AdPilot · Studio · decision

Workflow builder — pick the direction to ship

Three judge-verified samples of the same builder screen, built through the OpenDesign pipeline from community research (n8n, Zapier, Make, Gumloop, OpenAI AgentKit, AgentHub). Same workflow underneath: abandoned-cart recovery with typed edges, approval gates, compiled code. Pick the one that feels most trustworthy to you.

What the research said (docs/42, Addendum 3):
Recommendation:A — it is the direction you already approved ("very close"), now upgraded with the seven community-researched features. B and C are genuine alternatives if you prefer their bet.
Option A

Graph studio — Copilot + canvas

Recommended

The full three-column studio: Copilot proposes graph diffs (ghost nodes, Apply/Discard), typed-edge chips, Check panel, versions & templates. You get: per-node run badges, insert-on-wire ⊕, minimap, zoom, Check panel with type-mismatch/warning, run-to-here ▶, palette strip. Cost: three columns = densest screen; smallest merchants may need a guided mode on top.

judge: pass57.6 KBworkflow-canvas-v1.htmlOpen full size ↗
queued ✓

Option B

Ops console — execution data first

n8n's trust model in Calm Studio clothes: every node shows its last run's in→out data, and a timeline strip shows the run as bars in the graph. Strongest for: hands-on operators who debug workflows themselves. Cost: densest learning curve; the Copilot chat is not on this screen — it's an expert console.

judge: pass23.0 KBworkflow-canvas-v2-opsdense.htmlOpen full size ↗
queued ✓

Option C

Chat-first — Copilot builds, graph proves

Gumloop-style polish: the conversation is the product; the graph is a read-only proof with pending ghost nodes and a cost prediction strip. Strongest for: non-technical merchants; lowest time-to-first-automation. Cost: direct editing is demoted to a drawer — power users lose the always-there canvas and inspector.

judge: pass15.5 KBworkflow-canvas-v3-chatfirst.htmlOpen full size ↗
queued ✓