Grounding Agents with Markdown Wikis: An Agentic Workflow for Economists
aniketapanjwani · x · 2026-08-13
The author shares how economists can leverage agentic knowledge wikis (collections of Markdown text files in tools like Obsidian or VS Code) to enhance research.
- Core Concept: While AI agents may lack inherent research taste, feeding them a wiki accumulated with daily research fragments (meeting notes, ideas, literature notes) provides rich grounding. This allows tools like Claude Code to effectively connect the dots and generate usable ideas and first drafts.
- Case Study: Sharing his experience at Harvard's Opportunity Insights lab, the author wrote a lightweight Skill for Codex to clean up voice-to-text streams and archive them. Once enough raw material was collected, he used AI to outline clear strategic recommendations and identify gaps he had missed.
This workflow demonstrates how structuring personal data can maximize the value of AI coding assistants for knowledge production beyond pure coding.
More from coding & agent
- Building 3D Action Games with Claude: 'Dark Souls' in 7 Hours — vrdrift · 2026-08-14
- DeepSeek V4 Flash Makes AI Agents Affordable for Everyone — Teknium · 2026-08-14
- Workflow for Building iOS Apps Entirely via Claude Mobile — EricBuess · 2026-08-14
- DeepSeek Ships V4 Pro, Open-Sources Agent Software, Raises API Prices — The Decoder · 2026-08-14
- Are Agent Harnesses the Boring Way to Continual Learning? — scaling01 · 2026-08-14
- Open Source Slack Agent Engine with MCP Support — xwil · 2026-08-14