Automating RWD workflows with AI: builder argues the community underestimates what's possible
Ubunta · x · 2026-11-09
The author shares hands-on experience automating significant parts of RWD (real-world data) workflows with AI, with experts reviewing the work, arguing the community underestimates what's possible today.
Key points:
- The opportunity is mostly engineering: connecting AI to existing data tools, making steps repeatable, checking consistency, and making outputs easy for experts to inspect.
- Part of the gap is vocabulary: what a clinician calls a phenotype, an engineer sees as data operations with clinical meaning attached.
- The division of labor — AI executes, experts review, challenge, and direct — frees experts to explore more questions and test more alternatives.
- The author is attending ISPOR in Vienna, inviting skeptics to bring specific workflows to either see a working demo or diagnose the obstacle.
More from coding & agent
- NVIDIA open-sources Auto Ontology to fix text-to-SQL's biggest problem — Roger_M_Taylor · 2026-11-09
- Getting Omarchy running on Snapdragon Surface Pro: custom kernel plus SSH tunnel for OpenClaw — vincent_koc · 2026-11-09
- Resurfacing in Obsidian: Random Notes, Review Queues and Related Notes — dSebastien · 2026-11-09
- One prompt edit made an agent burn $133 on 21 rogue calls — and the 3 gates that fixed it — Worth_Wealth_6811 · 2026-11-09
- Solo dev adds read-only MCP connector so Claude and ChatGPT can query your food diary — Content-Two5729 · 2026-11-09
- Suspected DPRK npm supply chain attack: archetype-index-sdk ships obfuscated loader with credential harvesting — cyb3rops · 2026-11-09