Solutions Architect

3 courses · ~12 hours· 1 certification available

phase 1 — How models work

Build the foundation to evaluate model capabilities and make technology selection decisions.

[ ] Understanding Transformers [preview]

Understanding attention and embeddings gives you the foundation to evaluate model capabilities, compare architectures, and make technology selection decisions.

2 sections · 4 lessons

[ ] Attention Mechanisms (3 lessons)
[ ] Embeddings (1 lesson)

[→ start course]

phase 2 — How models interact with systems

Learn the integration layer between AI models and your existing systems.

[ ] Understanding Tool Calling

Tool calling is the integration layer between AI models and your existing systems. This is where your architecture diagrams connect to the model.

4 sections · 10 lessons

[ ] Foundations (2 lessons)
[ ] How Models Decide (2 lessons)
[ ] Advanced Patterns (3 lessons)
[ ] Security and Production (3 lessons)

[→ start course]

phase 3 — Systems-level AI engineering

Learn the systems programming of AI — memory management, process isolation, message passing.

[ ] Context Engineering

Context engineering is the systems programming of AI — memory management, process isolation, message passing. The concepts map directly to distributed systems architecture.

8 sections · 25 lessons

[ ] Tokens and Inference (2 lessons)
[ ] The Real Size of Your Context Window (4 lessons)
[ ] Anatomy of the Messages Array (5 lessons)
[ ] Dynamic Allocation: Tool Calling (2 lessons)
[ ] The Ralph Wiggum Loop (3 lessons)
[ ] Sub-Agents: Managed Runtimes for AI (3 lessons)
[ ] Message Passing: The Erlang OTP of AI (3 lessons)
[ ] Context Management Strategies (3 lessons)

certification: Certified Context Engineer

[→ start course]

key terms

Transformer·Tool Calling·Context Engineering·Agent·Sub-Agent·System Prompt·Model Context Protocol (MCP)

Solutions Architect

phase 1 — How models work

phase 2 — How models interact with systems

phase 3 — Systems-level AI engineering

key terms

related reading