These 5 security layers are non-negotiable when shipping AI to production (don't ship to production without these) Layer 1: Input. Validate and sanitize everything coming in. Block prompt injection at the door. Layer 2: Policy. Your model shouldn't have full access to your
@whats_ai
-
Full Breakdown of Designing GenAI Systems From Scratch
By
–
We wrote a full breakdown of how GenAI systems are actually designed from scratch.
— Louis-François Bouchard 🎥🤖 (@Whats_AI) 5 juin 2026
It went out in Neo Kim's "The System Design Newsletter":
Generative AI Masterclass: Everything You Need to Know to Design GenAI Systems From Scratch.
If you're a beginner in LLMs, this is for… pic.twitter.com/SBuWEne0CJWe wrote a full breakdown of how GenAI systems are actually designed from scratch. It went out in Neo Kim's "The System Design Newsletter": Generative AI Masterclass: Everything You Need to Know to Design GenAI Systems From Scratch. If you're a beginner in LLMs, this is for
-
Using one model vs splitting tasks across models
By
–
Are you using the same model for everything or splitting tasks across models?
-
Using Opus for every workflow step leads to context dumping
By
–
If you are using Opus for every single step in your workflow, then this post is for you! For example:
searching logs,
finding the right file,
checking where an error happened,
looking through a repo for one function. Then people dump all of that into the same context window and -
The transformer inside an LLM: two blocks repeated
By
–
In our AI engineering workshops, one question comes up over and over. What's actually inside an LLM? The answer is one word. 𝗔 𝘁𝗿𝗮𝗻𝘀𝗳𝗼𝗿𝗺𝗲𝗿. And it's much simpler than the name makes it sound. A transformer is just two blocks, repeated many times. 𝗕𝗹𝗼𝗰𝗸 𝟭
-
Systematic failures in long agent runs: repetition, forgetting, high API bill
By
–
You have probably seen this with Claude Code or any long agent run: – it repeats work
– it forgets a decision
– it argues with stale instructions
– it misses the exact file you mentioned earlier
– the API bill keeps climbing That is not random. -
AI Agents Have Three Memory Layers: Working Memory
By
–
You use AI agents every day.
ChatGPT, Claude, Gemini, Cursor. They remember what you said, who you are, and what you've worked on before. But this memory has three layers, not one. Working memory
Your current chat. Whatever you typed five messages ago. Gone when you close -
From Stack Overflow bug to autonomous features in 5 years
By
–
How did we go from opening Stack Overflow to solve one bug, to agents writing entire features on their own? That didn’t happen overnight, but in slow progress in about 5 years. And today, I want to walk you through the full story. The timeline, the tools, the tweets, the
-
Coding changed forever: AI agents rewrote rules – video
By
–
Coding Changed Forever
AI agents rewrote the rules I just made a video covering everything since the AI boom Watch it here: https://
youtu.be/ShFn3MG0h8s -
Boring context compaction beats multi-agent systems for most use cases
By
–
I've built multi-agent systems for clients. I still think they're overrated for most use cases. What's underrated is boring. Context compaction. The reason your AI app feels slow and expensive isn't the model. It's everything you keep stuffing into the prompt before it even