Swap the model. The project stays coherent
When the project’s identity lives in an index, not a model, you can switch Claude, Codex, or anything else mid-stream without losing coherence. The mouth changes. The soul stays.
AI Workflow Architecture further reading, page 10
AI workflow architecture matters because AI adoption fails when tools know the task but not the operating context around it.
The LLM structural crisis: solving context decay with the AI Memory Prosthesis
Introducing Simulated Recall via Shallow Indexing (SR-SI), an architectural pattern for reducing context drift in long-running AI workflows.
Before your team adopts an AI lead, read this
A workshop-facing piece on why teams should build AI infrastructure before hiring an AI lead to manage it.
What an AI integration actually costs a 30-person UAE startup - and what you get for it
An AI integration engagement is not a tool license or prompt-template pack. The real cost depends on operational complexity, knowledge distribution, and how much orientation the team needs.
Builder mode vs architect mode in AI development
Most AI dev workflows assume you’re executing a resolved plan. Real product work is architectural discovery — and specs should be the output, not the input.