Review dimensions for validating agent quality - template compliance, safety, testing, and priority validation
中文简介正在准备中。当前显示原文说明。
JTBD discovery techniques adapted for AI product owner context. Four Forces extraction, job dimension probing, question banks, and anti-patterns for interactive feature discovery conversations.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Use when conducting interactive discovery conversations to uncover jobs users are trying to accomplish. Adapted from Bob Moesta's Switch interview methodology for AI-guided feature discovery — the user describes their situation, Luna extracts forces and jobs through structured questioning.
Map user responses to Four Forces of Progress. Each force has characteristic language patterns to listen for and prompts to surface them.
User says: "I'm frustrated that..." | "It keeps breaking when..." | "I waste so much time on..." | "The last straw was when..."
Prompts:
User says: "I want to be able to..." | "I imagine being able to..." | "My colleague said it could..." | "I need it to..."
Prompts:
User says: "I'm worried that..." | "What if it doesn't..." | "I'm not sure I can learn..." | "The risk is..."
Prompts:
User says: "I'm used to..." | "At least with the old way, I know..." | "I've already invested..." | "My team is comfortable with..."
Prompts:
After extracting forces, assess the balance:
| Balance | Meaning | Action |
|---|---|---|
| Strong Push + Strong Pull | High motivation to switch | Proceed — real demand |
| Strong Pull only | Shiny feature syndrome | Probe for Push — is there real pain? |
| Strong Push + Weak Pull | Pain without clear solution | Explore solution space before committing |
| Strong Anxiety or Habit | Adoption barriers | Address anxiety in design; plan migration path |
Critical rule: Stories driven only by Pull without Push are low-priority candidates. Real jobs have real frustrations.
The practical task the user is trying to accomplish.
Questions:
How the user wants to feel during and after.
Questions:
How the user wants to be perceived by others.
Questions:
Use these patterns to go deeper when surface-level answers are insufficient.
| Technique | Pattern | When to Use |
|---|---|---|
| Timeline probe | "When did you first realize this was a problem?" | User gives vague frustration without specifics |
| Contrast probe | "How is this different from [related thing]?" | User conflates multiple concerns |
| Consequence probe | "What happens if you don't solve this?" | User can't articulate urgency |
| Concrete probe | "Can you give me a specific example?" | User speaks in generalities |
| Inversion probe | "What would make this feature useless to you?" | User gives only positive requirements |
| Scale probe | "How often does this happen? Daily? Weekly?" | User describes pain without magnitude |
| Anti-Pattern | Problem | Fix |
|---|---|---|
| Asking hypotheticals | People are poor predictors of future behavior | Ask about past events that already happened |
| Yes/no questions | Shallow data, no insight | Open-ended: "Tell me about a time when..." |
| Leading the witness | Contaminates data | Stay neutral; do not suggest answers or validate |
| Asking about features | Gets wants, not jobs | Ask about struggles and desired progress |
| Rushing to solutions | Misses real job | 80% of interview on problem, 20% on solutions |
| Accepting first answer | Surface-level understanding | Probe deeper: "Can you say more about that?" |
| Projecting emotions | Assumes how user feels | Ask directly: "How did that make you feel?" |
| Skipping social dimension | Misses organizational context | Always ask who else is affected or aware |
After extracting forces and dimensions, synthesize into job story format:
When [situation/push], I want to [motivation/pull], so I can [outcome/functional+emotional].
Validate with user: "Did I capture that correctly?" Refine until the user confirms.
If multiple jobs emerge, note each separately — opportunity scoring (load jtbd-opportunity-scoring) determines priority.
jtbd-core skilljtbd-opportunity-scoring skilljtbd-bdd-integration skill还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Review dimensions for validating agent quality - template compliance, safety, testing, and priority validation
中文简介正在准备中。当前显示原文说明。
Review dimensions for validating agent quality - template compliance, safety, testing, and priority validation
中文简介正在准备中。当前显示原文说明。
Review dimensions for acceptance test quality - happy path bias, GWT compliance, business language purity, coverage completeness, walking skeleton user-centricity, priority validation, observable behavior assertions, traceability coverage, and walking skeleton boundary proof
中文简介正在准备中。当前显示原文说明。
Detailed 5-phase workflow for creating agents - from requirements analysis through validation and iterative refinement
中文简介正在准备中。当前显示原文说明。
5-layer testing approach for agent validation including adversarial testing, security validation, and prompt injection resistance
中文简介正在准备中。当前显示原文说明。
Architectural style selection decision matrices, trade-off analysis, structural enforcement rules, and combination patterns. Load when choosing or evaluating architecture styles.
中文简介正在准备中。当前显示原文说明。