17 minutes12-Factor Agents: Patterns of reliable LLM applications — Dex Horthy, HumanLayer
Learn how to design AI workflows that can pause, resume, ask for human judgment and keep business state separate from model guesses.
Play videoIBM Technology. IBM's publisher description covers shadow AI, data exfiltration, access controls and model poisoning. Pair those concepts with the article's exact-tool approval and incident-reporting checks; do not infer the most common risk in your organization from this explainer.
Treat this as conceptual guidance. Confirm the exact tool, account, feature, task and data before use, including retention, connected recipients and required review. A paid account, training toggle or temporary mode does not supply permission.
Explain why personal AI accounts create workplace data risk and how to set safer boundaries.
None - watchable cold; it lands harder after the primary pick's three risk surfaces.
Last reviewed: May 18, 2026
Continue through the same learning path with the next curated companion videos.
17 minutesLearn how to design AI workflows that can pause, resume, ask for human judgment and keep business state separate from model guesses.
32 minutesLearn how to introduce AI into localization without removing human ownership of meaning, tone, terminology and final approval.
30 minutesUnderstand triggers, actions and simple automation flow before adding AI to a business process.