🧪 Superstar Sale · Female-Market Dropship — Pair Test Plan

Draft pair-test plan for Superstar Sale · Female-Market Dropship. Flows were auto-drafted from the project page — review and edit the steps before running the session. Two testers: the agent and Mike execute the same steps, compare results, and file GitHub issues for every mismatch.

Protocol Environments Flows Results
Draft plan. The flows below were generated from the project page — treat them as a starting checklist, edit freely before the session.

How this session works

  1. Agent executes a step in a real browser, posts screenshots to the Discord thread, and states pass/fail.
  2. Mike repeats the same step with his own accounts and data.
  3. Compare. Same result → check the box in the log. Different → both re-run once, then file an issue.
  4. File a GitHub issue for every wanted change (conventions below) and link it in the step’s issue box.

Issue conventions

Environments & test data

Repomicrospaces/superstarsale
SessionsAgent uses fresh browser profile + generated test data; Mike uses his real accounts with plus-tagged emails so records stay filterable.

Flows (draft)

A1Agent Source candidates. 3–5 supplier options for the picked product; order a sample and hold it before a dollar of ad spend. No sample, no campaign.
Expect: same result for both testers — screenshot the end state.
A2Mike Repeat A1 with your own account/data — compare against the agent’s result.
Expect: identical behavior; file an issue on any mismatch.
B1Agent Mike steps (agent cannot do these): Meta ad account billing/2FA, supplier and payment-processor accounts, spend approval, domain/policy sign-off on the store.
Expect: same result for both testers — screenshot the end state.
B2Mike Repeat B1 with your own account/data — compare against the agent’s result.
Expect: identical behavior; file an issue on any mismatch.
C1Agent Run the loop. Weekly kill/scale review on CTR → CPC → CPA; scale the winner; when a second niche graduates, it gets its own card and page as a new business.
Expect: same result for both testers — screenshot the end state.
C2Mike Repeat C1 with your own account/data — compare against the agent’s result.
Expect: identical behavior; file an issue on any mismatch.
D1Agent Campaigns PAUSED by default — nothing goes live without Mike's explicit approval. The wrapper's default state is the enforcement.
Expect: same result for both testers — screenshot the end state.
D2Mike Repeat D1 with your own account/data — compare against the agent’s result.
Expect: identical behavior; file an issue on any mismatch.
E1Agent One niche per business — isolation from the IG-affiliate and faceless rails cuts all ways: no shared offers, no cross-linked campaigns.
Expect: same result for both testers — screenshot the end state.
E2Mike Repeat E1 with your own account/data — compare against the agent’s result.
Expect: identical behavior; file an issue on any mismatch.
F1Agent Sample before spend — never run creative for a product nobody on the team has held.
Expect: same result for both testers — screenshot the end state.
F2Mike Repeat F1 with your own account/data — compare against the agent’s result.
Expect: identical behavior; file an issue on any mismatch.

Results log

Empty — fill in during the session: step id, pass/fail per tester, issue links.

StepAgentMikeIssue
————