A systematic dialogue framework for scientific problem selection built on the paper "Problem choice and decision trees in science and engineering" by Fischbach and Walsh (Cell, 2024).
Quick Start
Provide users with three entry points:
1) Propose an idea for a new project — refine it together
2) Share a problem encountered in the current project — troubleshoot and solve it together
3) Raise a strategic question — sort out the decision tree together
This conversational entry point can naturally meet researchers' current needs and establish a collaborative tone.
Option 1: Propose an Idea
Initial Prompt
Ask:"Describe your idea briefly in 1-2 sentences."
Response Approach
After the user shares an idea, return a brief summary (no more than one paragraph) showing your understanding of their idea. Point out the general research area and restate the core of the idea in your own words—showing that you understand and are ready to discuss it in depth.
Follow-up Prompt
Then ask for more details: "Please say a bit more. You can briefly mention, or indicate where you are still unsure:
- What exactly you want to do
- How you currently plan to do it
- If successful, why this is a big deal
- What you think the biggest risk is"
Workflow
Next, guide the user into the early stages of problem selection and evaluation:
- Skill 1: Intuition Pump - refine and strengthen the idea
- Skill 2: Risk Assessment - identify and manage project risks
- Skill 3: Optimization Function - define success metrics
- Skill 4: Parameter Strategy - determine what to fix and what to keep flexible
For detailed guidance, see references/01-intuition-pumps.md、references/02-risk-assessment.md、references/03-optimization-function.md and references/04-parameter-strategy.md。
Option 2: Troubleshoot Problems
Initial Prompt
Ask:"Describe the problem you encountered briefly in 1-2 sentences (however is convenient for you)."
Response Approach
After the user shares the problem, return a brief summary (no more than one paragraph) showing your understanding. Point out the project context in which the problem occurred and restate the problem—highlighting its core essence—so the user knows you understand the situation. At the same time, raise additional questions that seem to need discussion.
Follow-up Prompt
Then ask: "Please say a bit more. You can briefly mention:
- The overall goal of your project (if we haven't talked about it before)
- What exactly went wrong
- Your current approach to solving it"
Workflow
Next, guide the user through troubleshooting and decision tree navigation:
- Skill 5: Decision Tree Navigation - Planning decision node, flexibly switching between execution and strategic thinking
- Skill 4: Parameter Strategy - Fix one parameter at a time, keeping the other parameters floating
- Skill 6: Navigating Adversity - Turn problems into growth opportunities
- Skill 7: Problem Inversion - Strategies for working around obstacles
Whether or not the problem is easy to solve, you should include workarounds that may be useful.
For detailed guidance, see references/05-decision-tree.md、references/06-adversity-planning.md、references/07-problem-inversion.md and references/04-parameter-strategy.md。
Option 3: Ask a strategic question
Initial prompt
Ask:"Briefly describe your problem in 1-2 sentences."
How to respond
After the user shares the problem, return a brief summary (no more than one paragraph) showing your understanding. Point out the broader context and restate the problem—highlighting what is key about it—to confirm that your understanding matches the user's thinking.
Follow-up prompt
Then ask: "Please share a few more details. You can briefly mention:
- Background context (i.e., whether this is about a current project or a future project)
- What you are thinking—tell me a bit more"
Workflow
Next, depending on the specific situation of the problem, flexibly apply the most relevant modules from the problem selection framework:
- Skills 1-4 apply to future project planning (ideation, risk, optimization, parameters)
- Skills 5-7 apply to navigating the current project (decision tree, navigating adversity, inversion)
- Skill 8 applies to communication and synthesis
- Skill 9 applies to full-process orchestration
For the complete reference materials, see the references/ folder.
Core Framework Concepts
Core Insight
Problem Selection >> Execution Quality
Even excellent execution on a mediocre problem yields incremental impact. Good execution on an important problem yields substantial impact.
The Time Paradox
Researchers typically:
- Spenda few dayschoosing a problem
- Spendseveral yearssolving it
This imbalance limits impact. This skill set helps you invest more time in problem selection and make wiser choices.
Evaluation Axes
Used to evaluate ideas:
- X-axis: Likelihood of success
- Y-axis: Impact if successful
The skills help move ideas to the right (more feasible) and upward (greater impact).
The Risk Paradox
- Don't avoid risk—make risk your friend
- Zero risk = incremental work
- But: requiring multiple miracles = should be avoided or improved
- Balance point: Risk that is understood, quantified, and manageable
The Parameter Paradox
- Fixing too many = fragility
- Fixing too few = choice paralysis
- Optimal state: Fix one meaningful constraint
The Law of Adversity
- Crises are inevitable (don't be surprised)
- Crises are opportunities (don't waste them)
- Strategy: Fix the problem while upgrading the project
Overview of the 9 Skills
| Skill | Purpose | Output | Time |
|---|---|---|---|
| 1. Intuition Pump | Generate high-quality research ideas | Problem formulation document | ~1 week |
| 2. Risk Assessment | Identify and manage project risks | Risk assessment matrix | 3-5 days |
| 3. Optimization Function | Define success metrics | Impact assessment document | 2-3 days |
| 4. Parameter Strategy | Decide what to fix and what to keep flexible | Parameter strategy document | 2-3 days |
| 5. Decision Tree Navigation | Plan decision nodes and altitude switching | Decision tree diagram | 2 days |
| 6. Adversity Response | Turn crises into opportunities | Adversity response playbook | 2 days |
| 7. Problem Inversion | Strategies for bypassing obstacles | Problem inversion analysis | 1 day |
| 8. Integration and Synthesis | Synthesize into a coherent plan | Project communication package | 3-5 days |
| 9. Meta-Framework | Orchestrate the complete workflow | Complete project plan package | 1-6 weeks |
Skill Workflow
技能 1：直觉泵
|（产生想法）
v
技能 2：风险评估
|（评估可行性）
v
技能 3：优化函数
|（定义成功指标）
v
技能 4：参数策略
|（确定灵活度）
v
技能 5：决策树
|（规划执行与评估）
v
技能 6：逆境规划
|（准备应对失败模式）
v
技能 7：问题反转
|（提供转向策略）
v
技能 8：整合与沟通
|（综合为连贯的计划）
v
技能 9：元技能
（编排完整工作流）
Key Design Principles
- Conversational Entry - Naturally capture user needs through three clear starting points
- Thoughtful Interaction - Ask clarifying questions; request more input when confidence is low
- Literature Integration - Validate at key points using PubMed searches
- Concrete Outputs - Each skill produces a 1-2 page practical document
- Progressive Specification - Gradually unfold details through targeted questions
- Flexibility - Skills can be used independently, sequentially, or iteratively
- Scientific Rigor - Claims about generality and feasibility should be evidence-supported
Target Audience
Graduate Students (Core Audience)
- Use cases: Choosing a thesis topic, qualifying exams, committee meetings
- Key skills: Skills 1-3 (ideation, risk, impact) + Skill 9 (complete workflow)
- Timeline: 2-4 weeks for comprehensive planning
Postdocs
- Use cases: Starting a new position, planning independent projects, applying for grants
- Key skills: All skills, with emphasis on independence and risk management
- Timeline: 1-2 weeks of intensive planning
Principal Investigators (PIs)
- Use cases: Establishing a new lab, new research directions, mentoring students, grant cycles
- Key skills: Skills 1, 3, 4, 6 (Ideation, Influence, Parameters, Adversity Response)
- Timeline: Ongoing, integrated into lab culture
Entrepreneur
- Applicable scenarios: Company founding, pivot decisions, investor pitches
- Key skills: Skills 1-4 (Ideation to Parameter Strategy) + Skill 8 (Communication)
- Timeline: 1-2 weeks of initial planning, quarterly review
Reference Materials
See the detailed skill documentation in the references/ folder:
| File | Content | Search Mode |
|---|---|---|
01-intuition-pumps.md |
Generating research ideas | Intuition Pump #, Trap #, Phase [0-9] |
02-risk-assessment.md |
Risk identification | Risk.*1-5, go/no-go, assumption |
03-optimization-function.md |
Success metrics | Generality.*Learning, optimization, impact |
04-parameter-strategy.md |
Parameter fixing strategy | fixed.*float, constraint, parameter |
05-decision-tree.md |
Decision tree navigation | altitude, Level [0-9], decision |
06-adversity-planning.md |
Adversity response | adversity, crisis, ensemble |
07-problem-inversion.md |
Problem reversal strategy | Strategy [0-9], inversion, goal |
08-integration-synthesis.md |
Integration and synthesis | narrative, communication, story |
09-meta-framework.md |
Complete workflow | Phase, workflow, orchestrat |
Expected Outcomes
Immediate outcomes (after completing the workflow)
- Clear project vision
- Honest risk assessment
- Contingency plans
- Communication materials ready
- Confidence in the chosen topic
After 6 months
- Faster decisions (with a framework to follow)
- Efficient adversity response
- No existential crises (risks have been mitigated)
After 2 years
- Published results or substantial progress
- Avoided dead-end projects
- Career direction aligned with goals
- Time well spent(the ultimate measure)
Foundational Literature
Fischbach, M.A., & Walsh, C.T. (2024). "Problem choice and decision trees in science and engineering." Cell, 187, 1828-1833.
Based on Stanford University's BIOE 395 course.