agenticlately · GH-600 Study Prep
Home Phase A Lesson 1.2
PHASE A · LESSON 1.2

Agent vs workflow

You already met the GitHub Actions workflow in Phase 0 — the robot that runs fixed steps. Now meet its cousin, the agent. The difference is one question: who decides the next step? Get that, and you'll know when to reach for each.

~6 minread 4quiz questions Tier 1source cited
Story

You need to get across the city.

A train runs on rails. Same route every trip — stop A, stop B, stop C — no matter what. It never decides anything. It's predictable and repeatable, and if the track is laid right it just works, a thousand times the same. But it can't reroute. If your stop isn't on the line, the train can't help you.

A car with a driver gets a destination — "take me to the airport" — and the driver decides the route. Highway jammed? Side streets. Road closed? Another way. They handle a goal, not a script.

A GitHub Actions workflow is the train. An agent is the car. And the part people miss: the car still drives the same roads, stops at the same red lights, parks in the same lot. The agent doesn't tear up the rails — it joins the system and plays by its rules.

The idea, in plain English

A workflow (a GitHub Actions YAML file, from lessons 0.6–0.7) is a fixed script. You write the steps in order — on: push → run tests → build → deploy — and it runs those exact steps, in that exact order, every time it's triggered. You decided the steps in advance. The workflow just obeys.

An agent is given a goal, not a script. "Fix the failing test." It then decides the next step itself: read the error, find the file, try a change, run the tests, look at the result — and if it still fails, try something different. That deciding-and-looping is the Plan → Act → Evaluate loop (the repeating cycle: decide a step → do it → check the result → repeat — full lesson in 1.4). The steps aren't written ahead of time; the agent picks them as it goes.

Definition

A workflow runs pre-written steps in a fixed order — you decide the path in advance. An agent interprets a goal and decides the next step at run time, adapting to what it finds.

Side by side

Workflow (YAML)Agent
Who picks the steps?You, in advanceThe agent, at run time
Same every run?Yes — deterministic (same input always gives the same output — predictable)No — adapts to what it finds
Handles surprises?No — fails or skipsYes — re-plans
Best when…the steps are known + fixedthe path depends on what's found
They're not enemies

The agent uses workflows. When it finishes a change it opens a pull request, which triggers your CI workflow (tests, scans). The agent rides the rails you already built. GH-600 line to memorize: an agent joins the workflow as a contributor — it does not replace it.

When to use which (this is the decision the exam tests)

Don't reach for an agent just because you can. Use the green-light / red-light test:

🟢 Green light — an agent fits when:

🔴 Red light — use a plain workflow or a human instead when:

One-look contrast

"Deploy on every push to main" → a workflow (fixed, repeatable, no judgment). "The deploy keeps failing intermittently — figure out why and fix it" → an agent (the path depends on what it finds). Fixed + known → workflow. Open-ended + investigative → agent.

The cert-language version

Agentic systems interpret goals, propose solutions, and take action — beyond simple automation. They operate a Plan → Act → Evaluate loop rather than a single fixed pass, and they join the GitHub workflow as a contributor (branches, PRs, checks) rather than replacing it. Each agent should be bound to a specific SDLC (Software Development Life Cycle — the whole path from idea to coding to testing to shipped software) stage with a defined, bounded scope.

Our summary · grounded in MS Learn — Foundations of Agentic AI (units 2–3) + Designing Agent Architecture & SDLC Integration (units 1–2, 9) · fetched 2026-05-31

Common confusions (read these or get them wrong on the exam)

Ticks this lesson done on the home roadmap. Saved in this browser.

Quiz · Lock it in

0 / 0 answered
Q1 · multiple choice

What is the single clearest difference between a workflow and an agent?

Answer · B. The defining question is who decides the next step. A workflow follows a fixed script you wrote in advance (the train on rails). An agent interprets a goal and chooses each step as it goes (the car with a driver). Model size, where it runs, and language are not the test.
Q2 · multiple choice

Per GH-600, how does an agent relate to your existing GitHub Actions workflows?

Answer · C. "Agents don't bypass or replace the GitHub workflow — they join it as another contributor, just like a human developer." The agent opens a PR; your existing checks and scans run on it. It rides the rails, it doesn't tear them up.
Q3 · multiple choice

Which task is the best red-light case — i.e. you should NOT simply hand it to an autonomous agent?

Answer · D. D hits multiple red-light conditions at once: irreversible/production-sensitive, broad secret access, and the agent approving its own work. A, B, and C are green-light: clear inputs/outputs, scoped, reviewable, testable.
Q4 · explain back

A teammate says: "I set up automation that runs the same five steps on every push — so now we have an agent." Explain, in your own words, whether that's an agent, and give one green-light and one red-light example for when an agent is the right tool.

Suggested answer

That's a workflow, not an agent — the five steps were fixed in advance and run the same every time (a train on rails). An agent interprets a goal and decides the steps at run time. Green light for an agent: a clear, scoped, reviewable, testable task like "add tests for this file." Red light: an irreversible, production-sensitive task needing broad secrets or self-approval, like "deploy to prod and merge your own change" — that belongs to a workflow or a human.


  
Source · MS Learn — Foundations of Agentic AI + Designing Agent Architecture & SDLC Integration · fetched 2026-05-31

Unofficial study material. Not affiliated with, endorsed by, or sponsored by GitHub or Microsoft. “GH-600” and “GitHub” are trademarks of their respective owners, used for identification only.