Pipeline

Deep Research

Multi-agent investigation with citations, contradiction checks, and iteration until convergence.

Quick reference

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

Type
Pipeline
Slash command
/deepresearch
CLI
bohr deepresearch

At a glance

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

  • Runs multiple gathering agents in parallel, then scores and challenges evidence before writing.
  • Loops through review and iteration gates until convergence—suited to citation-heavy deliverables.
  • Best when you need traceable sources and contradictions surfaced, not a one-shot summary.

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 /deepresearch followed by your topic or instructions. From a terminal, invoke the CLI as bohr deepresearch. 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

Deep research is Bohr’s flagship workflow: it fans out gathering, scores evidence, runs adversarial checks, writes a synthesis, and loops until quality gates pass.

When to use it

Choose deep research when you need a source-heavy brief with traceable citations and resolved contradictions—not a quick summary.

What you get

A durable artifact (often Markdown or structured brief) with inline citations, explicit gaps, and iteration notes from iteration-controller.

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