The most efficient way to deep dive into a codebase is to start from its dependencies graph. This latter contains insights that allow within a few clicks and filters to know a lot about the applications without reading the code or any documentation (if exists) 🚀. The process is iterative and the findings are important both for the assessment (identify missing, obsolete code, duplications, complexity, common libraries and data, highly connected programs, etc. See more in Dependencies) and for the transformation as we need to get transformed the program within its dependencies (see details in Transformation Center). Computing and displaying the dependencies graph is one of the most used feature in AWS Blu Insights. The generated graphs contain different artefacts:
- Vertices ⚪: represented as circles with different colors based on their types. They can refer to
- Files: actual files in the codebase.
- Nodes: virtual objects like System Utilities, missing programs, database objects, etc.
- Edges 🔗: represented by links between the vertices and having different types based on the dependencies (e.g. Call, EXEC CICS, Copy...).
The graph may also display meta information like labels and workpackages. 
Users can customize all these artefacts by editing their types and colors. They can also hide and show nodes in their subgraphs. For expert users, it is even possible to download the results as a JSON file, rework it and upload it again. Reworking a JSON file can be done using an IDE, a text editor, or a program written in any programming language. Usually the goal is to add or remove some vertices and/or edges to get the graph that most fits the customer's needs or the project methodology (e.g. handling the data and code management in different steps). Many of our customers asked to inject more automation in the process and reduce the friction, i.e. do most of the rework directly in Blu Insights and in a simplified way. So we did it 🎉. You can now add, customize and remove edges and vertices within a few clicks.
Adding a node is as simple as specifying a name, a color, a type (existing or new) and a description.
A new link has a type (existing or new), a source node and a target node.
Try it and let us know. We have a long list of improvements we want to add to this feature. They will be available in the next versions. Stay tuned! 😊
The AWS Blu Insights team