AI collaboration
AI collaboration model
How I use AI collaborators while keeping judgment human-owned.
The best AI collaboration feels less like prompting and more like directing a small product team with explicit decision rights.
I do not treat AI as one generic assistant. I treat it as a set of bounded collaborators with different jobs: product manager, system architect, UX engineer, implementer, QA tester. Each role needs context, constraints, expected artifacts, and a clear human review boundary.
The more complete version of the model has eight roles: research analyst, product manager, product designer, system architect, implementation agent, QA and security reviewer, technical writer, and product operator. Those are not job titles for the AI. They are lenses for deciding what kind of artifact is needed and how it should be reviewed.
The important idea is that delegation should increase clarity. If the work is serious, the human still owns the problem framing, taste, tradeoffs, risk acceptance, verification, and final claims. AI can accelerate artifacts; it should not blur accountability.
The working sequence
Give the agent a job, context, and constraints.
A useful AI role knows the user, product surface, acceptance criteria, risk, and what output is expected.
Ask for artifacts, not vibes.
The expected output might be a brief, user story, system map, screen state, code change, test note, or launch blocker list.
Keep human ownership explicit.
AI can draft, inspect, generate, and test. The human owns product judgment, taste, risk acceptance, verification, and final claims.
AI is leverage, not authorship.
A model can help generate product artifacts quickly, but authorship of the product claim stays with the person deciding what matters, what is true, and what is safe to ship.
This is why my AI process separates role, task type, scope, non-goals, evidence, and stopping conditions. The model can recommend and implement. It should not silently decide the product purpose, target user, brand standard, release risk, customer message, deployment, or public claim.
A good AI workflow increases the visibility of human judgment instead of hiding it behind generated output.
Context is the quality control system.
The better the product dossier, the better the AI output. Roles and constraints make it easier to review the work because the work has a stated target.
The useful prompt pattern is consistent: load the relevant source-of-truth documents, assign the right role, say whether the task is analysis, design, implementation, or verification, define scope and non-goals, define expected evidence, and ask the AI to surface assumptions and blockers.
The Key Models editorial review workflow treated AI output as material for human approval, not a substitute for it. Notes, queues, previews, figure states, and approve/save-and-next actions made decisions durable.
Delegated work needs governance.
As coding agents and research/product tools become more capable, the bottleneck shifts toward direction-setting, review, eval-like checks, launch criteria, and trust.
Seen in the work
Trust-heavy nonprofit operations
Public fundraising, supporter records, organization controls, payments, certificates, content operations, and launch gates in one system.
Knowledge architecture and source-faithful systems
Searchable strategy corpus, model articles, semantic visuals, templates, protected resources, and editorial QA workflows.
Evidence-grade compensation decisions
Sensitive compensation workflows, compliance framing, source grounding, reviewer decisions, and human-in-loop AI boundaries.
Creative output as a product surface
Generative artwork, poster editors, saved libraries, export readiness, checkout paths, and output-quality judgment.