fraim-framework 2.0.35 → 2.0.37

package/registry/workflows/customer-development/insight-analysis.md

@@ -1,156 +0,0 @@
-# Insight Analysis Workflow
-
-## INTENT
-To help Product Managers extract, structure, and analyze customer insights from interview notes, enabling data-driven product decisions and systematic customer relationship management.
-
-## PRINCIPLES
-- **Comprehensive Extraction**: Capture all insights from raw notes
-- **Structured Analysis**: Organize insights into actionable categories
-- **Customer Scoring**: Evaluate customer fit and prioritization
-- **Follow-up Generation**: Create personalized follow-up communications
-
-## WORKFLOW TRIGGER
-**PM explicitly starts this workflow**:
-- "Starting Insight Analysis for [Customer Name]"
-- "I want to analyze the interview with [Customer Name]"
-- "Following the insight analysis workflow"
-
-## INPUT REQUIREMENTS
-**PM provides**:
-- The `[customer-name]-interview-prep.md` file that needs to be updated
-- Raw interview notes in any format (bullet points, paragraphs, voice-to-text, etc.)
-- Brief unstructured thoughts about the interview (optional but helpful)
-
-## AI AGENT PROCESS
-
-### Step 1: Insight Extraction & Template Update
-**AI Agent Analysis Process**:
-1. **Read Existing Prep File**
-   - Load the `[customer-name]-interview-prep.md` file
-   - Understand the customer context and research from preparation phase
-   - Review the pre-filled template structure
-
-2. **Parse Raw Notes**
-   - Extract customer quotes and key statements
-   - Identify pain points and challenges
-   - Capture success and failure criteria
-   - Note feature requests and preferences
-   - **Date Handling**: If user provides relative time references (e.g., "yesterday", "today", "last Friday"), run `new Date()` to determine the actual date and use that in the analysis file
-
-3. **Create Analysis File**
-   - Create new file: `[customer-name]-interview-analysis.md`
-   - Include comprehensive analysis with customer scoring and insights
-   - Reference the prep file for context but keep files separate
-   - Include follow-up actions and next steps
-
-### Step 2: Customer Scoring & Prioritization
-**AI Agent Scoring Process**:
-1. **Customer Fit Scoring (1-10)**
-   - Target customer segment alignment
-   - Pain point severity and frequency
-   - Budget and decision-making authority
-   - Influence and referral potential
-
-2. **Urgency Assessment**
-   - Active seeking of solutions
-   - Budget allocation and timeline
-   - Competitive pressure
-   - Implementation readiness
-
-3. **Willingness to Pay**
-   - Budget authority and constraints
-   - Current spending on similar solutions
-   - Value perception and ROI understanding
-
-### Step 3: Follow-up Generation
-**AI Agent Communication Process**:
-1. **Generate Follow-up Email**
-   - Use follow-up email templates as reference
-   - Create personalized email based on interview content
-   - Include key takeaways confirmation
-   - Add specific next steps and timeline
-   - Reference customer quotes and insights
-
-2. **Follow-up Questions**
-   - Clarify any gaps in understanding
-   - Deepen insights on key topics
-   - Validate assumptions and priorities
-   - Explore referral opportunities
-
-3. **Next Steps Planning**
-   - Demo scheduling if appropriate
-   - Additional stakeholder meetings
-   - Resource sharing and education
-   - Timeline and milestone setting
-
-### Step 4: File Creation & Finalization
-**AI Agent File Management**:
-1. **Create Analysis File**
-   - Create `[customer-name]-interview-analysis.md` with comprehensive analysis
-   - Include customer scoring, insights, and follow-up actions
-   - Reference the prep file for context but keep files separate
-
-2. **Preserve Prep File**
-   - Keep `[customer-name]-interview-prep.md` unchanged
-   - Maintains clean separation between preparation and analysis
-   - Both files can be referenced independently
-
-## OUTPUT TEMPLATE
-
-### Analysis File Template
-**Template**: Retrieve via `get_fraim_file({ path: "templates/customer-development/insight-analysis-template.md" })`
-**File Location**: `docs/customer-development/[customer-name]-interview-analysis.md`
-
-**Process**:
-1. Use the insight analysis template
-2. Extract insights from raw interview notes
-3. Score customer based on fit, urgency, willingness to pay, and likelihood to buy
-4. Include direct customer quotes for authenticity
-5. Create next steps and follow-up questions
-6. Reference the original prep file for context
-7. **Generate personalized follow-up email** using follow-up email templates as reference `get_fraim_file({ path: "templates/customer-development/follow-up-email-templates.md" })` ... add this to the end of the analysis file.
-
-## EXAMPLES
-
-### Good: Insight Analysis
-```
-Input: 
-- File: ronil-dhruva-interview-prep.md
-- Raw notes: "Ronil mentioned calendar conflicts, uses Outlook, frustrated with rescheduling, would pay $50/month, concerned about AI decisions. He was really engaged and seemed to understand the problem well."
-
-AI Agent Process:
-1. Reads existing prep file with LinkedIn research
-2. Extracts insights from raw notes
-3. Creates separate analysis file: ronil-dhruva-interview-analysis.md
-4. Preserves original prep file unchanged
-5. **Generates personalized follow-up email** using follow-up email templates
-6. Creates next steps and follow-up questions
-
-Output:
-- New analysis file: ronil-dhruva-interview-analysis.md
-- Original prep file: ronil-dhruva-interview-prep.md (unchanged)
-- Customer score: 8/10 (high fit, clear pain points, enterprise budget)
-- **Personalized follow-up email** using template structure with customer-specific content
-- Next questions: "What specific hierarchy rules should AI respect?"
-```
-
-### Bad: Surface-Level Analysis
-```
-Input: 
-- File: ronil-dhruva-interview-prep.md
-- Raw notes: "Ronil interview went well"
-
-AI Agent Output:
-- Generic analysis with no specific insights
-- No customer scoring or prioritization
-- No follow-up recommendations
-- No actionable next steps
-
-Result: Lost insights, no clear next steps, wasted prep work
-```
-
-## SUCCESS METRICS
-- **Insight Extraction**: 95% of key insights captured from raw notes
-- **Customer Scoring**: Consistent scoring across all customers
-- **Follow-up Quality**: 80% of follow-up emails result in positive responses
-- **Action Clarity**: Clear next steps for every customer