Skip to content
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
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
1 change: 1 addition & 0 deletions .github/workflows/daily-team-status.lock.yml

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

2 changes: 1 addition & 1 deletion .github/workflows/go-file-size-reduction.campaign.g.md

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

4 changes: 2 additions & 2 deletions docs/src/content/docs/index.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -44,6 +44,8 @@ import FeatureGrid from '../../components/FeatureGrid.astro';

## What are Agentic Workflows?

**Agentic means the AI can think and decide for itself.** Unlike traditional automation that follows exact steps you program, agentic workflows give the AI a goal and let it figure out how to achieve it—like asking a smart assistant to "organize my issues" instead of writing code for every possible scenario.

**Agentic workflows** are AI-powered automation that can understand context, make decisions, and take meaningful actions—all from natural language instructions you write in markdown.

Unlike traditional automation with fixed if-then rules, agentic workflows use AI agents (like GitHub Copilot) to:
Expand All @@ -61,8 +63,6 @@ clarification if important details are missing.

**To automated action**: The AI reads the issue, determines what's missing, and posts a helpful comment requesting specific information—adapting its response to each unique issue.

This is "agentic" because the AI acts as an intelligent agent with agency to make context-aware decisions, rather than just executing predefined steps.

<div style="max-width: 600px; margin: 3rem auto; text-align: center;">

> **Part of the Continuous AI Initiative**
Expand Down
22 changes: 20 additions & 2 deletions docs/src/content/docs/setup/quick-start.md
Original file line number Diff line number Diff line change
Expand Up @@ -213,6 +213,24 @@ Once complete, a new discussion post will be created in your repository with a d

Let's look at what you just added. The daily team status workflow automatically creates a status report every weekday and posts it as a discussion in your repository, and looks like this:

:::tip[YAML Basics for Beginners]
The configuration section uses **YAML syntax** (a human-friendly data format for configuration):
- `key: value` — Sets a configuration option
- `- item` — Creates a list item (note the dash and space)
- **Indentation matters** — Use 2 spaces for nested items (not tabs)
- Colons (`:`) separate keys from values
- Lists can be nested under keys

**Example:**
```yaml
tools: # Key with nested items below
github: # Nested key (indented 2 spaces)
- repos # List item (dash + 2 spaces)
```

Learn more: [YAML Tutorial](https://learnxinyminutes.com/docs/yaml/)
:::

```aw wrap
---
on:
Expand Down Expand Up @@ -248,11 +266,11 @@ This workflow triggers every weekday at 9 AM via cron schedule, has [permissions

**Understanding the structure:**

- **[Frontmatter](/gh-aw/reference/glossary/#frontmatter)** (between `---` markers): The configuration section with [YAML](/gh-aw/reference/glossary/#yaml) settings that control when the workflow runs (`on:`), what permissions it has (`permissions:`), what tools it can use (`tools:`), and what outputs it can create (`safe-outputs:`).
- **[Frontmatter](/gh-aw/reference/glossary/#frontmatter)** (between `---` markers): A section at the top of the markdown file that contains configuration in [YAML](/gh-aw/reference/glossary/#yaml) format. It's commonly used in static site generators and documentation tools. In agentic workflows, frontmatter controls when the workflow runs (`on:`), what permissions it has (`permissions:`), what tools it can use (`tools:`), and what outputs it can create (`safe-outputs:`).

- **Markdown body** (below frontmatter): Natural language instructions that tell the AI [agent](/gh-aw/reference/glossary/#agent) what tasks to perform. Written in plain English, not code.

- **[Safe outputs](/gh-aw/reference/glossary/#safe-outputs)**: Pre-approved actions (like creating discussions, issues, or comments) that the AI can request without needing write permissions during execution. The workflow processes these requests in separate, permission-controlled jobs for security.
- **[Safe outputs](/gh-aw/reference/glossary/#safe-outputs)**: Pre-approved actions (like creating discussions, issues, or comments) that the AI can request without needing write permissions during execution. This security feature prevents the AI from making unexpected changes—the workflow processes these requests in separate, permission-controlled jobs where humans can review what happened.

## Customize Your Workflow

Expand Down