Adoption Spectrum
Level 1

Regular Conversation Partner

You use AI habitually. You've developed prompting instincts — context matters, follow-ups help, format shapes output.

If this is you
Your risk

At this level, the AI is responsive but doesn't know your work deeply. It will affirm framings you bring to it. You can talk yourself into a bad argument faster than you'd expect — the AI never pushes back unless you ask it to. Confidence accumulates without scrutiny.

To reach Level 2
Regular Conversation Partner → Context-Aware Collaborator
Conceptual Shift
"The AI's ignorance of your work is the bottleneck."

Without context, Claude is a highly capable stranger — intelligent, responsive, but generic. It doesn't know what you're investigating, what you've already established, or what your standards are. Providing that context is the single highest-leverage thing you can do at this transition.

Experiment
Write a one-page project description for Claude in 30 minutes. Include: what the project is, what you're currently working on, what you want AI to help with, and — importantly — what you do not want AI to shape or decide. Don't try to be perfect. Use it for a week. Revise it based on what felt missing. The natural home for this is a Claude.ai Project or a CLAUDE.md file in your working directory.
Practice
  • Update the context when your work changes direction. Outdated project descriptions are actively misleading.
  • Counter confirmation accumulation actively: periodically ask Claude to steelman the opposing view, find the weakest points in your argument, or describe what a hostile reviewer would say.
  • Cultivate calibrated scepticism about what Claude can't know: recent literature, field-specific norms, your unpublished findings.
Next level →
Context-Aware Collaborator
← Level 0: Occasional Querier