← Back to work
In progressKnowledge

Second Brain

A personal knowledge base that holds what I read, then quizzes me on it.

What this shows: I can turn a growing pile of notes into a system that answers with sources and quizzes me on what matters. The same approach works on a company wiki or policy docs.

Outcome

Everything I read becomes searchable and gets quizzed back to me. Ask across the whole vault, get answers that cite the actual note.

Proof

Every answer cites the note it came from, and no relevant note means no answer. Kale Bot runs this same pipeline live and is scored on it; this vault is young and its counts are real.

Takeaway

Retrieval keeps answers honest: every reply is grounded in a real note, and what I flag gets quizzed back until it sticks.

Answer grounded across the vault

Knowledge graph · grounded across notesLIVE
illustrationSecond BrainPromptingForecastingSourcesRAGAgent workflowsMCP & SkillsClaude APIEvalswhat makes a forecast trustworthy?pulls from Evals + Forecastingbaselines firstcalibrationanswer, groundedcites: baselines first · calibrationhow does Kale Bot avoid guessing?pulls from MCP & Skills + RAGbot scopegroundinganswer, groundedcites: bot scope · groundinga question lights up the notes that answer it

Retrieval, step by step (RAG)

The vault is too big to read in one go, so a question never sees all of it, just the few notes that actually matter. That’s retrieval-augmented generation (RAG): embed everything once, pull the most relevant passages for each question, then answer only from those and cite them. Because the match is on meaning rather than exact words, a question about “forgetting curves” can surface a note that only ever said “spaced repetition”.

  1. 1Chunk & embed

    Each note is split into passages and embedded as vectors, so meaning is searchable, not just keywords

    embeddings
  2. 2Retrieve

    The question is embedded too; the closest passages are pulled, a handful, not the whole vault

    top-k
  3. 3Ground the answer

    Claude answers from only those passages, so it can't drift into notes it never retrieved

    grounded
  4. 4Cite the source

    Every claim links back to the note it came from, so I can check it

    citations

The trade-off is real: an embedding index to keep in sync, and a retrieval step that can miss the right note. Kale Bot runs this exact pipeline live on a small public vault (and is scored on it); Second Brain is where it has to scale, across a personal vault that grows every week.

How I learn a new topic

I write rough notes in Obsidian. A Claude coworker runs on a schedule: it tidies and links what I wrote, builds recall prompts, quizzes and grades me over time, and pushes hardest on the topics I keep missing. Reading turns into recall, spaced out so it sticks.

Spaced repetition · capture to recallLIVE
THE LOOP · RUNS ON A SCHEDULE1Capturenotes in Obsidian2Tidy & linkclean up, connect3Build promptsnotes → recall4Quiz & gradetest me, score it5Targetpush the misses↻ back to captureWHY IT STICKS · SPACED REPETITIONfull recallrecall1 day3 days1 week1 monthThe dots are reviews: recall snaps back to full each time, and the gaps keep widening.meClaude coworkerconcept, not data

At a glance

14
Notes in the vault
30
Links between notes
5
Topics in rotation
5
Fresh quiz questions a day

How it works

  1. 1

    Capture

    Notes, highlights, and ideas land in my Obsidian vault.

  2. 2

    Connect

    A scheduled Claude agent links each new note to what is already there.

  3. 3

    Retrieve

    I can ask questions across everything and get sourced answers.

  4. 4

    Quiz

    It quizzes me on what I flagged to remember, spaced over time.

Quiz mode

Reading turns into recall. The vault asks, I answer. A few real ones:

What is RAG, in one line?

Search first, write second: find the most relevant notes, then answer only from what was found.

Why stream answers token by token?

First words land in under a second instead of after a long pause. Same answer, no frozen screen.

What did I conclude about grounding?

Stricter retrieval beats a bigger model. Most of the hallucinations came from answering when nothing was relevant.

Brier score, in one line?

Mean squared error on probabilities. Lower is better, and it punishes confident misses.

spaced repetition

Problem

I read and think more than I can hold in my head. I wanted one place that remembers it all, connects it, and helps it actually stick.

Approach

Obsidian is the store, plain markdown I own. Claude Cowork, an AI agent that works over my files on a schedule, sits on top: it links new notes into the graph, answers questions with retrieval so every answer cites its notes, and runs the spaced quizzing loop. Same pipeline Kale Bot runs live (embed, retrieve, ground the answer), scaled to a vault that keeps growing.

Eval results

Real and early: 14 notes, 30 links, five topics in rotation. Each morning the agent writes five fresh quiz questions from the vault and grades my answers in the evening. Retrieval is already scored for real in Kale Bot, 95% hit-rate on a 48-prompt eval; this vault is where it has to scale.

What broke

Auto-linking first connected everything to everything. Tightening the similarity threshold made the graph readable again.

Want to know what's in the vault? Ask.

🥬Kale Bot

Ask me anything about Cael and his projects. I answer from real sources, and I will tell you if I do not know.