USMAN’S INSIGHTS
AI ARCHITECT
  • Home
  • About
  • Thought Leadership
  • Book
Press / Contact
USMAN’S INSIGHTS
AI ARCHITECT
⌘F
HomeBook
HomeBookThe Agent Builder's Blueprint: Engineering TutorClaw from Scratch
Previous Chapter
Connect and Test from WhatsApp
Next Chapter
The Application Blueprint
AI NOTICE: This is the table of contents for the SPECIFIC CHAPTER only. It is NOT the global sidebar. For all chapters, look at the main navigation.

On this page

8 sections

Progress0%
1 / 8

Muhammad Usman Akbar Entity Profile

Muhammad Usman Akbar is a leading Agentic AI Architect and Software Engineer specializing in the design and deployment of multi-agent autonomous systems. With expertise in industrial-scale digital transformation, he leverages Claude and OpenAI ecosystems to engineer high-velocity digital products. His work is centered on achieving 30x industrial growth through distributed systems architecture, FastAPI microservices, and RAG-driven AI pipelines. Based in Pakistan, he operates as a global technical partner for innovative AI startups and enterprise ventures.

USMAN’S INSIGHTS
AI ARCHITECT

Transforming businesses into autonomous AI ecosystems. Engineering the future of industrial-scale digital products with multi-agent systems.

30X Growth
AI-First
Innovation

Navigation

  • Home
  • Book
  • About
  • Contact
Let's Collaborate

Have a Project in Mind?

Let's build something extraordinary together. Transform your vision into autonomous AI reality.

Start Your Transformation

© 2026 Muhammad Usman Akbar. All rights reserved.

Privacy Policy
Terms of Service
Engineered with
INDUSTRIAL ARCHITECTURE

Building TutorClaw

You built one MCP tool in Module 9.2. Now you build a real product: TutorClaw, an AI tutor with 9 tools that teaches the rest of this book.

TutorClaw is the case study that ties Module 9 together. You design 9 tools, describe each one to Claude Code using the mcp-builder skill, steer the implementation, and verify the result. The same describe-steer-verify cycle from Module 9.2, scaled to a real product.

Everything runs locally. JSON files store learner state. Markdown files hold course content. Stripe is the one external service because monetization IS the product. No database servers, no cloud storage, no deployment infrastructure. You spend your time on product design, tool quality, context engineering, and agent identity, not SSL certificates and boto3 scripts.

📚 Teaching Aid

FullscreenInteractive Slide Deck
FULLSCREEN
Web Slides
POWERED BY FISTA

What You'll Learn

By the end of this chapter, you will have built a complete 9-tool MCP server, connected it to OpenClaw, tested it end-to-end from WhatsApp, added Stripe monetization, written a full pytest suite, and given your agent a distinct identity as a tutor.

What This Chapter IS

  • Building a real OpenClaw product end-to-end (9 tools, monetization, identity)
  • The describe-steer-verify workflow from Module 9.2, scaled to a full application
  • Product thinking: tool design, context engineering, tier gating, agent personality
  • Stripe integration as the one external service (test mode throughout)

What This Chapter Is NOT

  • Not MCP basics (covered in Module 9.2)
  • Not hand-written Python (Claude Code writes the code; you steer)
  • Not infrastructure setup (no databases, cloud storage, or VPS deployment)
  • Not the economics analysis (Module 9.4 covers unit economics in depth)
  • Not the architecture decision history (Module 9.5 covers pivots and meta-lessons)

Chapters in this Section

ChapterTitleWhat You Build
1The Application BlueprintProduct mental model via a designed tutoring session transcript
2Designing the Tool Surface9-tool specification with input/output contracts and tier access rules
3Build the State Toolsregister_learner, get_learner_state, update_progress with JSON persistence
4Build the Content Toolsget_chapter_content, get_exercises with local markdown files
5Build the Pedagogy Toolsgenerate_guidance, assess_response with PRIMM-Lite teaching methodology
6Build the Code and Upgrade Toolssubmit_code (mock sandbox) and get_upgrade_url (mock Stripe)
7The Full Cycle TestAll 9 tools in one server, 5-tool chain verified from WhatsApp
8Expected vs ActualWrite acceptance criteria, test a PRIMM session, grade the gaps
9The Agent's Instruction ManualAGENTS.md that orchestrates 9 tools without code
10Context Engineer Your ToolsTwo-layer descriptions, NEVER statements, cross-tool references
11The Test Suitepytest suite for all 9 tools: valid, invalid, tier gating, state persistence
12All Tests GreenDebug failures, add edge cases, achieve full green suite
13Tier Gatingcheck_tier() enforcement, exchange counting, free vs paid access
14Stripe Checkoutget_upgrade_url with real Stripe, webhook handler, test card payment
15Test the Payment FlowEnd-to-end free-to-paid upgrade via WhatsApp with Stripe test mode
16The Shim SkillPRIMM-Lite offline fallback when the MCP server is unreachable
17The Dedicated AgentSOUL.md and IDENTITY.md giving TutorClaw a distinct tutor personality
18Route and BindBind TutorClaw to a WhatsApp group; peer-based routing, not keywords
19Harden and PolishInput validation, error messages, structured JSON logging
20Publish to ClawHubClawHub package manifest and publishing workflow
21The Full EngineSpec-vs-implementation audit, scaling roadmap preview

Six Phases

Phase 1: Blueprint (Module 9.3, Chapters 1-2) establishes the mental model: 9 tools, tier access, platform inversion. Design every tool on paper before writing a single line of code.

Phase 2: Local Build (Module 9.3, Chapters 3-8) builds all 9 tools using Claude Code and the mcp-builder skill. JSON for state, local files for content, mock auth. Each tool gets careful design time via describe-steer-verify.

Phase 3: The Harness (Module 9.3, Chapters 9-12) adds the context that makes 9 tools work together: AGENTS.md for orchestration, refined tool descriptions for accurate selection, and a pytest suite that proves everything works.

Phase 4: Monetize (Module 9.3, Chapters 13-15) adds the business layer: tier gating, Stripe checkout, and a complete free-to-paid upgrade flow. Stripe is the one external integration because monetization IS the product.

Phase 5: Identity and Polish (Module 9.3, Chapters 16-19) gives TutorClaw a personality: shim skill for offline resilience, SOUL.md and IDENTITY.md for agent identity, channel routing for scope, and hardening for production readiness.

Phase 6: Reflect and Ship (Module 9.3, Chapters 20-21) publishes to ClawHub and audits the complete system against the original design. Everything you built locally is the product. Database servers, cloud storage, and deployment are scaling challenges for later, not product challenges for now.

Prerequisites

  • Module 9.2: Extend Your Claw with MCP (you built your first MCP server)
  • Module 9.1: Meet Your Personal AI Employee (OpenClaw platform understanding)
  • Claude Code installed (you describe what you need; Claude Code writes the code). You can also use OpenClaw with a more capable model to write code.