- Discuss this with your agent
- Open in Claude
- Open in ChatGPT
Turning 3,000+ hours of video into searchable data required ditching the AI hype. See how local models, automated transcription pipelines, and agent-ready Markdown solved a massive content discovery problem.
Matching moments
More from HalfStack Vienna 2026
Upcoming sessions on this topic
Starts in 5 days
Conference India 2026
November 25โ26, 2026
Bengaluru, India
-
Beware of Strangers Bearing Code: Open Source Trust in the Agent Era
Vikram Vaswani
Wed 25 Nov ยท Stage 3 - powered by GitHub
-
Ship Happens: Guardrails for AI-Written Code
Anthony Nguyen ยท LaunchDarkly
Wed 25 Nov ยท Stage 3 - powered by GitHub
-
The 200,000 line code repository: My AI wrote 1000 lines. I needed 100.
Hardik Gupta ยท IBM
Thu 26 Nov ยท Stage 1 - powered by IBM
Related videos
Related articles
CH
Chris Heilmann
CH
Chris Heilmann
BR
Benjamin Ruschin
CH
Chris Heilmann
From learning to earning
Jobs that call for the skills explored in this talk.
18 days ago
โข
Senior Software Engineer - Semantic Data Lake (Open)SDE3
WEX
Bengaluru, India
Expert
Hybrid ยท 4 days on-site
Scala
Python
Terraform
26 days ago
Staff Developer Advocate, GitHub Security Lab
GitHub
San Francisco, CA, United States
Experienced
$323k
Git
Github
Databases
19 days ago
Senior Web Software Architect, AI Experiences
TeamViewer Germany GmbH
Austin, TX, United States
Expert
ReactJS
TypeScript
TeamViewer
18 days ago
โข
Software Development Engineer 4 - Database Engineer
WEX
Bengaluru, India
Expert
Hybrid ยท 3 days on-site
ETL
T-SQL
Microsoft SQL Server
26 days ago
Staff Product Manager, Platform
GitHub
San Francisco, CA, United States
Expert
Github
Data Analytics
Machine Learning
26 days ago
Principal Product Manager, Platform
GitHub
San Francisco, CA, United States
Expert
Github
Data Analytics
Machine Learning