their work requirement by requirement.
How I used AI
How it was built
I built it in conversation with Claude, Anthropic's AI assistant. I started with a plain-language brief: a browser-based practice tool for intro lighting, with basic set lights and adjustable properties, characters and camera setups, and a quiz on classic setups across different poses. Claude wrote the code (HTML, CSS, and JavaScript, using the open-source three.js library for the 3D) and tested the quiz logic. I did the director's job: set the vision, reviewed what came back, and decided what a first-year student needs to see. The finished build is a single file that drops into a website or LMS page.
Lighting Lab is a 3D practice studio where students place real set lights around a character, then test themselves: identify the lighting setup in a portrait, or build butterfly, Rembrandt, clamshell, three-point, and more from a pose and a name. Built with Claude and directed by an instructor, it runs in any browser and drops into a website or LMS.
AI worked as a build partner and rapid prototyper. I described what I wanted in plain language, and it handled the implementation. The expertise stayed with me: which setups matter at the intro level, what each one should look like, and where students get confused. Because the AI drafted the setup rules and the angle ranges the Build checker uses, I review them against professional practice, as I would any draft, before students use them.
Why it matters for teaching
I built it in conversation with Claude, Anthropic's AI assistant. I started with a plain-language brief: a browser-based practice tool for intro lighting, with basic set lights and adjustable properties, characters and camera setups, and a quiz on classic setups across different poses. Claude wrote the code (HTML, CSS, and JavaScript, using the open-source three.js library for the 3D) and tested the quiz logic. I did the director's job: set the vision, reviewed what came back, and decided what a first-year student needs to see. The finished build is a single file that drops into a website or LMS page.
Learning by doing. Students see how moving a light changes the shadow under the nose, the catchlights, and the rim on the hair, instead of memorizing diagrams.
Different poses, different answers. Lighting angles are measured from where the subject's nose points, so students learn that the same light position looks different on a turned head. Short and broad lighting only make sense this way.
Feedback they can act on. The Identify quiz explains what to look for and what the setup is used for. Build marks each requirement as met or not and says how to fix it. A hint and a show-solution button are always available.
Camera and exposure in context. Shot size, lens, white balance, and exposure are in the same scene, so students see the lighting and the camera choices together.
Ready for the real set. Students learn the vocabulary and the standard setups before their first lab shoot.
Flexible. Use it as a pre-lab warm-up, a review, or a self-paced intro. It runs in a browser on laptops, tablets, and phones, with no install and no accounts. The app stores nothing about students. Scores are shown during a session and reset when the page reloads.
A model for what's possible. With clear learning goals and an AI partner, an instructor can build a custom teaching tool without a developer.