Intuit For Education
Scholarship explainer timed by GPT-4 and assembled in After Effects by script
A machine-timed explainer for Intuit's scholarship-types RFP — GPT-4 acting as animation director, ExtendScript building the After Effects timeline from its JSON, boards trained on Intuit's own illustration style.
GPT-4 acted as animation director — gapless scene timings and camera moves as JSON, and ExtendScript built the After Effects timeline from it
Automated
An explainer film assembled by script
v6 · 2:06 · 9:16 · fourteen boards, timed by a model, assembled by a script
- runtime
- 2:06
- boards
- 14
- scenes
- 14, gapless
- hand-keyframed
- 0 frames
The script analyzerHundreds of scripts were possible, so the first thing built was a script analyzer. Since it was already reading the script, it generated the boards too.
- script in
- 360 words
- scenes out
- 14
- cut to
- 2:00.8
- holds
- 7.1–16.4s
- camera moves
- punch in ×4 · out ×4 · pans ×2 · held ×4
One beat at four stages — The same fifteen seconds as script, extraction, prompt and board. Nothing here is paraphrased.
-
01the script section
Jake — Athletic & Community Scholarship (0:15–0:45). Jake, a stylized baseball player, catches a ball. The scene transitions to show a split screen: one side shows a baseball field, the other a community center icon. A stylized check with “Tuition” appears, partially covered by two smaller checks labeled “Athletic Scholarship” and “Community Scholarship.”
What a human wrote.
-
02what spaCy pulled
JakeAthleticCommunityScholarshipVisualbaseballplayercatchesballscenetransitionssplitscreenbaseballfieldcommunitycentericonstylizedcheckTuitionappears JakeAthletic & Community ScholarshipVisualJakestylized baseball playerballscenesplit screenbaseball fieldcommunity center iconstylized checkTuition45 keywords by part of speech — nouns, verbs, adjectives — and 25 noun chunks kept as phrases. A sample of each is shown.
-
03the prompt it wrote
Create a 2D illustration in the style of Intuit brand videos (simple shapes, clean lines, bright colors, hand-drawn style character). Scene description: Jake, a stylized baseball player, is catching a baseball. Visual elements based on keywords and phrases: Jake, stylized baseball player, baseball, Jake, athletic, baseball, player, catches. Character style should be similar to the example video provided (simple, illustrative, 2D). Color palette should adhere to Intuit visual guidelines.
Composed from the extraction above. Nobody typed this.
-
04what came back
Artboard 03, in the brand line, from a prompt the pipeline wrote itself.
Open the build record Eleven days, from an empty file to a comp that builds itself — including the three app screens the drawing above stands in for.
the analyzer
the app
the style search
the trained line
the boards
the assembly
Stage by stageSeven stages from script to delivered cut, with the material behind each.
How the edit was assembledOne explainer, from script to cut, where the timeline is machine-built.
Three students, three scholarship mixes. A script, a voice read, and fourteen one-line board descriptions — that is everything human-authored that enters the pipeline.
under the hood
detect_silence(vo_audio, min_silence_len=500, silence_thresh=-40)
{ "scene": 12, "image": "Artboard 11.png", "start": 82.55, "end": 90.0, "camera_move": "pan_right+punch_in" } under the hood
layer.startTime = scene.start; layer.outPoint = scene.end;
layer.scale.expression = "ease(time, inPoint, outPoint, [100,100], [120,120]);"
the inputs, in full
First, meet Jake, a high-school baseball player who just earned an athletic scholarship to play at a Division II university…
Artboard 03 — Jake looking straight to camera, in a baseball uniform, with a high school baseball game in the background.
the reference set
Intuit's published illustration system — the look wasn't invented, it was matched.
drawn once, reused everywhere
One drawn cast and prop set, generated once and reused on every board.
twelve beats, two rounds
Twelve beats, two rounds each. Rest on any frame to see the round it replaced:
Twelve of the fourteen locked boards, each shown with the round it replaced.
scene timings, to scale
All fourteen scenes, gapless from 0.00 to 120.82s, every cut sitting on a silence the VO itself chose. Read straight out of intelligent_scene_timings.json — the bar is each scene's hold, to scale.
the script that writes the edit — every draft of it
- day 1boiling_script.jsx124
- day 1boiling_script_new.jsx137
- day 1dynamic_sequence_camera_moves.jsx71
- day 2ae_llm_auto_sequence_auto_dimensions.jsx71
- day 2ae_llm_auto_sequence_final.jsx54
- day 2debug_ae_import_script.jsx39
- day 2final_ae_full_script.jsx97
- day 2final_ae_json_script.jsx92
- day 2final_ae_json_script_corrected.jsx98
- day 2final_ae_json_script_fixed.jsx93
- day 2final_ae_json_script_robust.jsx98
- day 2final_updated_ae_automation.jsx97
- day 2numeric_sequence_adj_reversed.jsx78
- day 2numeric_sequence_adjustments.jsx78
- day 2quick_test_sequence.jsx51
- day 3final_ae_exact_match_script.jsx96
- day 3final_ae_script_00-13.jsx103
- day 3final_ae_script_with_pan_and_ordering.jsx104
Eighteen drafts across three days to get one ExtendScript that reads the model's JSON and builds the whole timeline. The last one is the one that ran.
six versions of the same two minutes
The same moment, 1:00 in, across all six exports. v5 is where the cut grew by five seconds. Nothing here was hand-keyframed.
A language model assigned the timing and a script built the comp.
The script, the reference art and the final picks were human work.
Project Elements
Have a Project in Mind?
Animation direction, VFX and creative technology. Message me on LinkedIn or get in touch.