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.

Latest Articles

Aug 7, 2026

•

4 min read

Optimization techniques

+1

Send Your Retriever a Query, Not a Transcript

Most multi-turn RAG chatbots work like this: append each turn to a message list, send the whole thing, let the model sort it out. Splitting them is a small change with a measurable payoff.

Yatharth Lakhera

Jul 1, 2026

•

2 min read

Optimization techniques

+2

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

Jun 28, 2026

•

2 min read

Optimization techniques

+2

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

Load more