I asked an AI to make my career-switch video. It took 9 versions, 666 frames and no video editor

A software engineer and AI master's student used Claude Opus 5.5 in Cowork to produce a 45-second career-switch video entirely from code, iterating through nine versions and 666 frames rendered headless with Playwright and encoded with ffmpeg. The pipeline draws each frame as a deterministic pure function of frame number, generates the soundtrack in Python, and adds narration via ElevenLabs through an MCP connector, with no video editor involved.

I'm a software engineer with 16 years behind me, now halfway through a double MSc in AI EPITA × EM Normandie, the AIMS programme . In October I start looking for my end-of-studies internship. I needed one thing first: a short video that tells my story on LinkedIn. I don't do motion design. I don't own After Effects. So I tried something else: I asked Claude Opus 5.5 in Cowork to make it with me, from a one-line prompt typed half in French. This is the log of that session: what got built, how it works, where the AI pushed back, and what I'm taking away for my studies. <canvas , rendered headless with Playwright, encoded with ffmpeg. The soundtrack is generated in Python. The voice comes from ElevenLabs through an MCP connector. My first message was roughly: "create in stop-motion / JS / Canva HTML a video telling my move into AI leaving Prisma Media, the MSc AIMS to improve…" , and I hit Enter mid-sentence. Instead of guessing, it asked four questions with clickable answers: what the video is for, which format, which tone and length, which language. I picked LinkedIn personal branding, HTML + MP4, punchy ~45 s, English . That took ten seconds and saved at least two wrong versions. As a marketing-strategy student, this is the part I'd frame as a mini VSL video sales letter : a hook, a story, proof, and one call to action. The AI didn't use that word, but the structure it proposed was exactly that. The look is cut paper on a green cutting mat. Stop-motion is mostly two tricks: The whole video is one pure function: draw frameNumber . Given a frame number it paints that exact frame, with deterministic randomness. That's what makes it renderable, repeatable and cheap to fix. js // deterministic noise: same frame + same id = same jitter function hash a, b { let h = Math.imul a | 0, 374761393 + Math.imul b | 0, 668265263 ; h = Math.imul h ^ h 13 , 1274126177 ; return h ^ h 16 0 / 4294967296; } const jit = f, id, amount = hash f, id - 0.5 2 amount; // every paper piece goes through put : position + rotation + a little boil function put f, id, x, y, rot, scale, draw { ctx.save ; ctx.translate x + jit f, id 7 + 1, 1.7 , y + jit f, id 7 + 2, 1.7 ; ctx.rotate rot + jit f, id 7 + 3, 0.006 ; ctx.scale scale, scale ; draw ; ctx.restore ; } Paper pieces are polygons with slightly irregular edges, a drop shadow and a grain texture. Scenes are plain functions of local time: pop in, hold, slide out. The renderer is eight lines of Playwright that call draw i for each of the 666 frames and save a JPEG; ffmpeg turns them into an MP4. The same file also runs live in the browser as a player with a scrubber and chapter buttons, so I could review a scene without waiting for a render. | Version | What I asked for | What changed | |---|---|---| | v1 | The first draft | 7 scenes, paper cut-outs, 45 s, silent | | v2 | "From software engineer to AI engineer", a little character of me, the real master's name | Character with a "Software Engineer" cap that swaps for an "AI" cap | | v3 | Focus on GenAI, not ML. Don't say I was let go. Add sound. | A signpost scene "Same road" → "New path: AI" , a chat window that streams an LLM answer, procedural music and sound effects | | v4 | Shorter beard, school logos my files , less repetitive music | The track now changes with each scene, with a build-up and a drop on the cap swap | | v5 | Hoodie back, a laptop with the logo I supplied, a lighter beard, a glitch at frame 150 | Fixed a scene that hid its props one frame too early | | v6–v7 | A minimalist end card with a QR code that points straight to my site, with UTM tags | QR code generated locally, verified by decoding the final MP4 frame | | v8 | "AI" is too close to the end of the sign | Longer sign | | v9 | The ElevenLabs narration | Scenes re-timed to the voice, music ducked under it | Two things made this loop fast. First, it rendered contact sheets a grid of key frames and looked at them itself before sending me anything; it caught overlapping text and a cut-off arm that way. Second, when I asked for a new look for "me", it showed me one still frame for approval before re-rendering 666 frames. This is the part that surprised me most. Effects come from the animation code. Every time a piece pops in, slides or flips, the scene code logs a cue with its exact timestamp. The audio script reads that list and places a sample on each cue: pops, paper slaps, whooshes, a wooden knock for the signpost, pencil scratches for the checkmarks, keyboard clicks while the chat types. Change the animation and the sound follows. js const popS = t, d, dur = .42 = { cue 'pop', d ; / …scale-in easing… / }; The music is generated in Python with numpy: plucked arpeggios, bass, a few drum sounds, a pad. My feedback after v3 was "too repetitive", so v4 got one arrangement per scene: a quiet intro, a groove, a breakdown, a build-up into the cap swap, a chorus with a lead melody, and an outro. The narrator is a third-person, slightly self-mocking storyteller "He talks to language models all day. They talk back." . Once I connected the ElevenLabs connector, Claude picked a voice from the library and generated the takes. Then it found the sentence boundaries by measuring silences, re-timed every scene to the voice the new cap lands exactly on "He switched caps" , and lowered the music automatically under the speech. This is what I'd want to know before trying it myself. draw frame as a pure function meant every fix was a small diff and a re-render, never a re-shoot. Once the video was done, I asked for the look to be exported so another coding agent can rebuild my website in the same style. I got colour and type tokens, the fonts, twelve HTML/CSS components paper labels, sticky notes, the checklist, the chat window, the signpost… , the character in four poses, and a content deck with every section's copy. That's the next project. I'm Hamdi, a software engineer turning AI engineer, looking for a 6-month internship as an Applied / Forward Deployed AI Engineer. If you're building with LLMs in production, I'd like to hear from you: h4md1.fr https://www.h4md1.fr/?utm source=devto&utm medium=article&utm campaign=ai reboot 2026 · LinkedIn https://www.linkedin.com/in/hamdilaadhari .