Deep-Dives

Deep-Dives

Engineering fundamentals — architectures, memory, RAG, protocols, tools, reasoning, training, multi-agent.

These essays assume Concepts fluency — new here? Start with Concepts →

Architectures & Patterns

Reusable agent architectures — ReAct, plan-and-execute, supervisor-worker, router, reflection — and when each fits.

Protocols & Interop

The protocol layer of the agent stack — MCP, A2A, tool-calling standards, capability discovery — and how systems plug together.

Building, testing, securing, and operating Model Context Protocol servers — the practical layer above mcp-architecture's conceptual introduction.

Memory & Context

Context windows, memory stores, compaction, retrieval-augmented memory — keeping the right things on the prompt.

Retrieval & RAG

Retrieval-augmented generation past the basics — advanced architectures, graph RAG, retrieval as an agent tool, RAG security.

Training Agentic Models

Post-training for agentic ability — SFT, rejection sampling, distillation, RLHF/RLAIF, RL for tool use, reward design.

Multi-Agent Systems

When multiple agents pay off, when one beats many, and the topologies, failure modes and debate patterns in between.

Securing a production agent end-to-end — injection defense, policy-as-code, identity and attestation, red-teaming, isolation, and the audit primitives that shipped in 2026.

Evaluating Agents

The 2026 discipline of evaluating agents: benchmark saturation, judge calibration, drift detection, and the eval methodologies that survived contact with production.

Reasoning & Test-Time Compute

Chain of thought, self-consistency, tree/graph of thought, and the inference-time-scaling laws that govern them.

Tool & Capability Design

Designing tools an agent can actually use — granularity, schemas, error messages, recovery, antipatterns.