#Architecture

A2A: when the workflow IS the broker

The reference architecture distinguishes request-based and message-driven agent communication. For in-process orchestration, the workflow IS the broker — and A2A is just the wire format.

Memory done right with MAF

AgentSession is short-term memory. MemoryContextProvider + MemoryFileStore is long-term memory. Mem0 is long-term memory for serious workloads. The boundary that matters and how to implement each.

Agent registry as a project-local convention

The Microsoft Agent Framework deliberately does not ship an agent registry. Here is why that is the right call, and what to build as a project-local convention when you need one.

The 12-chapter reference architecture, in 102 Python files

Microsoft published a 12-chapter reference architecture for multi-agent systems and a separate framework — the Microsoft Agent Framework — to build them. Here is what the 102 Python files actually contain and how they map to the chapters.

Why We Migrated from Google ADK to Microsoft Agent Framework

The philosophy, trade-offs, and what we learned converting 18+ agents in 3 months.

The philosophy, trade-offs, and what we learned converting 18+ agents in 3 months. Provider abstraction as the foundation for portable agents.

Error-code orchestration — replacing a giant switch...

Status-code-based dispatch made every worker grow a longer and longer switch. Normalising every partner-specific error into an enumerated set let the orchestration logic stop changing as new partners landed.

Speaking at Google Cloud Next 2022 — the...

30 minutes on stage. The talk title looked tactical; the talk underneath was about why most microservices migrations fail and how to set up the one that doesn't.

Defence in depth for agentic AI — the eleven-layer envelope

The mental model that says no two adjacent layers share a single point of failure for the same class of attack. From TLS to OTel, the eleven layers a customer request crosses before an answer comes back.

Consolidated security deep-dive — RBAC, RLS, token...

The long-form security narrative for a multi-agent financial assistant — authentication, authorisation, tenant isolation, dual-identity audit, envelope encryption, hash-chained logs, governance, red team, BCP.

Why Go for production agentic AI

Stdlib over libraries, single binary over framework, fail-closed defaults over forgiveness. The boring-on-purpose case for choosing Go to ship a multi-agent system into a regulated environment.

Agent Pipeline

An Agent is a layered pipeline — knowing the layers tells you exactly where to plug in.

The layered execution model of a Microsoft Agent Framework agent: agent middleware, RawAgent, context providers, and the separate swappable ChatClient pipeline.

Agentic architecture on the Microsoft Agent Framework —...

Microsoft's Multi-Agent Reference Architecture in Go. Protocol, registry, bus, governance, orchestration, observability, evaluation — and how the seven hold each other up.

Google Cloud's 12 agent design patterns — mapped to real...

Google publishes a 12-pattern taxonomy for agent design. Most of them have direct corollaries in production code; one or two are best ignored. The mapping I've used.

The case for boring stack choices in regulated AI

Postgres over the latest vector DB. Go stdlib over the framework du jour. Single binary over Kubernetes operator. The choices that bore reviewers and delight on-call engineers.

Audit logs are the API of record

The audit log isn't a side effect of the system. It's the contract you owe to regulators, customers, and your future self. Treat it as a first-class API — schema, versioning, and SLOs included.