PaperQA2 is a useful reminder for scientific RAG: leave an evidence trail
A SciencesLoop technical note on PaperQA2, citation precision, and reviewable scientific RAG artifacts.
SciencesLoop Writing
Working notes on AI agents, scientific workflow automation, RAG, evaluation, and the bridge between battery-materials research and applied AI systems.
ChemGraph is a better first test for scientific agents
A SciencesLoop note on ChemGraph, computational chemistry agents, and why traceable workflows matter more than fluent chat.
Agentic Scientific Workflows: From Search to Traceable Decisions
A working model for scientific agents that retrieve evidence, plan the next step, preserve uncertainty, and leave a decision trail.
A Public-Safe Site Agent as a Portfolio Interface
Why a personal technical site can be more useful when the homepage becomes a small, cited, public-safe agent.
Scientific RAG Needs Evaluation Before Confidence
RAG systems for technical work should be judged by retrieval quality, citation faithfulness, and decision usefulness, not only fluent answers.
Publishing workflow
Automated drafting path
New posts are Markdown files under src/blog.
Use the scaffold script to create a dated draft, then publish by
committing the generated Markdown.
npm run new:post -- --title "My AI agent note"