Home | The Agent Engineer

The Agent Engineer

Deep dives on building AI agents that actually ship — the real problems startups hit between a clean demo and real users, and how they're solving them. Claude Code internals, production LLM patterns, and the stuff that breaks in production.

Featured

I bought a Mac Mini to run a 9B model. "Hello" took a minute.

Jun 14, 2026

•

2 min read

LLM Concepts

I bought a Mac Mini to run a 9B model. "Hello" took a minute.

I typed "hello" and watched the cursor blink. Sixty seconds later, one word came back.

Yatharth Lakhera

Latest Articles

The biggest speedup in local inference is one you never turned on

Jul 1, 2026

•

2 min read

Optimization techniques

The biggest speedup in local inference is one you never turned on

To work through your prompt, attention compares every token with every other token. A thousand tokens means a thousand-by-thousand grid of comparisons. Flash attention just refuses to build the grid.

Yatharth Lakhera

Speculative decoding isn't free. It's a bet you can lose.

Jun 28, 2026

•

2 min read

Optimization techniques

Speculative decoding isn't free. It's a bet you can lose.

Best case, several tokens for the price of one. Worst case, slower than doing nothing. And what you're wagering on is how predictable your output is.

Yatharth Lakhera

The runtime is the new API. You already picked one.

Jun 27, 2026

•

2 min read

LLM Concepts

The runtime is the new API. You already picked one.

I went local to stop letting a company quietly decide things for me. My third command was ollama run. And just like that, something was quietly deciding everything again.

Yatharth Lakhera