convoke-agents 2.0.0

package/_bmad/bme/_vortex/workflows/pivot-patch-persevere/pivot-patch-persevere.template.md

@@ -0,0 +1,201 @@
+---
+title: "PPP Decision: {topic}"
+date: {date}
+created-by: {user-name} with Max (learning-decision-expert)
+decision-type: {pivot|patch|persevere}
+confidence: {HIGH|MEDIUM|LOW}
+topic: {decision-topic}
+review-date: {next-checkpoint-date}
+tags: [{tags}]
+version: 1.0
+---
+
+# Pivot / Patch / Persevere Decision: {topic}
+
+> **Decision:** {PIVOT / PATCH / PERSEVERE} | **Confidence:** {level} | **Date:** {date}
+
+## One-Sentence Summary
+
+{one-sentence-decision-summary}
+
+---
+
+## Evidence Base
+
+### Learning Cards Reviewed
+
+| Card | Core Learning | Confidence | Outcome |
+|------|--------------|------------|---------|
+| {card-1} | {learning} | {confidence} | {outcome} |
+| {card-2} | {learning} | {confidence} | {outcome} |
+
+### Additional Evidence
+
+**Supporting current direction (STAY):**
+{stay-signals-with-strength}
+
+**Against current direction (CHANGE):**
+{change-signals-with-strength}
+
+**Ambiguous:**
+{unclear-signals}
+
+### Evidence Gaps
+{what-you-dont-know}
+
+---
+
+## Hypothesis Assessment
+
+### Hypothesis Stack Health
+
+| Layer | Hypothesis | Status | Confidence |
+|-------|-----------|--------|------------|
+| Problem | {hypothesis} | {status} | {confidence} |
+| Solution | {hypothesis} | {status} | {confidence} |
+| Business | {hypothesis} | {status} | {confidence} |
+
+### Health Score
+
+| Status | Count | Percentage |
+|--------|-------|------------|
+| Confirmed | {n} | {%} |
+| Partially confirmed | {n} | {%} |
+| Invalidated | {n} | {%} |
+| Untested | {n} | {%} |
+
+### Critical Failure Points
+{foundational-hypothesis-issues}
+
+---
+
+## Option Analysis
+
+### Option A: Pivot
+- **Direction:** {what-pivot-looks-like}
+- **Pros:** {key-advantages}
+- **Cons:** {key-disadvantages}
+- **Resource cost:** {time-money-team}
+- **Confidence:** {1-10}
+
+### Option B: Patch
+- **Adjustments:** {what-patch-looks-like}
+- **Pros:** {key-advantages}
+- **Cons:** {key-disadvantages}
+- **Resource cost:** {time-money-team}
+- **Confidence:** {1-10}
+
+### Option C: Persevere
+- **Next milestone:** {what-persevere-looks-like}
+- **Pros:** {key-advantages}
+- **Cons:** {key-disadvantages}
+- **Resource cost:** {time-money-team}
+- **Confidence:** {1-10}
+
+### Comparative Summary
+
+| Dimension | Pivot | Patch | Persevere |
+|-----------|-------|-------|-----------|
+| Addresses root cause? | {assessment} | {assessment} | {assessment} |
+| Time to next evidence | {weeks} | {weeks} | {weeks} |
+| Resource cost | {H/M/L} | {H/M/L} | {H/M/L} |
+| Reversibility | {H/M/L} | {H/M/L} | {H/M/L} |
+| Confidence (1-10) | {n} | {n} | {n} |
+
+---
+
+## Stakeholder Input
+
+### Perspectives Summary
+
+| Stakeholder | Preference | Conviction | Key Concern |
+|------------|------------|------------|-------------|
+| {name} | {option} | {strong/moderate/open} | {concern} |
+
+### Points of Agreement
+{shared-understanding}
+
+### Points of Disagreement
+{disagreements-and-how-to-resolve}
+
+---
+
+## Decision
+
+### The Decision
+**{PIVOT / PATCH / PERSEVERE}**
+
+{one-sentence-summary}
+
+### Rationale
+1. {reason-1-with-evidence}
+2. {reason-2-with-evidence}
+3. {reason-3-with-evidence}
+
+### Why Not the Other Options
+- **{rejected-option-1}:** {reason}
+- **{rejected-option-2}:** {reason}
+
+### What We're Betting On
+{key-assumptions-that-must-hold}
+
+### What We're Accepting
+{risks-and-opportunity-costs}
+
+### Dissenting Views
+{stakeholder-disagreements-documented}
+
+---
+
+## Reversal Criteria
+
+### KILL Criteria (triggers full re-evaluation)
+{specific-measurable-signals}
+
+### CONCERN Criteria (triggers check-in)
+{early-warning-signals}
+
+---
+
+## Action Plan
+
+### Immediate Actions
+
+| What | Who | By When | Done When |
+|------|-----|---------|-----------|
+| {action-1} | {owner} | {date} | {completion-criteria} |
+| {action-2} | {owner} | {date} | {completion-criteria} |
+
+### Next Experiment
+- **Name:** {experiment-name}
+- **Hypothesis:** {hypothesis}
+- **Method:** {method}
+- **Success criteria:** {criteria}
+- **Duration:** {timeline}
+
+### Checkpoints
+
+| Date | Review | Decision |
+|------|--------|----------|
+| {date-1} | {what-to-review} | {decision-to-make} |
+| {date-2} | {what-to-review} | {decision-to-make} |
+
+### Risk Mitigation
+
+| Risk | Probability | Impact | Mitigation | Owner |
+|------|------------|--------|------------|-------|
+| {risk} | {H/M/L} | {H/M/L} | {action} | {name} |
+
+---
+
+## Revision History
+
+| Date | What Changed | Why | Decision Impact |
+|------|--------------|-----|-----------------|
+| {date} | Initial decision | First PPP review | N/A |
+
+---
+
+**Created with:** Convoke v2.0.0 - Vortex Pattern (Systematize Stream)
+**Agent:** Max (Learning & Decision Expert)
+**Workflow:** pivot-patch-persevere

package/_bmad/bme/_vortex/workflows/pivot-patch-persevere/steps/step-01-evidence-review.md

@@ -0,0 +1,125 @@
+---
+step: 1
+workflow: pivot-patch-persevere
+title: Evidence Review
+---
+
+# Step 1: Evidence Review
+
+Before making a strategic decision, we need all the evidence on the table. This step gathers and organizes every relevant data point so the decision is grounded in reality, not opinion.
+
+## Why This Matters
+
+The most common failure in strategic decisions is incomplete evidence. Teams pivot based on one bad experiment while ignoring three positive signals. Teams persevere based on enthusiasm while ignoring warning signs. A complete evidence review prevents both traps.
+
+## Your Task
+
+### 1. List All Relevant Learning Cards
+
+Gather every learning card related to this decision area:
+
+For each learning card, capture:
+- **Card name and date**
+- **Core learning (one sentence)**
+- **Confidence rating** (High / Medium / Low / Exploratory)
+- **Outcome** (Validated / Invalidated / Partially validated / Inconclusive)
+
+### 2. List Additional Evidence
+
+Beyond formal learning cards, what other evidence is relevant?
+
+**Customer signals:**
+- Support tickets or complaints
+- Feature requests
+- Churn reasons
+- NPS or satisfaction scores
+- Usage analytics
+
+**Market signals:**
+- Competitor moves
+- Industry trends
+- Regulatory changes
+- Technology shifts
+
+**Internal signals:**
+- Team morale and confidence
+- Technical debt or feasibility concerns
+- Resource constraints
+- Opportunity costs (what else could you be doing?)
+
+### 3. Organize by Signal Direction
+
+Sort ALL evidence into three buckets:
+
+**Evidence supporting current direction (STAY signals):**
+- List each piece of evidence
+- Rate its strength (Strong / Moderate / Weak)
+
+**Evidence against current direction (CHANGE signals):**
+- List each piece of evidence
+- Rate its strength (Strong / Moderate / Weak)
+
+**Ambiguous evidence (UNCLEAR signals):**
+- List each piece of evidence
+- Note why it's ambiguous
+
+### 4. Identify Evidence Gaps
+
+What DON'T you know that would matter for this decision?
+
+- What experiments haven't you run yet?
+- What user segments haven't you tested?
+- What market conditions haven't you validated?
+- How would you rate your overall evidence completeness? (Comprehensive / Adequate / Gaps exist / Insufficient)
+
+## Example
+
+**Learning Cards:**
+
+| Card | Core Learning | Confidence | Outcome |
+|------|--------------|------------|---------|
+| LC-001: Async Adoption | Champions drive adoption; fails without them | Medium | Partially validated |
+| LC-002: Remote Manager Pain | Status tracking is top time-waster for remote managers | High | Validated |
+| LC-003: Pricing Survey | $15-20/seat/month acceptable for teams with 3+ timezones | Medium | Validated |
+| LC-004: Co-located Test | Co-located teams see minimal value in async status | Medium | Invalidated (our original assumption) |
+
+**Additional Evidence:**
+- Customer signals: 12 inbound inquiries from distributed teams in past month; 0 from co-located teams
+- Market: Competitor X launched an async standup tool last month targeting enterprise (validates market, increases urgency)
+- Internal: Engineering team is excited about the video feature but concerned about scaling video processing costs
+
+**Signal Direction:**
+
+STAY signals (support current direction):
+- Remote manager pain is validated (STRONG)
+- Willingness to pay confirmed for distributed teams (MODERATE)
+- Inbound interest from target segment (MODERATE)
+
+CHANGE signals (against current direction):
+- Adoption requires champions -- can we reliably create them? (MODERATE)
+- Co-located teams don't see value -- market is smaller than assumed (STRONG)
+- Competitor launched -- differentiation window may be closing (MODERATE)
+
+UNCLEAR signals:
+- Long-term retention unknown (only 2-week experiments)
+- Video processing costs at scale untested (engineering concern)
+
+**Evidence Gaps:**
+- No data on teams larger than 8 people
+- No data on non-engineering teams
+- No retention data beyond 2 weeks
+- Overall completeness: GAPS EXIST -- adequate for directional decision but not for major resource commitment
+
+---
+
+## Your Turn
+
+Please compile your evidence using the structure above. Be thorough -- it's better to include weak evidence and label it as weak than to omit it and make a decision with blind spots.
+
+**Important:** Resist the temptation to pre-judge the evidence. Just collect and organize it here. Analysis comes in the next steps.
+
+## Next Step
+
+When you've completed the evidence review, I'll load:
+
+{project-root}/_bmad/bme/_vortex/workflows/pivot-patch-persevere/steps/step-02-hypothesis-assessment.md

package/_bmad/bme/_vortex/workflows/pivot-patch-persevere/steps/step-02-hypothesis-assessment.md

@@ -0,0 +1,132 @@
+---
+step: 2
+workflow: pivot-patch-persevere
+title: Hypothesis Assessment
+---
+
+# Step 2: Hypothesis Assessment
+
+Now we assess your original hypotheses against the collected evidence. Which parts of your thesis are holding up, which are crumbling, and which are still uncertain?
+
+## Why This Matters
+
+Your product strategy is built on a stack of hypotheses. Some are foundational (if wrong, everything falls apart). Others are adjustable (if wrong, you can change approach without changing direction). Understanding which hypotheses are confirmed, partially confirmed, or invalidated determines whether you need a pivot, patch, or persevere.
+
+## Your Task
+
+### 1. Map Your Hypothesis Stack
+
+List every major hypothesis your current strategy depends on, organized by layer:
+
+**Problem Hypotheses (foundation layer):**
+- Does the problem exist?
+- Is it painful enough to motivate action?
+- Is it frequent enough to sustain engagement?
+
+**Solution Hypotheses (middle layer):**
+- Does our approach solve the problem?
+- Is it better than current alternatives?
+- Can users actually use it?
+
+**Business Hypotheses (top layer):**
+- Will people pay for this?
+- Can we acquire customers cost-effectively?
+- Can we retain them?
+- Can we scale the business?
+
+### 2. Assess Each Hypothesis
+
+For every hypothesis, provide:
+
+| Hypothesis | Status | Evidence | Confidence |
+|-----------|--------|----------|------------|
+| {hypothesis} | {Confirmed / Partially confirmed / Invalidated / Untested} | {key evidence} | {High / Medium / Low} |
+
+**Assessment guidelines:**
+
+- **Confirmed:** Multiple data points support it. You'd bet money on it.
+- **Partially confirmed:** True in some conditions but not others. The hypothesis needs refinement, not rejection.
+- **Invalidated:** Evidence contradicts it. Continuing to assume this is true would be ignoring data.
+- **Untested:** You haven't gathered evidence yet. This is a risk, not a finding.
+
+### 3. Identify the Critical Failure Points
+
+Which invalidated or partially confirmed hypotheses are FOUNDATIONAL?
+
+**The Foundation Test:** If this hypothesis is wrong, does the rest of the strategy still make sense?
+
+- If a PROBLEM hypothesis is invalidated: you likely need a pivot (the problem you're solving isn't real or isn't painful enough)
+- If a SOLUTION hypothesis is invalidated: you likely need a patch (the problem is real but your approach is wrong)
+- If a BUSINESS hypothesis is invalidated: you might need a patch (adjust pricing, channels, or positioning) or a pivot (the economics don't work)
+
+### 4. Calculate Your Hypothesis Health Score
+
+Count your hypotheses by status:
+
+| Status | Count | Percentage |
+|--------|-------|------------|
+| Confirmed | {n} | {%} |
+| Partially confirmed | {n} | {%} |
+| Invalidated | {n} | {%} |
+| Untested | {n} | {%} |
+
+**Interpretation guide:**
+- 70%+ confirmed/partially confirmed with 0 foundational invalidations: STRONG position (persevere likely)
+- Mixed results with foundational hypotheses partially confirmed: MODERATE position (patch likely)
+- Foundational hypotheses invalidated: WEAK position (pivot likely)
+- Many untested hypotheses: INSUFFICIENT DATA (more experiments needed before deciding)
+
+## Example
+
+**Hypothesis Stack:**
+
+**Problem Layer:**
+| Hypothesis | Status | Evidence | Confidence |
+|-----------|--------|----------|------------|
+| Remote managers spend 5+ hrs/week on status | Confirmed | Time-log study: 78% logged 5+ hours | High |
+| Status meetings are the primary time-waster | Partially confirmed | #1 for distributed teams, #3 for co-located | Medium |
+| This problem is getting worse (remote trend) | Confirmed | Industry data + inbound inquiries | High |
+
+**Solution Layer:**
+| Hypothesis | Status | Evidence | Confidence |
+|-----------|--------|----------|------------|
+| Async video replaces standups effectively | Partially confirmed | Works with champions, fails without | Medium |
+| Users will adopt without training | Invalidated | Only champion-led teams sustained adoption | Medium |
+| Screen-sharing adds value over text | Confirmed | Unprompted adoption + blocker discovery | Medium |
+
+**Business Layer:**
+| Hypothesis | Status | Evidence | Confidence |
+|-----------|--------|----------|------------|
+| Teams will pay $15-20/seat/month | Confirmed | Pricing survey with distributed teams | Medium |
+| Co-located teams are also our market | Invalidated | No measurable value for co-located teams | Medium |
+| We can acquire via product-led growth | Untested | No data | N/A |
+
+**Critical Failure Points:**
+- Problem layer is STRONG: the problem is real and growing
+- Solution layer has a PARTIAL failure: adoption requires champions (this is patchable, not fatal)
+- Business layer has a SIGNIFICANT invalidation: co-located teams are not a market (reduces TAM by ~60%, but remaining market is viable)
+
+**Hypothesis Health Score:**
+
+| Status | Count | Percentage |
+|--------|-------|------------|
+| Confirmed | 4 | 44% |
+| Partially confirmed | 2 | 22% |
+| Invalidated | 2 | 22% |
+| Untested | 1 | 11% |
+
+**Interpretation:** MODERATE position. No foundational invalidations. Solution needs patching (champion model). Market is narrower than assumed. Patch is the likely direction.
+
+---
+
+## Your Turn
+
+Please assess your hypothesis stack using the structure above.
+
+**Key principle:** Be brutally honest. The point of this exercise is to see reality clearly, not to justify the decision you've already made emotionally. If a beloved hypothesis is invalidated, that's the most valuable thing you can learn.
+
+## Next Step
+
+When you've completed the hypothesis assessment, I'll load:
+
+{project-root}/_bmad/bme/_vortex/workflows/pivot-patch-persevere/steps/step-03-option-analysis.md

package/_bmad/bme/_vortex/workflows/pivot-patch-persevere/steps/step-03-option-analysis.md

@@ -0,0 +1,167 @@
+---
+step: 3
+workflow: pivot-patch-persevere
+title: Option Analysis
+---
+
+# Step 3: Option Analysis
+
+Now we rigorously analyze all three options -- Pivot, Patch, and Persevere -- with their pros, cons, risks, and resource implications. This step forces you to seriously consider ALL options before deciding.
+
+## Why This Matters
+
+Teams almost always have a favorite option before analysis begins. This step's purpose is to steelman the options you're NOT leaning toward. Often the best decision is the one that felt uncomfortable at first. By forcing equal rigor across all three options, you protect against both change-aversion ("we've come this far") and shiny-object syndrome ("let's try something new").
+
+## Your Task
+
+### Analyze Each Option
+
+For each of the three options, work through this framework:
+
+---
+
+### Option A: PIVOT
+
+A pivot means changing one or more fundamental elements of your strategy: the problem you're solving, the user you're targeting, the solution approach, or the business model.
+
+**Define the pivot:**
+- What specifically would change?
+- What would stay the same?
+- What new direction would you take?
+
+**Types of pivot to consider:**
+| Pivot Type | Description | Example |
+|-----------|-------------|---------|
+| Customer segment | Same product, different users | B2C to B2B |
+| Problem | Same users, different problem | From "save time" to "reduce risk" |
+| Solution | Same problem, different approach | From software to service |
+| Channel | Same product, different distribution | From direct sales to marketplace |
+| Revenue model | Same product, different monetization | From subscription to usage-based |
+| Technology | Same problem, different tech stack | From mobile app to browser extension |
+| Platform | From product to platform | From tool to ecosystem |
+
+**Pros of pivoting:**
+- What opportunities does this open?
+- What problems does this avoid?
+- What evidence supports this new direction?
+
+**Cons of pivoting:**
+- What do you lose? (Sunk costs, momentum, team expertise, customer relationships)
+- What new risks does this introduce?
+- How long until you have evidence about the new direction?
+
+**Resource cost:**
+- Time to pivot (weeks/months)
+- Financial cost
+- Team impact (morale, skills gap, hiring needs)
+- Customer/partner impact
+
+**Pivot confidence:** On a scale of 1-10, how confident are you that the pivot direction would succeed? What evidence supports that confidence?
+
+---
+
+### Option B: PATCH
+
+A patch means adjusting your approach while keeping the core direction. You're changing HOW you execute, not WHAT you're pursuing.
+
+**Define the patch:**
+- What specifically would you adjust?
+- What stays the same?
+- How does this address the evidence that triggered this review?
+
+**Common patch patterns:**
+| Pattern | Description | When to Use |
+|---------|-------------|-------------|
+| Narrow focus | Reduce target scope | When it works for a segment but not broadly |
+| Add mechanism | Add enablement feature | When adoption needs a catalyst |
+| Reposition | Change messaging/framing | When value exists but isn't communicated |
+| Sequence change | Change the order of operations | When users struggle with the entry point |
+| Remove friction | Simplify the experience | When value is clear but execution is hard |
+| Extend timeline | Give it more time | When early signals are positive but immature |
+
+**Pros of patching:**
+- What does this preserve from your current progress?
+- How does this address the specific issues identified?
+- How quickly can you test the patched approach?
+
+**Cons of patching:**
+- Is this a genuine improvement or just "lipstick on a pig"?
+- Does it address root causes or just symptoms?
+- Are you patching because the data says to, or because pivoting feels scary?
+
+**Resource cost:**
+- Time to implement and test the patch
+- Additional experiments needed
+- Opportunity cost of time spent patching vs. pivoting
+
+**Patch confidence:** On a scale of 1-10, how confident are you that the patch would resolve the issues? What evidence supports that?
+
+---
+
+### Option C: PERSEVERE
+
+Persevere means staying the course. The evidence supports your direction, and you should invest more resources, run larger experiments, or move to the next stage.
+
+**Define what persevering looks like:**
+- What's the next milestone?
+- What resources will you commit?
+- What's the timeline before the next decision point?
+
+**Pros of persevering:**
+- What evidence supports continuing?
+- What momentum would you maintain?
+- What compounding effects are you building?
+
+**Cons of persevering:**
+- Are you persevering because of evidence or because of sunk-cost bias?
+- What risks accumulate the longer you stay on this path?
+- What opportunities are you forgoing?
+
+**Warning signs you might be persevering for the wrong reasons:**
+- "We've already invested so much time/money"
+- "The market will come around eventually"
+- "We just need more users and it'll work"
+- "The data is wrong / users don't know what they want"
+- "Our competitors are struggling too, so it's a hard market"
+
+**Persevere confidence:** On a scale of 1-10, how confident are you that persevering will lead to success within the next decision timeframe? What evidence supports that?
+
+---
+
+### Comparative Summary
+
+| Dimension | Pivot | Patch | Persevere |
+|-----------|-------|-------|-----------|
+| Addresses root cause? | | | |
+| Time to next evidence | | | |
+| Resource cost | | | |
+| Reversibility | | | |
+| Confidence (1-10) | | | |
+| Biggest risk | | | |
+
+## Example
+
+**Comparative Summary:**
+
+| Dimension | Pivot (to enterprise async platform) | Patch (add champion onboarding, narrow to distributed teams) | Persevere (continue broad remote team approach) |
+|-----------|-------|-------|-----------|
+| Addresses root cause? | Partially -- avoids adoption problem by selling to IT buyers | Yes -- directly addresses champion dependency and market fit | No -- ignores evidence that co-located teams don't benefit |
+| Time to next evidence | 3-4 months (new market research needed) | 4-6 weeks (run patched experiment) | 2-3 months (scale current approach, hope for different results) |
+| Resource cost | High (new positioning, possibly new features) | Medium (onboarding flow + refined targeting) | Low (continue current work) |
+| Reversibility | Hard to reverse (different market positioning) | Easy to reverse (additive changes) | Easy to reverse (no changes made) |
+| Confidence (1-10) | 4 (speculative, no evidence for enterprise market) | 7 (evidence supports both adjustments) | 3 (ignoring contradictory evidence) |
+| Biggest risk | Enterprise sales cycle is long; might run out of runway | Patch might not be enough; delays a needed pivot | Throwing good money after bad |
+
+---
+
+## Your Turn
+
+Please analyze all three options using the frameworks above. Remember: the goal is to steelman each option, not to argue for the one you prefer.
+
+**Key principle:** If you can't articulate strong pros for an option you disagree with, you haven't analyzed it well enough.
+
+## Next Step
+
+When you've completed the option analysis, I'll load:
+
+{project-root}/_bmad/bme/_vortex/workflows/pivot-patch-persevere/steps/step-04-stakeholder-input.md