Supercharging research with LLMs and agents. Talk + Q&A.
You build a working second brain on your laptop. Agent compiles a wiki from 3–5 of your own papers, then answers a cross-paper question.
By the end you leave with a vault that is ready to keep growing after the workshop.
The agent is better than you at reading every paper in the folder every time. You stay in the loop by reading, critiquing, and asking questions.
You drop PDFs, clipped articles, images into raw/. You never edit raw/.
Agent writes wiki/: per-paper summaries, concept articles grouping themes, backlinks, an INDEX.
Agent reads wiki and raw together, answers cross-cutting questions, files the answer back for next time.
Karpathy's vault: ~100 articles, ~400K words. Works without fancy RAG at that scale.
Rule: you own raw/, the agent owns wiki/. You rarely touch wiki/ directly.
raw/, writes wiki/, runs scripts, answers questions.Both Obsidian and opencode point at the same folder. Edit in one, see it in the other.
| Phase | What | Outcome |
|---|---|---|
| 01 · 5 min | Kickoff | Grab the OpenRouter key from Slack. Hear the stack overview. |
| 02 · 20 min | Install | Obsidian + opencode installed. Key pasted. Empty vault open in both. |
| 03 · 10 min | Ingest | 3–5 of your own PDFs in raw/. Optional web clip. |
| 04 · 25 min | Compile | Agent writes wiki/: summaries, concept articles, INDEX, backlinks. |
| 05 · 20 min | Q&A | One cross-paper question answered as markdown or Marp slides. |
| 06 · 10 min | Share | Post one surprising connection to Slack. |
Posted as a pinned message in #agentic-ai-for-neuroscience-workshop. Copy it now so you can paste in the install phase.
Scan the Workshop Slack QR on the landing page: neurogenomics.github.io/agentic-life-sciences-tutorial/workshops/agentic-ai-neuroscience-22-april-2026
Key rotates after the session. Don't commit it to git.
obsidian.md, install, skip the sign-in.opencode.ai. See the Get OpenCode tutorial on the site for screenshots.~/Documents/second-brain/raw/second-brain/.Get unstuck in Slack · #agentic-ai-for-neuroscience-workshop
2024-karpathy-llm-kb.pdf beats s41588-024-01919-z.pdf.raw/.If you have nothing to hand, use 3 papers from Will's talk. If you're stuck, ask a neighbour.
Read AGENT.md. Then:
1. Scan raw/ and list every source you find.
2. For each source, write wiki/papers/<filename>.md with:
- frontmatter (title, authors, year, tags, source: raw/<filename>)
- a 5-sentence summary
- 3-5 key findings as bullets
- a "Connections" section with [[wiki-links]]
3. Identify 3-5 themes connecting multiple papers. Write one
wiki/concepts/<theme>.md per theme, linking back to papers/.
4. Write wiki/INDEX.md listing everything, grouped by tag.
Ask before running if anything is unclear. Otherwise, go.
Full prompt + AGENT.md template are on the tutorial page.
You see the agent reading PDFs, drafting summaries, proposing concept clusters. Read along — you'll learn what it noticed.
Files appear live. Click any [[wiki-link]] to jump between papers and concepts. Open the graph view.
If it's slow, tell the agent to do 2 papers now and the rest in a second pass. Iterative is fine.
"Which papers share upstream methods or datasets? Where do they disagree?"
"What are the 3 most-repeated limitations across my review articles?"
"If I was writing an introduction to this topic, what 5 references would I cite and why?"
Ask the agent to render the answer as wiki/questions/<slug>.md with supporting quotes and backlinks. Open it in Obsidian. Verify the evidence against the original papers.
The agent reads every paper in the folder every time. You'd skim. It doesn't.
Frontmatter, backlinks, INDEX. Boring but compounding.
Add a paper, re-run the prompt. Concept articles update themselves.
At this scale, no fancy RAG needed. The agent auto-maintains INDEX + brief summaries and reads related docs as it works.
Agent audits your wiki — missing frontmatter, thin concepts, orphan notes.
Chat with Claude directly inside Obsidian alongside opencode.
Agent writes a script to plot citation timeline from YAML frontmatter.
Turn your Q&A answer into a slide deck you could present.
Vibe-code a TF-IDF CLI the agent can use as a tool.
Script add-paper.sh so new PDFs trigger a compile pass.
Full details: tutorials/10-second-brain-stretch on the workshop site.
Post one connection the agent found that you didn't expect to the workshop Slack:
The "why did you group these?" reveal is often the best part.
raw/ → ask the agent to update the wiki.wiki/questions/.Over weeks, the wiki becomes specific to your research. Every question you answer adds to the next answer's context.
neurogenomics.github.io/agentic-life-sciences-tutorial/workshops/agentic-ai-neuroscience-22-april-2026
tutorials/09-second-brain — full walkthrough with prompts.
tutorials/10-second-brain-stretch — linting, Marp, matplotlib, search.