Mastery: your playbook

Your mastery artifact is a multimodal evidence packet with redaction checklist, annotated image, observation/inference table, follow-up requests, and verification result. It should let a competent colleague repeat diagnose a confusing dashboard screenshot using image evidence plus written context without inheriting unstated assumptions. Include the job card, source requirements, prompt contract, examples, rubric, privacy boundary, escalation rule, and recovery steps.

Use sanitize → orient → observe → infer → request evidence → verify as the spine. For every stage, name the input, action, output, owner, check, and stop condition. Include the concrete prompt:

Inspect this redacted checkout dashboard screenshot. Goal: explain why the conversion total appears inconsistent. First inventory only visible labels and values with locations. Separate observation from inference. Then propose three hypotheses and the next screenshot or log needed to test each. Do not identify people, infer hidden fields, or invent unreadable text.

Then include a specimen response: An observation table grounded in screen regions, clearly labeled hypotheses, and targeted follow-up evidence instead of a confident visual guess. Label it as an example, not a guaranteed result. Attach proof from the independent check: you must zoom and compare source pixels, transcribe critical values manually, reproduce in the product, inspect logs, and reject claims unsupported by visible or supplied evidence.

Run the same playbook on a second case that differs in one meaningful way. Keep the quality bar fixed. Explain which context fields and constraints changed. If the workflow only succeeds on the memorized example, it is not mastered.

Teach the method in five minutes to someone who has not read this chapter. Ask them to identify the source of truth, the riskiest failure, and the human decision. Their answers reveal whether your playbook is explicit.

Score yourself:

1. Framing: I can reject work outside the stated job.
2. Context: I distinguish evidence, assumptions, and untrusted input.
3. Prompting: I constrain output and request inspectable artifacts.
4. Verification: I use an external check, not model confidence.
5. Safety: I enforce this boundary: crop and redact names, faces, addresses, notifications, account IDs, location clues, EXIF metadata, and confidential browser tabs before upload.
6. Operations: I can recover from hallucinated small text; mixing observation with inference; ignoring chart scale; accidental exposure around the crop; treating an image as current truth.
7. Communication: I disclose limitations and ownership clearly.

A weak score is a practice target, not a reason to pad the playbook. Point to regions, labels, frames, or timestamps. When the model cannot read a detail reliably, provide a crop or transcription instead of asking it to guess harder.

Package the project as produce a reproducible dashboard bug report from a sanitized screenshot, evidence inventory, hypotheses, logs, and confirmed root cause. Show the before state, constraint decisions, failed case, correction, measured result, and reflection. Remove sensitive inputs and avoid claiming impact you did not measure. Professional credibility comes from showing judgment under constraints.