The 21 architectural patterns that underpin every production AI system - each mapped to PSF safety domains and PAI-8 governance controls, with enterprise examples, production failure modes, and implementation checklists. Written for practitioners who need to deploy, govern, and audit these systems.
Once a pattern maps to your system or client conversation, move into the path that creates proof, revenue, or a working design.
I am designing a system
Use Studio to turn patterns into a concrete PSF-mapped workflow instead of a whiteboard diagram nobody owns.
Open Studio →I need evidence
Run the readiness check when the pattern is already implemented in a live or high-consequence AI deployment.
Run readiness check →I follow the record
Incident records show which patterns held and which failed - inspect the evidence behind each one.
Open incident registry →I need the standard
Every pattern maps to PSF domains. Read the standard to see which controls the pattern is doing the work of.
Read the PSF →The seven foundational patterns every production AI practitioner needs to understand. These appear in virtually every enterprise AI system.
Sequential task decomposition where each model output feeds the next input.
A classifier that directs each input to the most appropriate specialist agent or pipeline.
Running multiple agent tasks simultaneously and synthesising the results.
An agent critiques and revises its own output before it reaches a human.
The pattern that turns a language model from a text generator into an actor.
Specialised agents working together, each owning a domain of the overall task.
A controlling agent that directs sub-agents, manages state, and decides when a task is complete.
Seven patterns that determine whether a system survives contact with real users, real data, and real operational environments.
How agents store and retrieve information across sessions, tools, and agent boundaries.
How agents detect failure and decide whether to retry, escalate, skip, or fail gracefully.
The architecture for deciding when agents act autonomously and when they pause for human review.
The input and output filters that prevent agents from receiving or producing content they should not.
Systematic measurement of whether agents produce the right outputs at the right quality level.
Strategies for fitting the right information into the finite context an agent can process.
Connecting agents to external knowledge so they can retrieve facts rather than hallucinate them.
Seven patterns for complex, high-scale, high-stakes AI systems operating at the frontier of what production AI can do today.
Agents triggered by events in your systems rather than by direct user prompts.
Architectures that route agent outputs back as inputs to improve the next cycle.
Many simple agents working in parallel on variations of a problem, synthesised into one output.
An agent hierarchy where strategic agents direct tactical agents that direct operational agents.
Agents that propose improvements to their own configuration — with mandatory human approval.
Two agents take opposing positions; a third evaluates the debate and produces a verified conclusion.
Agents tested against progressively harder evaluation sets, with difficulty dynamically adjusted on performance.
Use the pattern library as an implementation reference for PSF-aligned systems. Capture system evidence, control owners, and unresolved gaps against the same open standard.
Tool policy changes, new incident records, disclosure signals, and practical next steps. Public evidence, plain English, no hype.