@@ -22,9 +22,11 @@ Start with SDK 101 if you are new to the SDK. Across the introductory and deeper
22224 . Enforce capability, input, timeout, validation, and lifecycle boundaries in application code.
23235 . Explain what the model can infer and what the application must prove.
2424
25- SDK 101 has exactly 30 minutes of guided lessons. Plan on about 90 minutes for Accessibility
26- Reviewer or 75 minutes for Museum Exhibit Studio. Machine setup, authentication, and dependency
25+ SDK 101 has exactly 30 minutes of guided lessons.
26+ Plan on about 115 minutes for Accessibility Reviewer or 90 minutes for Museum Exhibit Studio.
27+ Machine setup, authentication, and dependency
2728downloads happen separately in an untimed preflight for each workshop.
29+ The two deeper workshops include their interactive HTML lessons and end with a celebration and resources.
2830
2931## Start the workshop
3032
@@ -67,7 +69,7 @@ output, and troubleshooting.
6769``` text
6870copilot-sdk-workshop/
6971|-- docs/ GitHub Pages site and controlled target page
70- |-- workshop/ SDK 101 and two deeper tracks with optional extensions
72+ |-- workshop/ SDK 101, two deeper tracks, and completion resources
7173|-- start-intro/ SDK 101 starters and podcast helpers in all six languages
7274|-- start-accessibility/ Accessibility Reviewer starters in all six languages
7375|-- start-museum/ Museum Exhibit Studio starters in all six languages
@@ -93,7 +95,7 @@ bash scripts/validate-workshop.sh
9395
9496The command checks lesson structure, internal links, site behavior hooks, project coverage,
9597and the introductory track's exact 30-minute lesson budget.
96- It then runs browser-independent language-selection tests and restores, builds, or syntax-checks every
98+ It then runs browser-independent language-selection, site-flow, and completion tests and restores, builds, or syntax-checks every
9799intro, accessibility, and museum starter, every finished project, and the Blazor target without authenticating
98100Copilot, launching a browser, or sending a prompt. The museum projects ship no tests, mocks, or
99101fixtures, so their targets only restore and build.
@@ -145,9 +147,10 @@ system messages, the prompt builders, one session runner that owns the lifecycle
145147` main ` . The finished sample is what a learner ends up with, not a separate reference architecture.
146148
147149The learner-facing track begins at
148- [ ` workshop/museum-00-preflight.md ` ] ( workshop/museum-00-preflight.md ) , then runs through six core
150+ [ ` workshop/museum-00-preflight.md ` ] ( workshop/museum-00-preflight.md ) , then runs through seven
149151steps — first session, streaming, curator voice, approved facts, structural checks, and
150- Wikipedia MCP research — plus an optional interactive ` exhibit.html ` capstone.
152+ Wikipedia MCP research, followed by an interactive ` exhibit.html ` capstone — and finishes with
153+ [ celebration and resources] ( workshop/museum-09-complete.md ) .
151154
152155When usable cited research exists, the curator calls ` approved_fact_lookup ` and the read-only
153156` approved_wikipedia_fact_lookup ` before writing the narrative and visitor questions. The second
0 commit comments