Skip to content

proposal: assess adding lesson 09 (ai-agents) #2

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
passadis merged 2 commits into from
Aug 6, 2026
Merged

proposal: assess adding lesson 09 (ai-agents) #2

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
0ab6b3f
Initial plan
Copilot Aug 6, 2026
a65c532
docs: add lesson 09 assessment proposal with no-go recommendation
Copilot Aug 6, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 11 additions & 0 deletions docs/proposals/new-lesson-ai-agents.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,11 @@
# Proposal: Assessing a potential Lesson 09 (AI agents)

## 1) Gap analysis
The current 8-lesson arc is coherent and progressive for beginners: Lesson 01 establishes GenAI/LLM fundamentals, 02 gets learners shipping a first app, 03 improves prompt quality, 04 introduces structured outputs, 05 adds grounded responses with RAG, 06 adds capability extension through tool calling, and 07-08 teach MCP basics and advanced MCP client patterns. Together, this already covers the core path from "hello world" prompting to practical interoperability patterns in JavaScript.

The single most valuable missing topic is **AI agents/orchestration**, because it is the natural next conceptual step after tool-calling (06) and MCP integration (07-08): learners can combine model reasoning, tool selection, and iterative execution into a controlled loop. Compared with evaluations/testing, safety/guardrails, multimodal apps, deployment, or observability/cost, agents are the strongest fit *for this specific course narrative and sequence* since they directly compose concepts already taught here (prompts + tools + MCP) into end-to-end behavior learners can immediately recognize and build on.

## 2) Go / No-go recommendation
> ## **NO-GO (for now)**

Although AI agents are the most logical next topic, I recommend **not** adding Lesson 09 in this PR. For this beginner track, the current 8-lesson scope is already complete and appropriately bounded, and introducing agents now risks increasing conceptual load right after MCP. The repository already points learners to a dedicated **AI Agents for Beginners** course, which is a better venue for deeper agent orchestration patterns without overextending this course’s beginner promise. Revisit a Lesson 09 proposal later only if maintainers explicitly want this course to expand beyond its current foundational scope.