Pipeline

Visuals

Generate data-backed charts, source-linked tables, and conceptual image assets.

Quick reference

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

Type
Pipeline
Slash command
/visuals
CLI
bohr visuals

At a glance

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

  • Creates a report plus an asset folder with chart, table, JSON, CSV, and image outputs.
  • Keeps market analysis and numeric comparisons data-backed before any chart is rendered.
  • Uses image models only for conceptual visuals such as flowcharts, material boards, and presentation imagery.
  • Records every asset in a manifest with source data, provider/model, prompt, and verification state.

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

Visuals turns research or market-analysis data into a visible package: source data, charts, tables, optional generated images, a report, and a manifest.

When to use it

Use it when you need client-facing visual assets rather than only prose: market comparisons, product matrices, flowcharts, material boards, process diagrams, or research summaries with charts.

Outputs

The workflow writes outputs/<slug>.md, outputs/<slug>.provenance.md, and outputs/<slug>.assets/ with manifest.json, source data, chart/table assets, and optional generated images.

Accuracy rule

Factual charts and comparison tables are generated from structured source data. Image models are reserved for conceptual assets and are not used to invent numbers, market shares, rankings, or factual labels.

See also