Securing AI Agents from Doing Bad Things
Show notes for AI Explained Part 31 — sandboxing, permission scoping, instruction hierarchy, and the metrics that tell you whether your agent is safe to ship.
#ai-explained
The AI Explained series: short, focused episodes on individual AI building blocks — transformers, attention, tokenization, memory, tool use, multi-agent systems, and more.
11 posts below, newest first.
AI Explained: Finally Understand AI Errors & Human-in-the-Loop (HITL) (Part 30)
Feeling overwhelmed by the fear of AI making huge mistakes? In this video, we break it down into simple pieces.
AI Explained: Semantic Caching & State Management for AI Agents (Part 29)
Feeling overwhelmed by high AI API costs and latency? In this video, we break it down into simple pieces.
AI Explained: Short-Term vs Long-Term AI Memory Demystified (Part 28)
Feeling overwhelmed by the different layers of AI memory? In this video, we break it down into simple pieces.
AI Explained: Finally Understand How AI Agents Remember You (Part 27)
Feeling overwhelmed by memory and state tracking? In this video, we break it down into simple pieces.
AI Explained: Multi-Agent AI Systems for Complete Beginners (Part 26)
Feeling overwhelmed by the idea of communicating AIs? In this video, we break it down into simple pieces.
AI Explained: How AI Uses Tools - ReAct Loop & Tool Use Demystified (Part 25)
Feeling overwhelmed by APIs and AI Tool Integration? In this video, we break it down into simple pieces.
AI Explained: Finally Understand Autonomous AI Agents & Agentic RAG (Part 24)
Feeling overwhelmed by the hype around "AI Agents"? This video is your ultimate guide to finally understanding AI Agents and Agentic RAG, even if you're completely new…
AI Explained: Finally Understand the Magic of Transformers | Attention (Part 3)
Feeling overwhelmed by Transformer architecture diagrams? In this video, we break it down into simple pieces.
AI Explained: Tokenization for Non-Math People (Part 2)
Ever wonder why AI makes simple math or spelling mistakes? This video demystifies tokenization, breaking down how AI cuts up English words into puzzle pieces.
AI Explained: Finally Understand How AI Works - No Code (Part 1)
Unlock the secrets of AI in this masterclass! Part 1 simplifies how AI works, especially Large Language Models like ChatGPT, without any code.
Related topics
Subjects that frequently appear alongside #ai-explained. Click through to see every post on each one.
#ai 11 posts
How LLMs actually work — tokenization, embeddings, RAG, fine-tuning, agents — explained for engineers who ship production code, not papers.
#llm 11 posts
Large language models — how they think, why they fail, what RAG fixes, and how to evaluate them. The fundamentals every engineer building on top of an LLM should internalise.
#ai-agents 1 post
How autonomous AI agents reason, plan, use tools, and stay aligned with your intent — the ReAct loop, agentic RAG, and multi-agent orchestration.
#security 1 post
Practical software security for engineers — secrets handling, threat modelling, least privilege, prompt injection, sandboxing, and AI-specific attack surfaces.