A few ways Claude actually fits into research
Concrete ways an AI agent like Claude fits into a research workflow today: auditable literature work, pipelines with built-in human stop-gates, and where agents still fall short.
6 min read
Loading
Blog
Notes on building with AI: agents, prompting, vibe coding, and what the research actually says.
Posts from June 2026Show all posts
Concrete ways an AI agent like Claude fits into a research workflow today: auditable literature work, pipelines with built-in human stop-gates, and where agents still fall short.
Vibe research means you set the direction and AI agents do the execution, while the judgement and accountability stay yours. What it is, why I'm optimistic, and the failure mode to watch for.
Modern AI looks like it arrived in November 2022. It's really the tail end of a ninety-year chain of ideas, almost none of them built by people aiming at anything like it. A walk from Turing to ChatGPT.
Everyone says there aren't enough AI-skilled people. Our Delphi study with Finnish experts suggests the shortage isn't really about headcount, and sketches four ways the next fifteen years could go.
We reviewed 36 studies on how universities and companies work together. What held the good partnerships together came down to six things, all starting with C.
Instructing AI has moved from wording a prompt, to curating context, to engineering the loop the agent runs in. Some of these are real terms; some are barely a year old.