Built AI / Case study

Call notes in.
Shooting docs out.

  1. 01

    Call notes

    Input
  2. 02

    Pitch deck copy

    Claude skill
  3. 03

    Google Slides

    Slides API
  4. 04

    Script approved

    Director
  5. 05

    Pre-production deck

    Claude + Python
  6. 06

    Call sheet

    Spreadsheet
The system at a glance

The machine moves the work.
People check it.

Each step hands a finished document to the next. Between them, people check the work: script approval, product details and brand guidelines, among others.

AI needs humans to perform well in the marketplace at the moment, so I find strategic check points for it. I know what it does well, and where it needs the human touch.

6Custom AI skills
5Automated steps
3+Human checkpoints
35%+Faster pre-production, 6 weeks down to under 4
The problem

Pre-production took six weeks.

Every commercial moves through the same process. Call notes become a pitch deck. Won pitches become a script. An approved script becomes a pre-production deck. That deck becomes a call sheet for the shoot.

That is the norm on a typical project, before a single frame is shot.

What I built

Six skills. One pipeline.

01

Pitch deck copy

Turns discovery call notes and a brand’s website into finished pitch sections.

02

Pitch to Slides

Writes that copy straight into the studio’s Google Slides template through the API. No copying and pasting.

03

Pre-production deck builder

Takes an approved script and a reference deck, and builds a complete new pre-production deck. I later rebuilt it as a single-run Python script.

04

Call sheet generator

Converts the finished deck into a shooting schedule in the studio’s standard call sheet format.

05

Wizard agent

A browser agent that completes the studio’s five-step pre-production wizard: objectives, characters, scripts, storyboards and casting.

06

Style enforcer

One writing standard on every output. Short sentences, a banned-word list, and script conventions like frame numbers from 101 and INT./EXT. headers.

The human checkpoints

The AI drafts. People decide.

Automation never gets the final word. A person approves every script before the deck is built. People QC every product detail. People check every output against the brand guidelines. 

When I automated everything, engagement on the final videos dropped. So I pivoted, and now humans stay in the loop at every key moment of creation. AI needs constant innovation, because clients’ needs change.

The platform

I flipped the order. The workflow worked.

The studio’s internal production platform generated a pre-production deck first, then the script. There was no room for real creative to form, and one change to the script meant starting over from scratch.

Because I understood how the models work, I proposed generating the script first. It fixed the whole workflow. The team went from constant regenerations to simple edits on the writing.

The rollout

Packaged for a team.

I moved the system into Claude Enterprise: skills packaged, context documents exported, standards built in.

The team adopted the system first. Then the company used those findings to launch its own pre-production AI platform. 

The outcome

What changed.

Pre-production dropped from six weeks to under four, more than a third faster. That is two weeks or more back on every project.

It is not a pilot. Every project now runs through the pipeline, and the entire team uses it.

Also built: a brand strategy generator on Google Gemini. An intake form in, a full content strategy draft out in 15 to 30 minutes. It ran as a lead magnet and a working test of Gemini.

The tradeoff

What I chose not to automate.

Fine-tuning the script. Reference images for pre-production. Cinematography and art direction. Anywhere a person could make the work more unique, I kept a person.

Automation took the repetitive work. The craft stayed human.

Workflow designClaude skillsGoogle Slides APIPythonBrowser automationClaude Enterprise rollout
Next AI case study

Made with AI

Read the case study
Scroll to Top