← All work Case study · Agentic AI

FilmAI

Production assistants for filmmakers who don't want AI writing their films.

OpenClaw + Claude Code Runs locally on a Mac mini In production since June 2026
4
productions, with 4 producers and their crews
~$110
a month to run
50 → 15 h
first-draft cycle (writer's estimate)
2 weeks
to build V1
01 · Problem

The problem

A small team of award-winning independent filmmakers had just finished a documentary and were turning a short film into a feature. Coordination ran on memory and goodwill, so mistakes got through. In one case, a character was left out of a day's setup.

Writing was its own struggle. They found it hard to get ideas onto the page, and then hard to see how the story was taking shape. When a detail changed late, two finished scenes had to be rewritten.

They couldn't afford a production assistant or a script editor. And they didn't want AI anywhere near the creative work.

02 · Constraints

Constraints

  • No AI-generated creative content. It never writes scenes, characters, or story.
  • Close to free to run, on hardware they own.
  • No new tools to learn. The filmmakers work in Obsidian, Docs, Slack, and email.
  • Nothing reaches cast or crew until a producer confirms it.
03 · What I built

A team of production assistants

FilmAI is a set of AI agents, each with one job. None of them writes the film.

Production managerDaily / weekly
The orchestrator. It's built on a modified version of Karpathy's LLM Wiki pattern, restructured around projects. It sets up a folder and templates for every production, from future ideas to shoots in progress. Every day it checks each project for outstanding tasks and assigns them to the other agents.
Script supervisorOn call
A thought partner, not a writer. It takes in ideas in bite-sized pieces and files them against the right script. It understands scene structure, cross-references characters and locations, and tracks continuity and intent. When it spots a contradiction or a theme drifting, it questions the writer.
Production assistantOn call
Manages the shared Excalidraw board the team uses to see and coordinate the production, including storyboards and budget.
Daily PADaily
Builds the daily reports and shot list, and collects RSVPs from cast and crew.
Location scoutOn call · in progress
Tracks locations and helps find shots.

Under the agents sit code-only workers that do the mechanical work: sending email, parsing replies, posting to Slack, writing Docs, and building investor pitch decks in Slides. They call a model only when a step needs judgment.

OpenClaw runs the agents on a Mac mini M4 Pro (48 GB) in the filmmakers' house, using a local model. It launched on Qwen 3.5 in June and moved to Ornith 1.5 (35B A3B) in July. Claude Code runs only the script supervisor.

Agents
OpenClaw · local model · Mac mini
Production manager Daily / weekly · orchestrates
Production assistant On call · board, storyboards, budget
Daily PA Daily · reports, shot list, RSVPs
Location scout On call · in progress
Claude Code
Script supervisor On call · works with the writer
Workerscode-only
Email sender after producer approval
Reply parser local model only if unclear
Slack messaging
Google Docs
Google Slides investor pitch decks
Data
Obsidian vault
Google Drive
Gmail
Web APIs
Agents decide what needs doing. Code-only workers do it. A model is called only when a step needs judgment, and a producer approves anything that reaches cast or crew.
04 · Decisions

Decisions

A production assistant, not a content generator. The filmmakers were hostile to AI until it was framed as the assistant they couldn't afford, one that never touches the creative work. That framing was the adoption strategy.

Use a model only where judgment is needed. Code writes the emails. Code reads replies first, and a local model gets only the unclear ones. Claude handles the one job that needs real reasoning: talking through a script. That's why the whole system costs about $110 a month.

Story facts live in files, not in the model's memory. Characters and locations are cross-referenced files the system checks against. That's how it can tell the writer what a late change will affect.

Run it in parallel before trusting it. FilmAI ran alongside the old way of working, so we could see what it got right and what it missed before anyone depended on it.

05 · Failure handling

How it fails, and what happens then

The daily schedule is the riskiest output, because it reaches people outside the core team. It goes through three gates:

  1. Human

    A producer reviews every schedule against the scenes being shot that day, before anything is sent.

  2. Code

    Code generates the emails, not a model, from the approved data, so nothing made-up reaches cast or crew.

  3. Code → model → human

    Replies are handled in tiers. Code handles clear replies and updates the record directly. Anything less clear goes to the local model, which returns YES or NO plus a comment. If the model can't tell either, the reply is flagged for the producer.

A real miss

During the parallel run, a sound crew member was missing from a daily schedule. The producer caught it at review. The model wasn't the cause: that person had never been entered into the system. The fix was structural. Crew who are always needed are now flagged and selected before any schedule is generated, so the same gap can't recur silently.

06 · Results

Results

  • In daily use by 4 producers and their crews across 4 productions.
  • About $110 a month to run: $108 for four Claude seats and $1–2 in power. In heavy writing weeks they buy extra usage credits, or the writer moves up a plan.
  • First-draft cycle went from about 50 hours to about 15, by the writer's own estimate.
  • It catches what a script editor would. In a horror short, the first three scenes were deliberately oblique. The supervisor flagged the fourth as on-the-nose, and the writer rewrote it.
  • Built in about two weeks to V1, and in production since June 2026.
07 · Next

What's next

  • Finish the location scout.
  • Keep iterating on what the producers report back.

Building something like this?

I build AI and automation systems around how people actually work, and make sure they get adopted.