Pipeline

Autoresearch

Autonomous experiment loop: analyze, measure, hypothesize, test toward a goal.

Quick reference

Core invocation details and the exact command surfaces users will touch first.

Type
Pipeline
Slash command
/autoresearch
CLI
bohr autoresearch

At a glance

The shortest useful summary of what this workflow is for and what it produces.

  • Runs a goal-directed loop: analyze state, propose hypotheses, measure, repeat.
  • Fits exploratory problems where the next step should follow from data.
  • Stops when configured criteria are met; full trace is retained.

How to run

Start with the slash command in the REPL for interactive work, or call the CLI when you need a shell-native invocation.

In the Bohr research shell (REPL), enter /autoresearch followed by your topic or instructions. From a terminal, invoke the CLI as bohr autoresearch. Refer to the linked documentation for arguments, profiles, and environment setup.

Flow diagram

Stages and agent labels are indicative. Your configuration may swap or rename modules, but the diagram still shows the intended execution shape and handoff order.

Detailed guide

Full notes, usage guidance, and the longer explanation for how this workflow behaves in practice.

Overview

Runs repeated cycles of analysis → hypothesis → measurement until stop criteria hit—good for optimization-style research questions.

When to use it

Exploratory spaces where the next step should emerge from measurements.

Outputs

Iteration log plus final recommendation and metrics.

Practical notes

Exact agents, tools, and stop rules depend on your Bohr configuration. For CLI flags, examples, and edge cases, open the full documentation from the Documentation & links section on this page.

See also