T0–T5 model
Name your starting level. Name the next behavior that proves progress.
What T0–T5 means at Car-Mart
T0 = never used Claude. T1 = tried a few prompts, got generic answers. T2 = use weekly, save good prompts. T3 = use daily, customize preferences. T4 = built into workflows, multi-step. T5 = agentic, multi-Claude, custom tools.
Why level matters
The next level isn't about volume — it's about behavior. The behaviors are observable. A T2 with a saved prompt library is more useful than a T3 who hasn't set preferences.
How to read yourself
Don't overclaim. Pick the level that matches what you actually do this week, not what you could do in a demo.
I'm a senior backend engineer on the Car-Mart API team (Python, 8 years).
Walk me through the T0-T5 behaviors I should adopt THIS WEEK to move from
T2 to T3. For each, give me one example from my domain (e.g., PR review
velocity, runbook generation, on-call summaries).In your lane
T2 = ask Claude to summarize a PR. T3 = set preferences for code-style + error-handling. T4 = build a CLAUDE.md for the api-refactor Project.
T2 = paste a SQL query, ask for explanation. T3 = set preferences for table-first output. T4 = build a Project for the q3-dashboard with all data dicts in context.
T2 = paste a stack trace, ask for hypothesis. T3 = set preferences for SRE-tone + actionable steps. T4 = build a Project for the runbook-update with the team's runbook library.
Pick your T-level. Write one sentence: "This week I will…" Save it to your team's Slack or your personal note.
Want the long-form version with all 6 tiers, the 60-second self-check, the T1→T2 path, and common questions?