Epilogue

A book like this is a snapshot of an architecture discipline that is still being written. The cognitive patterns will move; the models will improve; the Skills standard will evolve; new failure modes will be discovered and named. The shape of the discipline is more durable. Deterministic infrastructure bounds probabilistic reasoning components. Governance is enforced in the system’s structure, memory is architected, failure modes are cataloged before an incident, and traces serve as the system of record.

If the book has done its job, the reader closes it with three things: a vocabulary for talking about agentic-system architecture with peers, a set of templates (the bounding YAML, the governance pipeline, the trace schema, the skill manifest, the harness loop, the Concord worked example) to adapt, and the conviction that the architecture around the model carries more of the system’s reliability than the model itself does.

Build the architecture around the agent, not under it. The rest follows.