12-Factor Agents: Patterns of reliable LLM applications — Dex Horthy, HumanLayer
AI Engineer. Dex Horthy explains why reliable agent systems are mostly disciplined software around a few LLM calls: own the prompt, own the context window, keep control flow deterministic and use tool calls to contact humans when the workflow needs judgment. That maps directly to the article's approval, exception and escalation patterns.
AI Expert note
Treat the "agent" framing as software architecture, not autonomy theatre. The durable lesson is explicit state, deterministic control flow and a real human handoff path.
What you should get from this
Learn how to design AI workflows that can pause, resume, ask for human judgment and keep business state separate from model guesses.
Watch or know first
Basic familiarity with tool-calling or multi-step AI workflows.
Watch next
Continue through the same learning path with the next curated companion videos.
32 minutesHow to Build Human-Centered AI Workflows in Localization with Shashi Bhushan
Learn how to introduce AI into localization without removing human ownership of meaning, tone, terminology and final approval.
Watch next
19 minutesGPT Actions and Automations with Zapier AI Actions
Understand the assistant-to-automation pattern before deciding whether Zapier, Make, n8n or MCP should own the actual action.
Watch next
30 minutesHow to use Zapier: Basics you need to know
Understand triggers, actions and simple automation flow before adding AI to a business process.
Watch nextRelated videos
18 minutesAWS re:Invent 2025 - Implementing Human-in-the-Loop Controls for Multi-Agent AI Systems (CNS428)
6 minutesAI Voice Agents: How They Actually Work & Why They Sound So Human
8 minutesAnthropic's Claude Computer Use Is A Game Changer | YC Decoded
5 minutesClaude has taken control of my computer...
Take it further
Hand-picked external courses that go deeper on this topic.
Coursera · Vanderbilt UniversityChatGPT: Excel at Personal Automation with GPTs, AI & Zapier
The clearest path from "I use ChatGPT in a tab" to "my AI handles my inbox while I sleep." Three-course specialization built around Zapier — no Python required. By the end you'll have agents that summarise emails, update spreadsheets, and trigger workflows when conditions are met.
Hugging FaceAI Agents Course
The clearest open-source treatment of agentic systems available. Anchored in the three frameworks engineers actually evaluate (smolagents, LlamaIndex, LangGraph) rather than one vendor's stack. Concludes with a benchmark assignment and public leaderboard — accountability your team can verify.