videos
Every lesson
14 videos, newest first. Prefer an order? Start a series.
Context Rot Explained
Models read long prompts worse than short ones. Why context rot happens, what the research shows, how to measure it in your app, and what to trim.
How to Sandbox AI Agents (and What It Won't Stop)
Your agent's commands run as you. How a file wall and a network wall contain it, how strong the wall should be, and the four gaps a sandbox leaves open.
What an Agent Harness Is, and a Tiny One You Can Build
An agent is a model plus a harness: the loop, tools, stop rules, context trimming and permissions around it. Here's each part, and a tiny harness in Python.
Prompt Injection Explained: What Actually Stops the Bad Tool Call
Why an LLM obeys instructions hidden in a web page or email, how a markdown image leaks your chat, why filters fall to adaptive attacks, and the design patterns that actually hold.
Observability for LLM Apps
How to catch the failures your dashboard says aren't happening: traces, spans, what to log on every model call, privacy, sampling, quality scores and alerts.
MCP Server Security: Scoping Tools So an Agent Can't Wreck Things
Whatever your MCP server can do, your agent can do. Remove tools, pin descriptions, confirm writes, give the agent its own role, check every call and log it.
Rate Limiting LLM APIs: Token Buckets, Queues and 429s
How OpenAI and Anthropic rate limit you (requests and tokens, token buckets, 429s) and how to stay under it: your own bucket, a queue, the batch API, one shared limiter.
Caching LLM Calls: Prompt, Exact and Semantic
Stop paying for the same tokens on every call: how prompt caching works, the prompt order that keeps it hitting, and when exact or semantic caching is safe.
RAG That Actually Retrieves the Right Thing
Most bad RAG answers start in search. Fix retrieval with structure-aware chunks, hybrid keyword plus vector search, a reranker, and a recall test you can rerun.
Supply-Chain Attacks on AI Apps: How a pip install Steals Your Keys
How a poisoned LiteLLM release ran at Python startup without an import, how attackers got it through an official pipeline, and how pins, hashes, cooldowns and digests stop it.
Structured Outputs: Reliable JSON from a Model
Why please return JSON breaks in production, and the ladder that fixes it: JSON mode, constrained decoding, tool calling, then validate and retry.
Agents in Production: Why They Loop
Why your agent can loop all weekend, and the guardrails that make it stop: step caps, budgets, timeouts, loop detection, idempotent tools, a kill switch and traces.
Retries, Timeouts and Fallbacks for LLM Calls
Why instant retries make an outage worse and why 200 OK can lie: backoff with jitter, Retry-After, timeout budgets, idempotency keys and tested fallbacks.
How LLM Evals Work
Vibes are not a test suite. Build your first LLM eval: a dataset from real failures, your real app, and a grader you can trust, wired into CI.
