AI4RA Tip of the Week #2
One of the most difficult parts of incorporating AI into your daily workflow happens before you ever touch a computer: identifying the processes to be automated.
-
-
AI4RA General Office Hours
Have questions about Vandalizer, research data, or AI? Come join us for monthly office hours!
When: Fourth Tuesday of every month at 11:00am PDT
Where: Zoom -
From Prompt Engineering to Context Engineering
The blog post explains the shift from prompt engineering, carefully wording individual requests to get better AI responses, to context engineering, which focuses on designing the entire information environment an AI uses to produce results.
-
AI4RA Tip of the Week #1
What is Vandalizer, how do I get access, and how do I get support?
-
The Research Is Not The Manuscript
by Michael Overton, PhD Original post
-
When Can AI Be Used in Research Administration?
When Can AI Be Used in Research Administration? It Comes Down to One Question: Does It Matter How the Work Got Done? By Nate Layman AI tools are remarkably capable, and they are getting better fast. They can digest hundreds of pages of sponsor guidelines in seconds, draft polished narrative text from rough notes, and…
-
From Copiers to AI: The Technology Evolution of Research Administration and Why Adoption Matters
Research administration has always been a profession defined by reaction. New regulations arrive and we react.
-
Digitizing the Last Mile: OCR in Research Administration
University research departments receive billions of dollars in federal grants each year, but managing those grants is surprisingly old-fashioned. When a university gets a grant award, the official notice arrives as a PDF, and staff have to manually copy all the important details
-
Beyond Embeddings: Why Relationships Matter in RAG
Structured RAG, presented by Python creator Guido van Rossum at PyBay 2025, addresses a fundamental limitation of classic RAG: the loss of relationships between information fragments. Instead of embedding raw text into vectors, structured RAG extracts entities, relationships, and actions from conversations and stores them in queryable databases with inverted indices.
-
From Clutter to Clarity: How to Build Your First Automated Workflow in Vandalizer
In this guide, you’ll learn how to build your first workflow by following a real-world example — creating a Request for Applications (RFA) checklist from start to finish.
