oracle-devrel · AlexanderHodicke · Aug 21, 2026 · Aug 21, 2026
diff --git a/ai/data-science/oracle-ai-agent-memory/concepts_and_ api_walkthrough/README.md b/ai/data-science/oracle-ai-agent-memory/concepts_and_ api_walkthrough/README.md
@@ -2,6 +2,10 @@
 
 This notebook demonstrates how to use **Oracle Agent Memory** for managing and retrieving conversational memory in AI applications.
 
+Reviewed: 2026.08.13
+
+# When to use this asset?
+
 The notebook includes:
 
 * An overview of how memory is structured and managed within Oracle Agent Memory
@@ -10,13 +14,9 @@ The notebook includes:
 
 This notebook does not cover agent creation. Instead, it focuses on using Large Language Models (LLMs) to explore and demonstrate Oracle Agent Memory capabilities and API usage.
 
-Reviewed: 2026.08.13
-
-# Environment
 
-Conda environment: python3 (ipykernel)
+# How to use this asset?
 
-# Prerequisites
 * Access to an Oracle Database 26ai instance with Oracle Agent Memory enabled
 * Installation of the oracleagentmemory Python package
 * Access to at least one LLM model and one embedding model from the supported model list: https://docs.oracle.com/en/database/oracle/agent-memory/26.4/agmea/get-started.html#GUID-1DC2BEC9-4CAF-4668-BBBB-E9FC57C7E71E

diff --git a/ai/data-science/oracle-data-science/anomaly-detection/README.md b/ai/data-science/oracle-data-science/anomaly-detection/README.md
@@ -11,9 +11,8 @@ The repository currently includes:
 
 Reviewed: 2026.08.13
 
----
 
-# Projects
+# When to use this asset?
 
 ## Fraud Classification
 
@@ -26,7 +25,6 @@ The project also demonstrates production-oriented concepts such as:
 
 The deployed model can support both real-time and batch fraud monitoring workflows. The batch implementation is also covered in this project, the real time use case requires streaming tool, and not covered here.
 
----
 
 ## Sales Unlabeled Anomaly Detection
 
@@ -35,23 +33,20 @@ This project demonstrates anomaly detection for a continuous unlabeled target va
 The workflow includes exploratory analysis, time-series modeling and validation, anomaly detection using prediction intervals, custom model deployment, and production monitoring workflows integrated with OCI Monitoring.
 
 
----
 
-# Environment
+# How to use this asset?
+## Environment
 
 Conda environment: `generalml_p311_cpu_x86_64_v1`
 
-Created: 2026
 
----
-
-# Prerequisites
+## Prerequisites
 
 * Access to OCI Data Science
 * Required IAM permissions
 * Familiarity with Python and machine learning workflows
 
----
+
 
 # License
 

diff --git a/...cience/oracle-data-science/customizing-ads-model-deployment-artifacts/README.md b/...cience/oracle-data-science/customizing-ads-model-deployment-artifacts/README.md
@@ -16,12 +16,13 @@ Specifically, the notebook covers:
 3. Customizing the generated artifact to include feature engineering in score.py
 4. Registering, deploying, and invoking the model
 
-# Environment
+# How to use this asset?
+## Environment
 
 Conda environment: generalml_p311_cpu_x86_64_v1
 Created: April 2026
 
-# Prerequisites
+## Prerequisites
 - Access to OCI Data Science
 - Required IAM permissions for model registration and deployment
 - Basic familiarity with Python, Pandas, and Scikit-learn

diff --git a/ai/data-science/oracle-data-science/jobs-pipelines/README.md b/ai/data-science/oracle-data-science/jobs-pipelines/README.md
@@ -1,22 +1,26 @@
 # Jobs & Pipelines
 
-This package provides examples for creating and managing OCI Data Science Jobs and Pipelines using the ADS SDK. It includes three use cases:
+This package provides examples for creating and managing OCI Data Science Jobs and Pipelines using the ADS SDK. 
 
+Reviewed: 2026.08.13
+
+# When to use this asset?
+It includes three use cases:
 1. Basic Job Creation – simple job using a single script
 2. Advanced Job – job using a source folder, custom variables, and flexible configuration
 3. Pipeline Creation – multi-step workflows using jobs as pipeline steps
 
-Reviewed: 2026.08.13
 
-# Prerequisites
+# How to use this asset?
+## Prerequisites
 
 To use this package, you need:
 
 - Basic Python knowledge
 - Access to the OCI Data Science Platform with appropriate Resource Principal permissions and IAM policies
 - An OCI Object Storage bucket
 
-# Environment
+## Environment
 
 Run the examples in a Jupyter Notebook inside an OCI Data Science Notebook Session using: generaml_p311_cpu_x86_64_v1
 

diff --git a/...science/oracle-data-science/model-catalog-fundamentals-and-automation/README.md b/...science/oracle-data-science/model-catalog-fundamentals-and-automation/README.md
@@ -8,39 +8,33 @@ It contains two examples with increasing levels of sophistication:
 
 Reviewed: 2026.08.13
 
-# Project Scope
+# When to use this asset?
 
 This project covers the following topics:
 
-1. Model Catalog Fundamentals
-
-* Essential Model Catalog operations, including:
+Model Catalog Fundamentals
 1. Model serialization
 2. Model registration in the Model Catalog
 3. Loading a registered model and using it for inference
 4. Retrieving model metadata from the catalog (using multiple approaches)
 5. Updating a registered model’s metadata (using multiple approaches)
 
-* The implementation heavily relies on the ADS SDK.
-* Note: Model deployment is out of scope for this notebook.
-
-2. Automated Model Registration
-
-* Automating the model registration process using OCI Data Science Jobs and model version sets, including:
+Automated Model Registration
 1. Defining a model version set
 2. Adding multiple model versions to a version set via job runs
 3. Implementing a retention mechanism for archiving older model versions
 4. Use of Object stroage in the JupyterLab and Jobs 
-* This example also heavily relies on the ADS SDK.
 
-# Prerequisites
+
+# How to use this asset?
+## Prerequisites
 * Access to the OCI Data Science Platform
 * Basic familiarity with Python and machine learning concepts
 * An OCI compartment with:
 1. Resource principal configured
 2. Appropriate IAM policies for OCI Data Science, Object Storage, and Model Catalog
 
-# How to Use
+## How to Use
 1. Open the notebooks in an OCI Data Science Notebook Session.
 2. Select the following conda environment: generalml_p311_cpu_x86_64_v1
 3. Run the notebook cells sequentially to reproduce each workflow:

diff --git a/ai/data-science/oracle-data-science/operational-research/README.md b/ai/data-science/oracle-data-science/operational-research/README.md
@@ -8,7 +8,7 @@ This project presents three operational research use cases with different levels
 
 Reviewed: 2026.08.13
 
-# What You’ll Learn
+# When to use this asset?
 
 This project covers the following topics:
 
@@ -22,18 +22,19 @@ This project covers the following topics:
    - Endpoint invocation for predictions
    - Data Science Jobs
 
-# Prerequisites
-
-- Access to the OCI Data Science Platform
-- Basic familiarity with Python and machine learning concepts
-- A valid OCI compartment, resource principal, and policies configured for Data Science services
 
 # How to Use this asset?
 
 1. Open the provided notebook in your OCI Data Science Notebook Session.
 2. Select the following conda environment: generalml_p311_cpu_x86_64_v1
 3. Run the notebook cells in sequence to reproduce the complete workflow.
 
+## Prerequisites
+
+- Access to the OCI Data Science Platform
+- Basic familiarity with Python and machine learning concepts
+- A valid OCI compartment, resource principal, and policies configured for Data Science services
+
 # License
 
 Copyright (c) 2026 Oracle and/or its affiliates.

diff --git a/...-science/oracle-data-science/registration-and-deployment-with-oci-sdk/README.md b/...-science/oracle-data-science/registration-and-deployment-with-oci-sdk/README.md
@@ -1,18 +1,22 @@
 # Registration and Deployment with OCI SDK
 
 This project demonstrates how to register and deploy a machine learning model using the OCI SDK, while using the ADS SDK to create the model artifact.
-Although ADS simplifies model registration and deployment, it can be limiting for advanced scenarios. In this notebook, we use the OCI SDK to:
+Although ADS simplifies model registration and deployment, it can be limiting for advanced scenarios.
+
+Reviewed: 2026.08.13
+
+# When to use this asset?
+In this notebook, we use the OCI SDK to:
 - Register a model in a different compartment than the Notebook Session
 - Deploy the model to that target compartment
 - Move an existing model deployment between compartments
 
-Reviewed: 2026.08.13
-
-# Environment
+# How to use this asset?
+## Environment
 Conda environment: automlx251_p311_cpu_x86_64_v2
 
 
-# Prerequisites
+## Prerequisites
 - Access to OCI Data Science
 - Required IAM permissions for model registration and deployment
 - Basic familiarity with Python and OCI SDK

diff --git a/ai/data-science/oracle-data-science/your-first-data-science-project/README.md b/ai/data-science/oracle-data-science/your-first-data-science-project/README.md
@@ -6,37 +6,28 @@ The project walks through the main stages of a typical machine learning lifecycl
 
 Reviewed: 2026.08.13
 
-# What You’ll Learn
+# When to use this asset?
 
-This project covers the following steps:
+1. This project covers the following steps:
+2. Data ingestion
+3. Data preprocessing and visualization
+4. Model training and validation
+5. Model explainability
+6. Model deployment
+7. Endpoint invocation for predictions
 
-Data ingestion
+# How to use this asset?
+## Prerequisites
 
-Data preprocessing and visualization
+* Access to OCI Data Science Platform
+* Basic familiarity with Python and machine learning concepts
+* A valid compartment, resource principal and policies configured for Data Science services. More details can be found in the Guide for Your First Data Science Project prerequisites.pdf
 
-Model training and validation
+## How to Use
 
-Model explainability
-
-Model deployment
-
-Endpoint invocation for predictions
-
-# Prerequisites
-
-Access to OCI Data Science Platform
-
-Basic familiarity with Python and machine learning concepts
-
-A valid compartment, resource principal and policies configured for Data Science services. More details can be found in the Guide for Your First Data Science Project prerequisites.pdf
-
-# How to Use
-
-Open the provided notebook in your OCI Data Science Notebook Session.
-
-Select the following conda environment: automlx234_p310_cpu_x86_64_v1
-
-Run the notebook cells in sequence to reproduce the complete workflow.
+* Open the provided notebook in your OCI Data Science Notebook Session.
+* Select the following conda environment: automlx234_p310_cpu_x86_64_v1
+* Run the notebook cells in sequence to reproduce the complete workflow.
 
 # License
 

diff --git a/ai/data-science/oracle-vector-search/python-rag-wikipedia-search/README.md b/ai/data-science/oracle-vector-search/python-rag-wikipedia-search/README.md
@@ -12,7 +12,8 @@ Use this asset as support material when wanting to showcase Oracle AI Vector Sea
 3. Running hybrid search (keyword + vector similarity)
 4. Applying rerankers to improve retrieved context
 
-# Prerequisites
+# How to use this asset?
+## Prerequisites
 
 To use this package, you need:
 - Basic Python knowledge
@@ -21,7 +22,7 @@ To use this package, you need:
 - Required IAM permissions for Data Science and Database access
 - A configured database wallet or secure connection details
 
-# Environment
+## Environment
 
 Run the examples in a Jupyter Notebook inside an OCI Data Science Notebook Session.
 

diff --git a/ai/data-science/oracle-vector-search/sql-your-first-vector-project/README.md b/ai/data-science/oracle-vector-search/sql-your-first-vector-project/README.md
@@ -12,8 +12,6 @@ Use the scripts to learn basics about AI Vector Search.
 
 Please use the posting [Getting started with vectors in 26ai](https://blogs.oracle.com/coretec/post/getting-started-with-vectors-in-23ai) for information about the scripts.
 
-# Useful Links
-
 ## Documentation
 
 - [Oracle AI Vector Search User's Guide](https://docs.oracle.com/en/database/oracle/oracle-database/23/vecse/overview-ai-vector-search.html)