[docs-linker] workshop docs: add gh-aw doc links

workshop/23-ab-experiments.md

@@ -119,7 +119,7 @@ Write a report according to the output_style: ${{ experiments.output_style }}.
 1. Using your confirmed 1:1 counts for `concise` and `detailed`, predict the next three assignments.
 2. Run the workflow three times and compare your prediction with activation logs and `experiment` counts.
 
-## Understand how the round-robin works
+## Understand how the [round-robin](https://github.github.com/gh-aw/experimental/experiments/#statistical-balancing) works
 
 <picture>
    <source media="(prefers-color-scheme: dark)" srcset="images/23-ab-roundrobin-dark.svg">
@@ -135,7 +135,7 @@ On each run, gh-aw:
 1. Loads state from `experiments/{workflow-id}` (created on first run).
 2. Picks the variant with the lowest invocation count (ties are broken by first-in-array order).
 3. Saves the updated counts.
-4. Uploads the `experiment` artifact.
+4. Uploads the `experiment` [artifact](https://github.github.com/gh-aw/reference/artifacts/).
 5. Injects the selected variant into your template conditionals.
 
 </details>

workshop/24-self-hosted-runners.md

@@ -78,7 +78,7 @@ registration settings (Settings → Actions → Runners).
 > [!TIP]
 > Labels act as filters. A workflow job is dispatched to the first idle runner that satisfies all labels in the list. Adding `linux` alongside `self-hosted` ensures the job only lands on Linux runners when your fleet is mixed.
 
-Running in an enterprise environment? See [Side Quest: Self-Hosted Runner Infrastructure Deep Dive](side-quest-24-01-runner-infrastructure.md) for guidance on ephemeral and JIT runners, proxy configuration, and network isolation for air-gapped environments.
+Running in an enterprise environment? See [Side Quest: Self-Hosted Runner Infrastructure Deep Dive](side-quest-24-01-runner-infrastructure.md) for guidance on ephemeral and JIT runners, proxy configuration, and [network](https://github.github.com/gh-aw/reference/network/) isolation for air-gapped environments.
 
 ## :pencil2: Exercise: Compile and commit
 

workshop/25-audit-and-observability.md

@@ -6,7 +6,7 @@
 
 ## :dart: What You'll Do
 
-Use `gh aw logs` and `gh aw audit` to review the built-in [artifacts](https://github.github.com/gh-aw/reference/artifacts/) that every agentic workflow run produces, understand token usage, and debug unexpected behavior. By the end you know where to look when a run behaves unexpectedly or when a compliance review asks what the agent did.
+Use `gh aw logs` and `gh aw audit` to review the built-in [artifacts](https://github.github.com/gh-aw/reference/artifacts/) that every agentic workflow run produces, understand [token usage](https://github.github.com/gh-aw/reference/cost-management/#monitoring-costs-with-gh-aw-logs), and debug unexpected behavior. By the end you know where to look when a run behaves unexpectedly or when a compliance review asks what the agent did.
 
 ## :clipboard: Before You Start
 
@@ -73,7 +73,7 @@ suggest how to reduce it.
 <paste report here>
 ```
 
-The skill understands agentic workflow [frontmatter](https://github.github.com/gh-aw/reference/frontmatter/) and safe-output rules. It can suggest a more efficient prompt, validate your changes, or walk you through a fix — all without leaving the chat. Ask the agent to make edits directly so it can run `gh aw compile` to validate before committing.
+The skill understands agentic workflow [frontmatter](https://github.github.com/gh-aw/reference/frontmatter/) and [safe-output](https://github.github.com/gh-aw/reference/safe-outputs/) rules. It can suggest a more efficient prompt, validate your changes, or walk you through a fix — all without leaving the chat. Ask the agent to make edits directly so it can run `gh aw compile` to validate before committing.
 
 ### Browse artifacts in the GitHub UI
 

workshop/26-manage-costs-and-budgets.md

@@ -54,7 +54,7 @@ Look at the **AIC** column. Average the last five runs, then multiply:
 monthly cost = average AIC per run × runs per day × 30
 ```
 
-If your workflow averages 1.5 AIC and runs once a day: `1.5 × 1 × 30 = 45 AIC per month`. Share this estimate with your GitHub administrator before enabling a high-frequency schedule.
+If your workflow averages 1.5 AIC and runs once a day: `1.5 × 1 × 30 = 45 AIC per month`. Share this estimate with your GitHub administrator before enabling a high-frequency [schedule](https://github.github.com/gh-aw/reference/triggers/#scheduled-triggers-schedule).
 
 ### Project costs with [gh aw forecast](https://github.github.com/gh-aw/setup/cli/#forecast-experimental)
 

workshop/27-evaluate-workflow-quality.md

@@ -18,7 +18,7 @@
 
 ## :dart: What You'll Do
 
-You'll add an `evals:` block to your workflow, define binary quality questions, run the workflow, and verify that results are recorded in the `evals` artifact and persisted for historical comparison.
+You'll add an `evals:` block to your workflow, define binary quality questions, run the workflow, and verify that results are recorded in the [`evals` artifact](https://github.github.com/gh-aw/reference/artifacts/#evals) and persisted for historical comparison.
 
 ## :clipboard: Before You Start
 

workshop/side-quest-05-01-actions-power-user.md

@@ -66,7 +66,7 @@ Key differences at a glance:
 Think of agentic workflows as a superset of Actions:
 
 - Frontmatter remains compatible with the Actions model you already know.
-- The Markdown body becomes the runtime prompt and can include templating and inline agent features.
+- The Markdown body becomes the runtime prompt and can include [templating](https://github.github.com/gh-aw/reference/templating/) and inline agent features.
 - You can still keep deterministic logic when that is the right tool for the job.
 
 ## Hybrid pattern for real teams