diff --git a/workshop/18-share-and-reuse.md b/workshop/18-share-and-reuse.md
index 8fca2bd8..4e766f74 100644
--- a/workshop/18-share-and-reuse.md
+++ b/workshop/18-share-and-reuse.md
@@ -92,7 +92,7 @@ This hint saves teammates guesswork when they first open the file.
 - [ ] A teammate (or you in a second repo) has successfully imported the template with `gh aw add`
 
 <!-- journey: all -->
-**Next:** [What's Next? Keep Exploring](14-next-steps.md)
+**Next:** [Build a Research-Driven Next Training Node](19-research-driven-training-node.md)
 <!-- /journey -->
 
 
diff --git a/workshop/19-research-driven-training-node.md b/workshop/19-research-driven-training-node.md
index d9f2bb13..e76a99fc 100644
--- a/workshop/19-research-driven-training-node.md
+++ b/workshop/19-research-driven-training-node.md
@@ -82,7 +82,7 @@ gh aw compile --validate
 - [ ] You ran lint and compile validation before preparing a PR
 
 <!-- journey: all -->
-**Next:** [Learning GitHub Agentic Workflows](README.md)
+**Next:** [Make Your Workflow Remember Across Runs](20-persistent-memory.md)
 <!-- /journey -->
 
 
diff --git a/workshop/20-persistent-memory.md b/workshop/20-persistent-memory.md
index 1da8bea0..03bd12ee 100644
--- a/workshop/20-persistent-memory.md
+++ b/workshop/20-persistent-memory.md
@@ -148,7 +148,7 @@ git push
 - [ ] After opening a new issue and running again, only the new issue is reported
 
 <!-- journey: all -->
-**Next:** [Learning GitHub Agentic Workflows](README.md)
+**Next:** [Split Complex Workflows with Inline Sub-Agents](21-inline-sub-agents.md)
 <!-- /journey -->
 
 
diff --git a/workshop/21-inline-sub-agents.md b/workshop/21-inline-sub-agents.md
index 6ccaa32d..ab6ad720 100644
--- a/workshop/21-inline-sub-agents.md
+++ b/workshop/21-inline-sub-agents.md
@@ -117,7 +117,7 @@ Trigger a manual run. In the Actions log, confirm the parent agent calls your su
 - [ ] The final workflow output used the sub-agent result
 
 <!-- journey: all -->
-**Next:** [Learning GitHub Agentic Workflows](README.md)
+**Next:** [Make Your Workflows Resilient to Failure](22-error-handling-and-resilience.md)
 <!-- /journey -->
 
 
diff --git a/workshop/22-error-handling-and-resilience.md b/workshop/22-error-handling-and-resilience.md
index 0979c98c..f2c28403 100644
--- a/workshop/22-error-handling-and-resilience.md
+++ b/workshop/22-error-handling-and-resilience.md
@@ -119,7 +119,7 @@ After pushing:
 - [ ] You can name at least two common agentic workflow failure modes and how to mitigate them
 
 <!-- journey: all -->
-**Next:** [What's Next? Keep Exploring](14-next-steps.md)
+**Next:** [Test Your Prompt Ideas with A/B Experiments](23-ab-experiments.md)
 <!-- /journey -->
 
 
diff --git a/workshop/23-ab-experiments.md b/workshop/23-ab-experiments.md
index 31451a0c..9dea4154 100644
--- a/workshop/23-ab-experiments.md
+++ b/workshop/23-ab-experiments.md
@@ -149,7 +149,7 @@ After enough runs (10+ per variant reduces variation), compare usefulness and to
 - [ ] You can explain what you would do once a winning variant is identified
 
 <!-- journey: all -->
-**Next:** [Learning GitHub Agentic Workflows](README.md)
+**Next:** [Run Your Agentic Workflow on a Self-Hosted Runner](24-self-hosted-runners.md)
 <!-- /journey -->
 
 
diff --git a/workshop/24-self-hosted-runners.md b/workshop/24-self-hosted-runners.md
index d72a5b5c..d43315d2 100644
--- a/workshop/24-self-hosted-runners.md
+++ b/workshop/24-self-hosted-runners.md
@@ -174,7 +174,7 @@ Commit the updated lock file before triggering your next workflow run.
 - [ ] No workflow steps failed due to runner availability or label mismatch
 
 <!-- journey: all -->
-**Next:** [What's Next? Keep Exploring](14-next-steps.md)
+**Next:** [Audit and Monitor Your Agentic Workflows](25-audit-and-observability.md)
 <!-- /journey -->