ai-engineering
The Prompt Is Not the Product: A Realistic Mental Model for AI Agents
Recently I fed an AI agent a prompt that, stripped to its essence, said this: Build me an app people will pay for, and an AI agent…
AI Engineering
7 posts RSS
ai-engineering
Securing LLM API Keys with AWS KMS
A prompt-injection researcher points your app's own debug endpoint at itself, triggers an unhandled exception, and your error hand…
ai-engineering
LLM Observability with OpenTelemetry
Your LLM feature works in the demo. Then it ships. A week later finance forwards a cloud bill with a line item that tripled, a cus…
ai-engineering
Building an MCP Server in TypeScript
A support agent asks your assistant, "What is the status of order 4417?" The model does not know. It has never seen your database,…
ai-engineering
Prompt Injection: A Threat Model for LLM Apps
Your support agent has a new superpower. It reads the customer's ticket, looks up their account, and drafts a refund. To do that w…
ai-engineering
How I Actually Use AI to Ship Code: Context Engineering Over Clever Prompts
The last post in this series was about what not to feed an AI: keep your secrets out of the prompt. This one is the other half of…
ai-engineering
Using AI Without Leaking Your Secrets: A Threat Model for AI-Assisted Development
Someone hits an error, copies the whole stack trace into a chat window, and asks the model to "just figure this out fast." Buried…