How I AI
“Nobody Wanted to Do This Work”: How Emmy Award–Winning Filmmakers Use AI to Automate the Tedious Parts of Documentaries
How I AI
•November 17, 2025•47 min
0
How I AI•Nov 17, 2025
Why It Matters
The workflow shows that AI can eliminate tedious archival tasks, freeing filmmakers to focus on storytelling and setting a scalable model for media‑intensive industries.
Key Takeaways
- •AI extracts metadata from thousands of archival assets automatically
- •Custom iOS app turns chaotic research into searchable database
- •OCR and Whisper convert illegible documents and audio to text
- •Vector embeddings enable semantic search across massive footage libraries
- •Different models (Claude, OpenAI, Whisper) optimize workflow steps
Pulse Analysis
Documentary filmmakers have long wrestled with the sheer volume of historical material required for a single series. Traditional cataloguing methods involve manual tagging, frame‑by‑frame review, and painstaking transcription—processes that can stall production for months. By deploying AI models that automatically read, describe, and index images, video frames, and audio snippets, studios like Florentine Films can transform raw archives into structured, queryable datasets. This shift not only accelerates the research phase but also reduces the risk of overlooking valuable content hidden in unorganized files.
The technical backbone of McAleer’s solution blends several specialized AI services. Claude assists in generating robust code for the metadata pipeline, while OpenAI’s Vision API supplies image classification and captioning. Whisper handles high‑accuracy speech‑to‑text conversion, and custom OCR tools decode faded documents that were previously unreadable. All extracted data is embedded as vectors, enabling semantic search that goes beyond keyword matching to retrieve contextually similar footage. The resulting iOS app, "Flip Flop," lets researchers capture field notes and instantly sync them with the central database, ensuring that every new asset is immediately searchable.
Beyond the immediate efficiency gains, this approach signals a broader industry trend: AI as a collaborative assistant rather than a creative replacement. By automating repetitive tasks, production teams can allocate more resources to narrative development, interview preparation, and visual storytelling. The modular nature of the system—choosing the optimal model for each task—offers a template that other media companies can adapt to their own archives. As AI tools become more accessible, we can expect a wave of custom solutions that democratize high‑quality documentary production, ultimately enriching the cultural record with faster, more comprehensive storytelling.
Episode Description
Tim McAleer is a producer at Ken Burns’s Florentine Films who is responsible for the technology and processes that power their documentary production. Rather than using AI to generate creative content, Tim has built custom AI-powered tools that automate the most tedious parts of documentary filmmaking: organizing and extracting metadata from tens of thousands of archival images, videos, and audio files. In this episode, Tim demonstrates how he’s transformed post-production workflows using AI to make vast archives of historical material actually usable and searchable.
What you’ll learn:
How Tim built an AI system that automatically extracts and embeds metadata into archival images and footage
The custom iOS app he created that transforms chaotic archival research into structured, searchable data
How AI-powered OCR is making previously illegible historical documents accessible
Why Tim uses different AI models for different tasks (Claude for coding, OpenAI for images, Whisper for audio)
How vector embeddings enable semantic search across massive documentary archives
A practical approach to building custom AI tools that solve specific workflow problems
Why AI is most valuable for automating tedious tasks rather than replacing creative work
—
Brought to you by:
Brex—The intelligent finance platform built for founders
—
Where to find Tim McAleer:
Website: https://timmcaleer.com/
LinkedIn: https://www.linkedin.com/in/timmcaleer/
—
Where to find Claire Vo:
ChatPRD: https://www.chatprd.ai/
Website: https://clairevo.com/
LinkedIn: https://www.linkedin.com/in/clairevo/
X: https://x.com/clairevo
—
In this episode, we cover:
(00:00) Introduction to Tim McAleer
(02:23) The scale of media management in documentary filmmaking
(04:16) Building a database system for archival assets
(06:02) Early experiments with AI image description
(08:59) Adding metadata extraction to improve accuracy
(12:54) Scaling from single scripts to a complete REST API
(15:16) Processing video with frame sampling and audio transcription
(19:10) Implementing vector embeddings for semantic search
(21:22) How AI frees up researchers to focus on content discovery
(24:21) Demo of “Flip Flop” iOS app for field research
(29:33) How structured file naming improves workflow efficiency
(32:20) “OCR Party” app for processing historical documents
(34:56) The versatility of different app form factors for specific workflows
(40:34) Learning approach and parallels with creative software
(42:00) Perspectives on AI in the film industry
(44:05) Prompting techniques and troubleshooting AI workflows
—
Tools referenced:
• Claude: https://claude.ai/
• ChatGPT: https://chat.openai.com/
• OpenAI Vision API: https://platform.openai.com/docs/guides/vision
• Whisper: https://github.com/openai/whisper
• Cursor: https://cursor.sh/
• Superwhisper: https://superwhisper.com/
• CLIP: https://github.com/openai/CLIP
• Gemini: https://deepmind.google/technologies/gemini/
—
Other references:
• Florentine Films: https://www.florentinefilms.com/
• Ken Burns: https://www.pbs.org/kenburns/
• Muhammad Ali documentary: https://www.pbs.org/kenburns/muhammad-ali/
• The American Revolution series: https://www.pbs.org/kenburns/the-american-revolution/
• Archival Producers Alliance: https://www.archivalproducersalliance.com/genai-guidelines
• Exif metadata standard: https://en.wikipedia.org/wiki/Exif
• Library of Congress: https://www.loc.gov/
—
Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email jordan@penname.co.
Show Notes
0
Comments
Want to join the conversation?
Loading comments...