From c3defa4419fcef8bd1fdeb1654128b77496b1bc8 Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" <41898282+github-actions[bot]@users.noreply.github.com> Date: Wed, 29 Jul 2026 18:29:24 +0000 Subject: [PATCH] Add theme-aware explanatory diagram for classic Actions vs agentic workflow Migrates the existing single-theme 00-actions-vs-agentic.svg to a light/dark SVG pair and wires it into workshop/05-agentic-workflows-intro.md next to Activity 2 (agentic or standard?). Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --- workshop/05-agentic-workflows-intro.md | 8 ++ .../images/00-actions-vs-agentic-dark.svg | 124 ++++++++++++++++++ .../images/00-actions-vs-agentic-light.svg | 124 ++++++++++++++++++ 3 files changed, 256 insertions(+) create mode 100644 workshop/images/00-actions-vs-agentic-dark.svg create mode 100644 workshop/images/00-actions-vs-agentic-light.svg diff --git a/workshop/05-agentic-workflows-intro.md b/workshop/05-agentic-workflows-intro.md index 7bfd32d1..bc5ca52e 100644 --- a/workshop/05-agentic-workflows-intro.md +++ b/workshop/05-agentic-workflows-intro.md @@ -53,6 +53,14 @@ Now check your prediction: did you name both files and identify which one Action ## Activity 2 — agentic or standard? +The diagram below shows how the same schedule trigger leads to two very different outcomes — one driven by static YAML, the other by an AI agent with built-in safety guardrails. + + + + + Side-by-side comparison of Classic GitHub Actions YAML versus an Agentic Workflow with safety highlights. Classic: schedule trigger flows through static YAML steps and shell scripts to produce output. Agentic: same trigger flows through a plain-English task brief with safety config (permissions, tools, safe-outputs) into a sandbox-isolated AI agent that applies integrity filtering and zero-secrets constraints, producing output only through declared safe-output surfaces. + + Read each task and decide before revealing the answer. **Task A:** Run lint and unit tests on every pull request, fail if any check exits non-zero. diff --git a/workshop/images/00-actions-vs-agentic-dark.svg b/workshop/images/00-actions-vs-agentic-dark.svg new file mode 100644 index 00000000..c88d0bac --- /dev/null +++ b/workshop/images/00-actions-vs-agentic-dark.svg @@ -0,0 +1,124 @@ + + + + + + Classic GitHub Actions vs Agentic Workflow + Same trigger — safety built in: sandbox · zero secrets · integrity filtering · safe outputs. + + + + + + BEFORE — Classic Actions YAML + + + + ⏰ Schedule Trigger + cron: "0 8 * * *" + + + + + + + 📄 Static YAML Steps + checkout → run script + → call API → format + → post comment + ~200 lines of YAML + shell + + + + + + + 🐚 Shell Scripts + hard-coded logic + + + 🔧 API Calls + explicit plumbing + + + + + + + + + + + + + + + 📋 Report Posted + but brittle to maintain + + + + + + AFTER — Agentic Workflow Markdown + + + + ⏰ Schedule Trigger + cron: "0 8 * * *" + + + + + + + 📝 Task Brief + Safety Config + "Create a daily repo status update." + permissions: read · tools: gh-proxy + safe-outputs: write-summary + ~20 lines of Markdown + + + + + + + 🏖️ Sandbox — isolated, ephemeral runner + + + + 🤖 AI Agent + Reads live repo state · decides what matters + Uses only declared tools and permissions + + + + 🔒 Zero Secrets + + + + 🔍 Integrity Filter + + + + + + + 📤 Safe Outputs + Report posted to declared write surface + + + + + VS + + + Safety is built in: sandbox isolation · no secret leakage · integrity filtering · safe-output surfaces enforced at runtime. + + + + + + + + diff --git a/workshop/images/00-actions-vs-agentic-light.svg b/workshop/images/00-actions-vs-agentic-light.svg new file mode 100644 index 00000000..66c5f775 --- /dev/null +++ b/workshop/images/00-actions-vs-agentic-light.svg @@ -0,0 +1,124 @@ + + + + + + Classic GitHub Actions vs Agentic Workflow + Same trigger — safety built in: sandbox · zero secrets · integrity filtering · safe outputs. + + + + + + BEFORE — Classic Actions YAML + + + + ⏰ Schedule Trigger + cron: "0 8 * * *" + + + + + + + 📄 Static YAML Steps + checkout → run script + → call API → format + → post comment + ~200 lines of YAML + shell + + + + + + + 🐚 Shell Scripts + hard-coded logic + + + 🔧 API Calls + explicit plumbing + + + + + + + + + + + + + + + 📋 Report Posted + but brittle to maintain + + + + + + AFTER — Agentic Workflow Markdown + + + + ⏰ Schedule Trigger + cron: "0 8 * * *" + + + + + + + 📝 Task Brief + Safety Config + "Create a daily repo status update." + permissions: read · tools: gh-proxy + safe-outputs: write-summary + ~20 lines of Markdown + + + + + + + 🏖️ Sandbox — isolated, ephemeral runner + + + + 🤖 AI Agent + Reads live repo state · decides what matters + Uses only declared tools and permissions + + + + 🔒 Zero Secrets + + + + 🔍 Integrity Filter + + + + + + + 📤 Safe Outputs + Report posted to declared write surface + + + + + VS + + + Safety is built in: sandbox isolation · no secret leakage · integrity filtering · safe-output surfaces enforced at runtime. + + + + + + + +