BTW Studio
← All work

Several agents, one cited answer.

A command-line research pipeline over a notes vault: a planner splits the question, workers search in parallel, and a judge sends weak answers back.

Read the code

In plain words

Ask one question of a large pile of notes and a single pass will miss half of it. This tool splits the question into parts, researches each part separately, writes one answer with its sources, and then grades its own answer. A weak answer is sent back for another try.

How it works

  1. Ask a question

    In the command line, in plain language.

  2. Watch it work

    The plan, the parallel searches and the draft appear live.

  3. Get an answer with sources

    It is graded first; below the pass mark it is revised before you see it.

The problem

One model call over a large body of notes either misses half of it or answers with confidence it has not earned.

What we built

A planner breaks the question into sub-questions and a router decides how deep each one goes. Workers read the vault through a standard tool protocol in parallel, a synthesizer writes a structured answer with sources, and a judge scores it. Below the threshold, the answer is revised.

How we know it works

Evaluation set15 questions
Judged ongroundedness, relevance, completeness
Regression gatethe run fails below a set score
Built with
TypeScript, Claude, Model Context Protocol
Runs as
A command-line tool; a demo vault is bundled
Good fit for
Research over internal notes and documentation

Under the hood

  1. PlannerSplits the question into 2 to 5 parts
  2. RouterQuick, deep or impossible, per part
  3. WorkersSearch the notes in parallel through MCP
  4. SynthesizerOne structured answer with sources
  5. JudgeScores it; a low score sends it back

It runs from a clean clone with a bundled demo vault and a mock model, so no API key is needed to see the pipeline.

Decisions and why

A small model plans, a larger one writes

Planning and routing use the fast model; synthesis and judging use the stronger one.

"Impossible" is a valid route

A part the notes cannot answer is marked as such instead of being forced into an answer.

The notes are reached through a standard protocol

Workers use MCP tools, so the same pipeline can be pointed at another source.

A score gates the run

The evaluation set fails the run when the judged score drops below the threshold.