snowplow · mscwilson · Jul 15, 2025 · Jul 15, 2025 · Jul 15, 2025 · Jul 16, 2025
diff --git a/docs/signals/configuration/attributes/index.md b/docs/signals/configuration/attributes/index.md
@@ -174,6 +174,7 @@ This example extends the previous minimal example. Now the attribute is only cal
 
 ```python
 from snowplow_signals import Attribute, Event, Criteria, Criterion
+from datetime import timedelta
 
 my_attribute = Attribute(
     name="emoji_button_click_counter",

diff --git a/tutorials/signals-end-to-end/define-prospect-attributes.md b/tutorials/signals-end-to-end/define-prospect-attributes.md
diff --git a/tutorials/signals-end-to-end/intro.md b/tutorials/signals-end-to-end/intro.md
diff --git a/tutorials/signals-end-to-end/meta.json b/tutorials/signals-end-to-end/meta.json
diff --git a/tutorials/signals-end-to-end/prerequisites-and-setup.md b/tutorials/signals-end-to-end/prerequisites-and-setup.md
diff --git a/tutorials/signals-end-to-end/train-ml-prospect-scoring.md b/tutorials/signals-end-to-end/train-ml-prospect-scoring.md
diff --git a/tutorials/signals-ml-prospect-scoring/conclusion.md b/tutorials/signals-ml-prospect-scoring/conclusion.md
@@ -0,0 +1,48 @@
+---
+position: 10
+title: Conclusion
+---
+
+TODO
+
+![](./screenshots/console_output.png)
+
+## Final Notes and Next Steps
+
+This tutorial walked you through the process of building a prospect scoring system using Snowplow Signals together with a machine learning model.
+It is a starting point in exploring and using Signals APIs for your own needs.
+
+Suggested **next steps**:
+
+- **Define More Signals Attributes:** Define more Signals attributes custom-tailored for your use cases and events.
+- **Integrate Attributes into your Flows:** Integrate Signals APIs into your backend workflows to act on the users attributes.
+- **Explore More Signals Use Cases and Docs:** Explore Signals Documentation to get more ideas on how to integrate Signals capabilities into your use cases.
+
+
+
+### End Result
+
+At the end of the tutorial, you will:
+
+* see live prospect attribute updates in the browser console,
+* score them using an ML model,
+* and use the outputs to drive decisions on the website.
+
+![](./screenshots/console_output.png)
+
+<!--
+In this tutorial you've learned how to use Signals to calculate and serve information about user behavior in near real time.
+
+This is the process workflow:
+* Define attributes
+* Test definitions
+* Apply attribute configurations to Signals
+* Retrieve calculated attribute values from the Profiles Store
+
+## Next steps
+
+Here are some ideas for further exploration:
+* Try out other entities, e.g. `domain_userid`, to calculate the attributes against
+* Define attributes based off other event types
+* Retrieve calculated attributes in your real applications
+* Explore our other Signals tutorials -->