Notes on building AI agents, LLM systems, and software that holds up in production.
A hands-on walkthrough that builds up the agent loop one cell at a time, from a plain LLM that can only produce text to an agent that chains tools to finish a real task.
LLMs don't fail because they're dumb, they fail because every fact, instruction, and document has to fit in a fixed token budget. Here's why, and the engineering that fixes it.
A from-scratch agentic CLI that turns one sentence into a formatted .xlsx: formulas, charts, conditional formatting, and a validator the agent writes for itself. No framework. One brain, two wire protocols.
I built a leaky integrate-and-fire spiking network in snnTorch that reaches 98% on MNIST using discrete spikes over time instead of continuous activations. Here is how event-driven inference actually works, and why it matters for edge hardware.