Skip to content

Commit 1d0a0d1

Browse files
Copilotpelikhan
Copilot
and
pelikhan
authored
split 05-agentic-workflows-intro into concept + practice pages to improve learning score (#1897)
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>
1 parent e6361e8 commit 1d0a0d1

4 files changed

Lines changed: 85 additions & 51 deletions

File tree

‎.github/skills/micro-environment-simulator/workshop-student-journey.js‎

Lines changed: 14 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -33,6 +33,7 @@ const STEP_FILE_ALIASES = {
3333
"02-setup": ["02a-setup-codespace.md", "02b-setup-local.md", "02c-setup-browser.md"],
3434
"04-actions-intro": ["04-github-actions-intro.md"],
3535
"05-agentic-intro": ["05-agentic-workflows-intro.md"],
36+
"05c-agentic-practice": ["05c-agentic-workflows-practice.md"],
3637
"05b-agentic-security": ["05b-agentic-workflows-security.md"],
3738
"06-install-gh-aw": [
3839
"06-install-gh-aw.md",
@@ -72,6 +73,7 @@ const STEP_IDS = [
7273
"02-setup",
7374
"04-actions-intro",
7475
"05-agentic-intro",
76+
"05c-agentic-practice",
7577
"05b-agentic-security",
7678
"06-install-gh-aw",
7779
"07-first-workflow",
@@ -657,6 +659,18 @@ function buildTransitions() {
657659
next.flags.sawAgenticIntro = true;
658660
return { ok: true, state: applyLearning(next, context, { agentic: 0.1, actions: 0.03 }) };
659661
},
662+
"05c-agentic-practice": (state, context) => {
663+
const readiness = contentReadinessCheck(state, context, {
664+
salt: 74,
665+
category: "agentic-classification-gap",
666+
failedAssumption: "The learner cannot reliably distinguish tasks that need agentic judgment from those suited to deterministic CI/CD steps.",
667+
remediation: "Add more contrasting examples with explicit before/after explanations to make the classification pattern more memorable.",
668+
emphasis: { conceptWeight: 0.14, bias: 0.06 }
669+
});
670+
if (!readiness.ok) return readiness;
671+
const next = cloneState(state);
672+
return { ok: true, state: applyLearning(next, context, { agentic: 0.06, concepts: 0.04 }) };
673+
},
660674
"05b-agentic-security": (state, context) => {
661675
const readiness = contentReadinessCheck(state, context, {
662676
salt: 79,

‎workshop/05-agentic-workflows-intro.md‎

Lines changed: 1 addition & 51 deletions
Original file line numberDiff line numberDiff line change
@@ -84,62 +84,12 @@ The **compile command** — it reads the `.md` source and writes the `.lock.yml`
8484
> [!TIP]
8585
> Want more examples of how the two-file structure works? [Side Quest: Agentic Workflows Deep Dive](side-quest-05-02-aw-deep-dive.md) includes a fully annotated workflow pair.
8686
87-
## Try it: agentic or standard?
88-
89-
For each task below, decide whether it calls for an **agentic workflow** or a **standard Actions workflow**, then reveal the answer.
90-
91-
**Task A:** Run lint and unit tests on every pull request, fail if any check exits non-zero.
92-
93-
- [ ] I've made my decision for Task A
94-
95-
<details>
96-
<summary>Reveal Task A answer</summary>
97-
98-
**Standard Actions workflow.** Every run follows the same fixed steps: run lint, run tests, report the exit code. No judgment is required.
99-
100-
</details>
101-
102-
**Task B:** Each morning, read all open issues, decide which ones look most urgent, and post a short triage summary.
103-
104-
- [ ] I've made my decision for Task B
105-
106-
<details>
107-
<summary>Reveal Task B answer</summary>
108-
109-
**Agentic workflow.** The agent reads live issue data, applies judgment to assess urgency, and composes a summary that differs every run based on what it finds.
110-
111-
</details>
112-
113-
> [!TIP]
114-
> Want to go deeper? [Side Quest: Agentic Workflows Deep Dive](side-quest-05-02-aw-deep-dive.md) covers more exercises, example output, the two-file structure, and concept checks.
115-
116-
## Try it: write a one-sentence task brief
117-
118-
Pick any routine task you do today that involves reading some data and writing a summary — a daily standup note, a weekly inbox digest, or a triage of support tickets. Write a one-sentence task brief for an agent to do it automatically.
119-
120-
Your brief should answer: *what data should the agent read, and what should it post when it's done?*
121-
122-
Example:
123-
124-
```
125-
Each Monday morning, read all pull requests opened in the past week,
126-
identify the three with the most review comments, and post a summary
127-
as an issue with the title "Weekly PR Digest".
128-
```
129-
130-
- [ ] I've drafted a one-sentence task brief for a real routine task
131-
- [ ] My brief specifies what data the agent should read
132-
- [ ] My brief specifies what the agent should post when done
133-
134-
> [!TIP]
135-
> Struggling to think of a task? Browse the [gh-aw issue-ops pattern](https://github.github.com/gh-aw/patterns/issue-ops/) for inspiration. You will write a real version of your brief in Step 7.
136-
13787
## ✅ Checkpoint
13888

13989
- [ ] I can describe what an agentic workflow is in one sentence
14090
- [ ] I can explain one way an agentic workflow differs from a standard Actions workflow
14191
- [ ] I can identify the three parts: trigger → agent → safe output
14292

14393
<!-- journey: all -->
144-
**Next:** [How Agentic Workflows Stay Safe](05b-agentic-workflows-security.md)
94+
**Next:** [Practice: Recognize Agentic Workflows](05c-agentic-workflows-practice.md)
14595
<!-- /journey -->

‎workshop/05c-agentic-workflows-practice.md‎

Lines changed: 69 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,69 @@
1+
<!-- page-journey: all -->
2+
<!-- page-adventure: core -->
3+
# Practice: Recognize Agentic Workflows
4+
5+
## 📋 Before You Start
6+
7+
- You've read [What Are Agentic Workflows?](05-agentic-workflows-intro.md)
8+
9+
These exercises help you apply what you just learned — deciding when to use an agentic workflow and drafting your first task brief.
10+
11+
## Try it: agentic or standard?
12+
13+
For each task below, decide whether it calls for an **agentic workflow** or a **standard Actions workflow**, then reveal the answer.
14+
15+
**Task A:** Run lint and unit tests on every pull request, fail if any check exits non-zero.
16+
17+
- [ ] I've made my decision for Task A
18+
19+
<details>
20+
<summary>Reveal Task A answer</summary>
21+
22+
**Standard Actions workflow.** Every run follows the same fixed steps: run lint, run tests, report the exit code. No judgment is required.
23+
24+
</details>
25+
26+
**Task B:** Each morning, read all open issues, decide which ones look most urgent, and post a short triage summary.
27+
28+
- [ ] I've made my decision for Task B
29+
30+
<details>
31+
<summary>Reveal Task B answer</summary>
32+
33+
**Agentic workflow.** The agent reads live issue data, applies judgment to assess urgency, and composes a summary that differs every run based on what it finds.
34+
35+
</details>
36+
37+
> [!TIP]
38+
> Want to go deeper? [Side Quest: Agentic Workflows Deep Dive](side-quest-05-02-aw-deep-dive.md) covers more exercises, example output, the two-file structure, and concept checks.
39+
40+
## Try it: write a one-sentence task brief
41+
42+
Pick any routine task you do today that involves reading some data and writing a summary — a daily standup note, a weekly inbox digest, or a triage of support tickets. Write a one-sentence task brief for an agent to do it automatically.
43+
44+
Your brief should answer: *what data should the agent read, and what should it post when it's done?*
45+
46+
Example:
47+
48+
```
49+
Each Monday morning, read all pull requests opened in the past week,
50+
identify the three with the most review comments, and post a summary
51+
as an issue with the title "Weekly PR Digest".
52+
```
53+
54+
- [ ] I've drafted a one-sentence task brief for a real routine task
55+
- [ ] My brief specifies what data the agent should read
56+
- [ ] My brief specifies what the agent should post when done
57+
58+
> [!TIP]
59+
> Struggling to think of a task? Browse the [gh-aw issue-ops pattern](https://github.github.com/gh-aw/patterns/issue-ops/) for inspiration. You will write a real version of your brief in Step 7.
60+
61+
## ✅ Checkpoint
62+
63+
- [ ] I can decide whether a task calls for an agentic or a standard Actions workflow
64+
- [ ] I have drafted a one-sentence task brief that specifies what data to read and what to post
65+
- [ ] I can describe the three parts of an agentic workflow: trigger → agent → safe output
66+
67+
<!-- journey: all -->
68+
**Next:** [How Agentic Workflows Stay Safe](05b-agentic-workflows-security.md)
69+
<!-- /journey -->

‎workshop/README.md‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -11,6 +11,7 @@ A hands-on workshop that takes you from zero to a fully automated, AI-powered wo
1111
| 2 | Choose one: [02a-setup-codespace.md](02a-setup-codespace.md), [02b-setup-local.md](02b-setup-local.md), **or** [02c-setup-browser.md](02c-setup-browser.md) | Setup Adventure — A: Codespace, B: Local Terminal, or C: Browser (no terminal) | ✅ |
1212
| 4 | [04-github-actions-intro.md](04-github-actions-intro.md) | What Are GitHub Actions? | ✅ |
1313
| 5 | [05-agentic-workflows-intro.md](05-agentic-workflows-intro.md) | What Are Agentic Workflows? | ✅ |
14+
| 5c | [05c-agentic-workflows-practice.md](05c-agentic-workflows-practice.md) | Practice: Recognize Agentic Workflows | ✅ |
1415
| 5b | [05b-agentic-workflows-security.md](05b-agentic-workflows-security.md) | How Agentic Workflows Stay Safe | ✅ |
1516
| 6 | [06-install-gh-aw.md](06-install-gh-aw.md) | Install the gh-aw CLI Extension | ✅ |
1617
| 6a | [06a-install-terminal.md](06a-install-terminal.md) | Codespace Terminal Path — Install gh-aw | ✅ |

0 commit comments

Comments
 (0)