Technical Architecture & Scope Document
Prototype: AI-Enabled 5-Theme Culture Management System
Phase: Prototype / POC
Total Est. Hours: 75-95
Duration: 5 Weeks
Ahmed Reda
Software Engineer
April 20, 2026
1. Executive Engineering Summary
This document defines the exact technical scope, functional modules, technology stack, and delivery
roadmap for the ElKattan Consulting AI Culture System Prototype. The objective is to build a robust,
scalable "Vertical Slice" that proves the system's ability to ingest complex Excel
data, calculate organizational gaps deterministically, and leverage Generative AI (Claude 3.5 Sonnet) to
orchestrate consulting tactics matching the firm's proprietary methodology.
2. Prototype Scope Definition (Vertical Slice)
What is a Vertical Slice?
Instead of building the entire system superficially, the prototype will implement 100% of the
functionality for One Core Value (e.g., Accountability / المسؤولية). This proves
the complete data flow from end to end without spreading resources thin.
✅ In-Scope for Prototype
- Parsing structural and survey data from the "COE Culture Assessment" Excel files.
- Automated Actual vs. Desired Gap Calculation for criteria under the selected Core Value.
- AI generation of Contextual Tactics (Behaviors, Practices, Mindsets, Communication).
- Interactive UI for consultants to review, edit, and approve AI outputs.
- Automated generation and export of a standard PPTX/Word presentation.
3. Core System Architecture & Data Flow
1. Ingestion
ExcelJS Parser
→
2. Logic Core
Node.js / Gap Math
↔
3. AI Engine
Claude 3.5 Sonnet
→
4. Presentation
Next.js / PptxGenJS
4. Detailed Functional Modules
Module 1: Data Ingestion & Normalization Engine
- Excel Upload Interface: Secure drag-and-drop UI for `.xlsx` files.
- Sheet Parsing: Automated reading of specific sheets (e.g., "1.Data",
"11.Org Results").
- Schema Validation: Ensuring data integrity using strict Zod schemas before
processing.
Module 2: Analytical Calculation Core
- Deterministic Logic: Hardcoded mathematical algorithms to calculate gaps
(Desired Score - Actual Score).
- Severity Calibration: Categorizing gaps automatically into bands (Low,
Moderate, High, Critical).
Module 3: AI Orchestration & Generation
- Prompt Engineering: Development of highly optimized, few-shot prompts in
Arabic to guide the AI.
- Structured Outputs (JSON): Forcing the Claude API to return tactics in
strict JSON format.
Module 4: Presentation & Export Engine
- Consultant Dashboard (Next.js): A clean, responsive data table viewing
interface.
- PPTX Generator: Utilizing `PptxGenJS` to map the final approved JSON data
into branded PowerPoint slides dynamically.
5. Comprehensive Technology Stack
| Category |
Technology |
Engineering Justification |
| Frontend / Framework |
Next.js 14 (App Router)
React, TypeScript |
Provides a unified Full-Stack environment. TypeScript ensures end-to-end type safety,
drastically reducing runtime errors. |
| UI / Styling |
Tailwind CSS
Shadcn UI components |
Enables rapid development of highly professional, enterprise-grade B2B interfaces without
writing CSS from scratch. |
| Data & Validation |
ExcelJS, Zod |
ExcelJS handles complex workbooks safely. Zod validates the extracted JSON structure before
feeding it to the AI. |
| Artificial Intelligence |
Anthropic API (Claude 3.5 Sonnet) |
Superior contextual understanding of large documents (BRD) and unmatched fluency in formal
Arabic consulting terminology. |
| Export Generation |
PptxGenJS, docx |
Client-side or Node-based libraries capable of generating native Microsoft Office files
programmatically from JSON data. |
6. Agile Execution Plan: Sprints & BRD Deliverables Mapping
Consulting Alignment: The 5-week engineering timeline is structured into 3 Milestones
matching the exact phases of the KC BRD. Each Sprint concludes with a Review Checkpoint
to validate the code outputs directly against the expected ElKattan Excel/Word deliverables.
Sprint 1 (Week 1): Data Intake & Definitions
- Initialize Clean Architecture and data ingestion engine.
- Automate extraction of Corporate Values and Dimensions.
- Map Cultural Levels, Criteria, and Survey tool logic.
- Ingest Offline data and organizational hierarchy.
🤝 Checkpoint: Extraction Logic Review
- Validate programmatic definitions of values vs. criteria.
- Review accurate mapping of survey statements to dimensions.
📄 BRD Artifacts Digitized (Data Sheets)
0.Intro
2. Values
3.Methodology-Dimensions
4.Dimension Levels
5.Dimension Values
6.Criteria Levels-Dx
6.Dx Levels Description
7.Culture Description
8.Offline Data
10.Org Survey Tool
14.Org Interview
Sprint 2 (Week 2): Gap Math & Calibration
- Program deterministic Gap Calculation algorithms for Org/Sector.
- Implement GAP Calibration rules and Perception gap logic.
- Automate Style Scores and Readiness indexing.
- Compile overall Gap Descriptions into consolidated reports.
🤝 Checkpoint: Gap Calibration Review
- Approve actual vs. desired math against manual COE baseline.
- Validate organizational and perception gap thresholds.
📄 BRD Artifacts Digitized (Analysis Sheets)
11.Org Results
12.GAP Calibration Report
13.Gap Description-Dx
14.a Style Score
14.b Style Readiness Score
15.Org Desired Score
16.Org Analysis
17.Org-Overall-REPORT
18.Dx-Overall-REPORT
19.Perception Gap report
20.Org Criteria Gaps-REPORT
21.Dimension Gaps-Report
Sprint 3 (Week 3): AI Generation & UI
- Map Sub-objectives and Cultural Levers to API contexts.
- Execute engineered Claude 3.5 prompts to generate thematic Tactics.
- Build Consultant Dashboard UI (Interactive Data Tables).
- Develop Inline Editing tool for SMEs to refine AI outputs.
🤝 Checkpoint: AI Consulting Tone Review
- Evaluate AI "Tone of Voice" and consulting terminology accuracy.
- Test consultant approval, editing, and locking workflow (UI).
📄 BRD Artifacts Digitized (Tactics Sheets)
22.Objectives-Org-Dx
23.Objective-Dx-Report
24.Lever & Approached
25.Tactics-Org-D1
27.Tactics-Org-D2
29.Tactics-Org-D3
31.Tactics-Org-D4
26.Tactics-Report-Dx-Ox
28.Tactics-Report-Dx-Ox
30.Tactics-Report-Dx-Ox
32.Tactics-Report-Dx-Ox
33.No of Tactics
Sprint 4 (Week 4): Consolidation & Reporting
- Develop the automated Consolidated Plan compilation.
- Automate Sector-specific Tactics structuring & governance.
- Map out Communication Strategies & Themes.
- Build the Roadmap Timeline generator.
🤝 Checkpoint: Execution Planning Review
- Review formatting, campaign themes, and sector governance mapping.
- Ensure the consolidated roadmap aligns with KC templates.
📄 BRD Artifacts Digitized (Plan Sheets)
34-38.X Tactics-Sec
39.Cosolidated Plan
40.Compaign Theme & Subjects
41.Theme X
42.Roadmap
43.Sec Plan-VX-OX
Sprint 5 (Week 5): Export & Handover
- Implement PptxGenJS and Word export modules.
- Conduct comprehensive End-to-End (E2E) integration testing.
- Process and implement final SME feedback on wording/logic.
- Prepare staging environment for Management Demo.
🤝 Final Review Checkpoint
- Live System Demo (End-to-End file upload to export).
- Official Prototype Sign-off and Project Handover.
📄 Final Output Generation (Documents)
تقرير تقييم الوضع الراهن (Word/PPTX)
وثيقة تصميم الثقافة المستهدفة (Word/PPTX)
خطة إدارة الثقافة المؤسسية (Word/PPTX)
7. Resource & Infrastructure Costs (Prototype Phase)
Development Environment (IDE)
Required
for high-speed AI-assisted engineering and complex context management.
-
Cursor Pro Plus MANDATORY
$60
/ month
Provides
1,500 premium fast requests. Required to handle the massive context
window (BRD + Excel logic) without hitting rate limits.
-
Cursor Pro (Alternative)
$20
/ month
Provides only 500 requests. Not recommended for
this project's intensity.
Operational AI & Cloud Hosting
System
runtime costs associated with generating consulting data and hosting the UI.
-
Claude 3.5 Sonnet API (Anthropic)
$50 - $100
/ estimated total
The core "Brain" of
the application. Billed on a Pay-as-you-go basis for prompt testing and generation.
-
Cloud Hosting (Vercel)
$0
/ Prototype Phase
The Free Tier (Hobby)
provided by Vercel is fully sufficient to host the MVP dashboard for testing and
management demonstration.