Spinning up a fresh cover image for every campaign eats designer time on repetitive work. This agent takes one brief and renders on-brand banners across every size you need, using your locked Bannerbear templates.
sonnet3 daysBannerbearClaudeAirtableFigma
Claude
60ROI
70Scale
$3k91Saved
ROI for
README.md
Why this subagent
Spinning up a fresh cover image for every campaign eats designer time on repetitive work. This agent takes one brief and renders on-brand banners across every size you need, using your locked Bannerbear templates.
It handles the awkward part, fitting copy without overflow and matching your palette, then hands back ready URLs in Airtable. You define the template once and get consistent covers for each new post or launch without reopening the design file.
How it runs
Used at step 01 to kick off the pipeline.
Write
Used at step 01 to kick off the pipeline.
WebFetch
Used at step 01 to kick off the pipeline.
WebSearch
Used at step 01 to kick off the pipeline.
Pick the matching Bannerbear template and pass in copy, colors, and any product image.
pending
Render banner variants at each required size, including LinkedIn cover, X header, and OG image.
pending
Return the rendered URLs to Airtable and flag any text that overflows its frame for a manual fix.
pending
Sample output
json
// Sample output
// (generated when the pipeline finishes)
Given a banner brief, render Bannerbear variants per required size with headline and subtext placed safely inside the template; output an array of size plus image URL.
Unlock the rest
The full agent definition, install snippet, and starter task are gated for community members.
Members get the full `.md` agent file, the npm / pnpm install one-liners, a starter prompt that we've tuned against real runs, and the open-source repo when this automation ships there. One email, magic link, done.