Skip to content

Category

Running AI in production? See how we build it.

Production depth across six series: agent architecture, model selection, fine-tuning, infrastructure, and prompt design.

36 pieces

Engineering

Framework or platform? Choosing the right abstraction for your agent system

6 minPast the prototype, you are assembling your third agent by hand — and the coordination tax is real.

Off-the-shelf, or adapt your own?

When one agent isn't enough

Run it for real

The agent that acts (and when not to)

The augmented LLM

The LLM is a component

The Coordinator, the Worker, and the Delegator

Three lessons the human mind offers agent architecture

Cognitive Least Privilege: your agent should know only what it needs

Evaluate models on your own set, not the public leaderboard

Event-driven by design: agent teams that don't lose messages

Fine-tune, RAG, or prompt: which one, and what each costs

Common fine-tuning pitfalls and how to debug them

From prompt engineering to context engineering

The LoRA family: QLoRA, DoRA, and LoRA+ — which, and when?

LoRA hyperparameters demystified: rank, alpha, and what to set

MLP is the model's memory: where knowledge lives

PagedAttention and continuous batching: how one server answers more users