mancitrus/system-prompts-and-models-of-ai-tools

mirror of https://github.com/x1xhlol/system-prompts-and-models-of-ai-tools.git synced 2026-06-18 23:39:34 +00:00

Phase 2 Execution Waves: 90-day plan + Verification Protocol scaffolding

Saves the DEALIX_PHASE2_EXECUTION_WAVES.md 90-day plan and scaffolds every
artifact the coding agent can produce. Wave A-E execution is explicitly
blocked until the Week-12 Phase Gate (§3) returns Green.

Added:
  §1 Verification Protocol (V001-V007)
    - scripts/v001_secret_scan.sh — trufflehog + gitleaks full-history scan
    - backend/tests/security/test_rls_fuzz.py — 10K cross-tenant fuzz
    - docs/verification/V003_pentest_engagement.md — vendor RFP + scope
    - docs/verification/V004_no_founder_demo_test.md — 3-tester protocol
    - scripts/v005_truth_registry_audit.py — independent audit tool
    - infra/load-tests/baseline.js — k6 perf baseline
    - frontend/tests/a11y/baseline.spec.ts — Playwright+axe baseline
    - docs/baselines/README.md + docs/verification/README.md

  §2 Founder Decision Sprint (FD001-FD005)
    - docs/internal/legal_entity_decision.md — MISA/DIFC/Delaware brief
    - docs/internal/trademark_status.md — SAIP filing kit tracker
    - docs/hiring/{design_engineer, backend_engineer, head_of_cs}.md

  §3 Customer Validation (CV001-CV004)
    - docs/customer_learnings/pilot_agreement_template.md
    - docs/customer_learnings/pilot_template/success_criteria.md
    - docs/customer_learnings/pilot_template/kickoff_checklist.md
    - docs/customer_learnings/friction_log.md + feature_requests.yaml
    - docs/customer_learnings/weekly_review_template.md

  Truth registry updates
    - docs/registry/TRUTH.yaml — new verification_protocol,
      founder_decision_sprint, customer_validation sections

Gates (post-change):
  architecture_brief.py     40/40
  release_readiness_matrix  94/94 (added 30 new scaffold checks)
  v005_truth_registry_audit 19/19 SUPPORTED

2026-04-17 11:13:27 +00:00

2.6 KiB

Raw Blame History

V004 — No-Founder Customer Demo Test

Status: Template ready — founder schedules 3 sessions Gate: Acceptance = 2 of 3 fresh testers complete the golden path unassisted in <30 minutes with no show-stopper Target completion: Week 6

Purpose

Eliminate "founder-assisted success" bias. If the product requires the founder in the room, it is not ready for pilot.

Tester Profile (matches ICP Filter §3)

Commercial operations background (CFO adjacent, Sales Ops, RevOps)
3+ years in Saudi/GCC enterprise
Bilingual (Arabic + English)
Has NOT been exposed to Dealix demo before
NOT a founder friend (too generous in feedback)
Compensated 500 SAR + short LinkedIn endorsement

Protocol

Before the Session

Provide tester a single PDF brief (2 pages max) with:
- What Dealix is (30 seconds)
- Credentials for a seeded demo tenant
- Goal: "Bring a new partner through the golden path and generate an evidence pack"
Confirm tester will screen-share
Confirm 60-minute window (30 for task + 30 for retro)

During the Session

Founder is on the call but MUTED and video OFF
Tester proceeds without assistance
Observer (founder + one engineer) takes notes on the Friction Log template
DO NOT intervene even if tester is stuck, unless >10 minutes on same step → then ask: "What are you trying to do right now?" (diagnostic only)

After the Session

Ask tester 5 questions (see below)
Tester uninstalls / forgets credentials
Add findings to docs/customer_learnings/friction_log.md within 24h

The 5 Post-Session Questions

In one sentence, what did Dealix do for you?
What was the one thing that felt confusing or wrong?
On a scale of 1–10, how likely are you to recommend this to a peer CFO/COO? (NPS)
What word(s) would you use to describe the UI? (signature capture)
If you had to pay $3,000/year for this, what would you need to see added first?

Scoring (Pass / Fail per tester)

Dimension	Pass	Fail
Time to golden path completion	<30 min	>30 min or abandoned
Show-stoppers encountered	0	1+ (e.g., crash, auth loop, untranslated Arabic, broken approval)
NPS	≥7	≤6
Arabic experience	"clean" or "native"	"broken" or "translated feel"

Overall verdict: 2 of 3 testers PASS → V004 green. Anything less → iterate UX before pilot.

Deliverables

3 session recordings archived at docs/customer_learnings/v004/ (PRIVATE)
3 completed friction logs
Aggregated findings report at docs/customer_learnings/v004/summary.md
Top-5 UX issues added to Wave A backlog

2.6 KiB Raw Blame History Unescape Escape