Multi-Agent Systems
Coordinating specialised agents through orchestrators, planners and shared state. Patterns for delegation, conflict resolution and handoffs.
A living index of the systems I study, build and document — from multi-agent coordination to production reliability patterns. Each track is a vertical of related breakdowns.
Coordinating specialised agents through orchestrators, planners and shared state. Patterns for delegation, conflict resolution and handoffs.
Short-term working memory, episodic recall, vector-based semantic memory and long-horizon context compression strategies.
From naive retrieval to hybrid, agentic and graph RAG. Choosing the right retrieval substrate for your domain.
Model Context Protocol patterns for tool servers, resource exposure and cross-process agent capability sharing.
Offline and online evaluation pipelines, LLM-as-judge designs, regression suites, traces and continuous quality measurement.
Reliability, cost control, observability, guardrails, fallbacks and the operational shape of AI systems in production.