DECISION ARCHITECTURE

Make consequential AI and platform decisions with evidence, not momentum.

Decision Crafters helps technology leaders structure uncertain decisions, separate evidence from assumptions, compare viable alternatives, and identify the smallest responsible next action.

PATH ONE

Explore the research

Evidence-labelled briefs, syntheses and method notes. Enter →

PATH TWO

See whether the Diagnostic fits

A bounded review of one architecture decision. Discuss the decision →

Latest

Research Hub →
2026·09·27

MCP Gives Agents Tools. Who Gives Them Authority?

MCP gives agents connectivity. Enterprise architecture still needs identity, delegated authority, policy, evidence, and revocation.

2026·09·01
Method note

Agent Harnesses Are a Layer, Not the Whole AI System

A comparative synthesis of OpenAI, Anthropic, and DeepSeek harness architectures—and why the harness should be treated as a replaceable runtime layer, not the whole AI system.

2026·08·14
Decision brief

Where more AI stops helping: The AI–human breakpoint

A framework for finding when better models and more automation stop being the constraint—and authority, economics, policy, coordination, or judgment take over.

INFERENCE
2026·08·14
Method note

From business problem to governed AI system

A governed AI architecture starts with actors, state, authority, policy, evidence, and workflow before models, agents, databases, or orchestration are selected.

HYPOTHESIS