1A · Customer Feedback Analysis

LOFI BLUEPRINT · Section 1A · Tier 0locked

Purpose: Turn the raw customer corpus into a structured feedback analysis — the prerequisite that grounds targeting and resonance in real voice-of-customer, never invented.

Inputs → Output

Sources

SPP0

Reads

block_b.customer_feedback_corpus

Writes

brand.intake_data.feedback_analysis (jsonb)

Pipeline

Load anchors

SP loaded as system message (voice anchor, Rule 4). Task prompts: SP · P0. Pull ≥3 reference IDs (Rule 2).

Generate

5-section Feedback Analysis Doc per TARGET-REF: Word Cloud · Top 3 Challenges (w/ frequency) · Top 3 Desires (w/ frequency) · Why This Brand themes · Data Source Summary

QA gate

Section 25 auto-runs QA L1 (24 checkpoints) + L2 (6 brand gates). Any L2 fail = REJECT → rewrite.

Cascade

Locked output becomes read-only input to: 1B, 2B. Names must stay identical across sections (cross-section consistency).

Technical Reference

Generation contract (machine-executable)

section: "1A"
id: s01a-feedback-analysis
state: LOFI_BLUEPRINT
tier: 0
sources: ["SP", "P0"]
inputs:
    - block_b.customer_feedback_corpus
output: "5-section Feedback Analysis Doc per TARGET-REF: Word Cloud · Top 3 Challenges (w/ frequency) · Top 3 Desires (w/ frequency) · Why This Brand themes · Data Source Summary"
cascades_from: []
cascades_to: [1B, 2B]

Supabase sync map (from Part 10)

Section 1A ->
  brand.intake_data.feedback_analysis (jsonb)

SCHEMA NOTE: verify all jsonb paths + brand.assets type values against live Supabase before write. Flag missing columns in the PR; never create new columns without review.

Note

This is a LOFI artifact: its consumer is the next generation call, not a customer. Reviewed at the Doc/wizard LOFI gate before any HIFI section reads it. Source of truth: Master Template Part 3 + the Master Index. To change this page, edit content/docs/roadmap/_sections.json and re-run the compiler.