Canvora × Perplexity Computer

On-brand visuals for Perplexity Computer

Research is only half the deliverable. Turn Perplexity Computer's findings into stat cards, infographics and carousels — cited content, designed.

Start free Setup guide

Free credits, no card required. Please make sure there is always a human in the loop.

Get started

Terminal

# CLI lane (any shell-capable setup)
npx skills add canvora/canvora-mcp
export CANVORA_API_KEY=vd_...

# Then hand research output straight to Canvora:
canvora generate --input "$(cat research-summary.md)" \
  --format infographic,stat_card --style corporate

This is what your agent ships

One generation, localized twice. Same design, natively re-composed in Spanish and Arabic — right-to-left done correctly, not mirrored English.

Generated with the same commands shown on this page.

How it works

1. Research produces the brief

Perplexity Computer does what it does best

Perplexity

"Research remote-work productivity studies from the last
 two years; summarize the five strongest statistics with
 sources into findings.md"

2. The findings become visuals

Each stat gets designed, not pasted

Terminal

ID=$(canvora generate \
  --input "$(cat findings.md)" \
  --format stat_card,infographic \
  --style corporate --brand "$BRAND_ID" | head -1)

canvora status "$ID" --json   # poll to completed

3. Package for distribution

Carousel for social, PDF for the newsletter

Terminal

canvora variations "$ID" --count 1     # alternate takes
canvora download "$ID" --dir report-visuals/

What is Perplexity Computer?

Perplexity Computer is Perplexity's agentic workspace: it researches, browses and synthesizes with citations, producing dense, factual summaries. That output is Canvora's ideal input — numbers, claims and structure that map directly onto data-visual formats.

Research-shaped input

Summaries with statistics and key claims map straight onto stat cards, comparison charts and infographic sections — no rewriting step.

Data-visual formats

infographic, infographic_long, stat_card, comparison_chart, timeline — formats built for exactly what research produces.

Multi-market output

Research once, publish everywhere: localize re-renders the same visual natively in any of 150+ languages, RTL included.

A real research-to-visual run

From question to shareable asset set

Perplexity

> "Research: how much does deep work time affect remote
   team output? Turn the findings into a visual set."

Perplexity Computer: Researched 14 sources.
  Key stat: teams protecting 4+ focus hours ship
  measurably more than always-online teams.

  -> canvora generate --input "..." \
       --format stat_card,instagram_carousel
  -> status: completed
  -> 6 visuals: 1 stat card + 5 carousel slides,
     each slide one finding, sources on the last slide.

Same findings, every market

The research is universal; the language shouldn't be a barrier

Terminal

canvora localize "$ID" --language es
canvora localize "$ID" --language de
canvora localize "$ID" --language ar   # native RTL composition

# Identical design; the statistics now read natively
# in each market's language.

Why Perplexity Computer + Canvora

Research summaries are ideal generation input — statistics map onto stat-card and infographic formats
Dense multi-point findings become carousels: one finding per slide, sources on the last
localize turns one research run into assets for every market
Brand kits keep a publication look consistent across every report
CLI with JSON output, or MCP for chat-first setups

Command reference

Add --json to any command for machine-readable output. Progress goes to stderr, results to stdout.

Command	Description
canvora generate	Create visuals from --idea, --input text, --url or --file-url; pick formats, brand, style, language
canvora status <id>	Check a generation; --json returns status and output file URLs
canvora download <id>	Save output files to a directory
canvora localize <id>	Same design, natively re-composed in another language (RTL included)
canvora variations <id>	Alternate takes on a finished generation
canvora edit <outputId>	Revise one visual with a natural-language instruction
canvora formats	List all 100+ format ids
canvora brands	List brand kits (colors, fonts, logo, tone)
canvora credits	Show credit balance

100+ formats, one engine

Every format has platform-correct composition and safe zones — your agent picks by id.

Instagram Carousel

Up to 20 slides, hook to CTA

LinkedIn Carousel

Swipeable document posts

Pitch Deck

Coherent multi-slide sets

Instagram Post & Story

Feed and vertical formats

Stat Card

One number, designed to land

Infographic

Data and process visuals

Blog Header & OG Image

The launch surface

Ad Creatives

Display and social ads

See all formats and tools →

FAQ

How does the research get into Canvora? +

As text: --input takes the summary directly (or --url if the research lives at a link, or --file-url for a PDF). Canvora structures it into sections and designs each — statistics land on stat cards, sequences on timelines, comparisons on charts.

What does a visual set cost? +

Flat credits: 10 per single visual, 15 per carousel slide. A stat card plus a 5-slide carousel is 85 credits, known before you run it. Balance is checked before deduction and failed generations refund automatically.

Can it keep our publication style? +

Yes — a brand kit (colors, fonts, logo, tone) applies to every generation with --brand. Reports, social cuts and newsletter graphics all come out of the same visual system.

Are the visuals accurate to the findings? +

Canvora designs the text you provide — use --exact when wording must be verbatim (statistics, quotes). Review remains yours: keep a human in the loop before anything cited goes public.

Also works with

Claude Cowork → OpenClaw → Any MCP client →

Your agent's next tool call is a design department.

Create a free account, set one key, and let Perplexity Computer ship on-brand visuals.

Start free Read the setup guide