Proposal Review

Methodically review proposals by chunking content, predicting feedback, and producing actionable output for the proposer.

Workflow

┌─────────────────────────────────────────────────────────────┐
│  1. INTAKE: Read entire proposal, identify source format    │
├─────────────────────────────────────────────────────────────┤
│  2. CHUNK: Split into reviewable sections (smart hybrid)    │
├─────────────────────────────────────────────────────────────┤
│  3. REVIEW LOOP: For each chunk:                            │
│     • Present chunk content                                 │
│     • Predict 3-4 likely reactions                          │
│     • Use AskUserQuestion for feedback                      │
│     • Record response                                       │
├─────────────────────────────────────────────────────────────┤
│  4. SYNTHESIZE: Compile feedback, infer overall sentiment   │
├─────────────────────────────────────────────────────────────┤
│  5. OUTPUT: Generate feedback document matching source      │
└─────────────────────────────────────────────────────────────┘

Phase 1: Intake

Read the entire proposal. Identify:

• Source format: Local file, GitHub PR/issue/gist, Google Doc export, etc.
• Structure: Headers, sections, numbered lists, or flowing prose
• Length: Estimate chunk count (aim for 3-8 chunks for typical proposals)

Do not summarize or share initial impressions. Proceed directly to chunking.

Phase 2: Chunking Strategy

Use smart hybrid chunking:

Chunk ordering: Present in document order unless there's a clear dependency (e.g., "Alternatives" before "Proposed Solution" if alternatives inform the solution review).

Phase 3: Review Loop

For each chunk:

3.1 Present the Chunk

Quote or summarize the chunk content. For longer chunks, quote key sentences and summarize the rest. Use a clear header like:

### Chunk 2 of 5: Technical Architecture

3.2 Predict Reactions

Generate 3-4 predicted reactions spanning these categories:

Select predictions that feel most relevant to this specific chunk. Not every chunk needs all categories.

3.3 Collect Feedback

Use AskUserQuestion with:

• Predicted reactions as options (2-4 most likely)
• User can select one OR provide custom feedback via "Other"
• Keep option labels concise (under 10 words), use description for detail

Example:

question: "What's your reaction to this technical architecture section?"
header: "Architecture"
options:
  - label: "Looks good"
    description: "The proposed architecture is sound and well-reasoned"
  - label: "Scope concern"
    description: "This feels too ambitious for the timeline"
  - label: "Need clarification"
    description: "Some technical details are unclear or missing"
  - label: "Consider alternative"
    description: "There may be a simpler or better approach"

3.4 Record Response

Store each response with:

• Chunk identifier (number + title)
• Selected option or custom text
• Any quoted content the feedback references

Phase 4: Synthesis

After all chunks reviewed:

1. Group feedback by theme: Consolidate similar concerns across chunks
2. Infer overall sentiment: Based on feedback distribution:
   • Mostly approvals → Positive with minor suggestions
   • Mixed → Conditional support, needs revisions
   • Mostly concerns → Significant issues to address
3. Identify patterns: Note if same concern appears multiple times

Then ask:

question: "Would you like me to include suggested next steps for the proposer?"
header: "Next Steps"
options:
  - label: "Yes, include action items"
    description: "Generate concrete next steps based on feedback"
  - label: "No, just the feedback"
    description: "Keep output to observations and reactions only"

Phase 5: Output Generation

Adapt output format to source:

...