#experiment

Code-grounded implementation+product spec for the voice demo lander: live feature spec, real providers (ElevenLabs voice, OpenPay, Cognito Google auth), video-first content on Sophie Dee (live + non-live), multi-variant design direction (casino + clean), reuse map, decisions, blockers, build sequence.

Config-driven voice demo lander for hand-testing: flip Lean-3 / Core-5 / Full-7 / Photo-led shapes, gate type, upsell timing & photo price live. Full answer→gate→register→paywall flow with GTM-2182 funnel events.

145 agent-initiated hang-ups in the inappropriate/unclear buckets, sub-categorized with suggested true/false-positive verdicts for human review; includes recommendations.

Performance read across 12 TJ campaigns (4 countries x 3 device types), plus the final read of the one campaign we continued (Canada / Android Mobile). Conclusions by country, device/OS, source, creative, landing; final campaign totals, per-creative, and TrafficJunky vs Everflow attribution. Trends based on registrations.

Which quiz funnel produces better in-product behavior. Part 1: visual scoreboard (paired bars + multiples). Includes click->signup via Everflow paid-click proxy (match_me ~1.5%, creator_funnel_v2 ~1.6% — tied at top of funnel; creator pulls ahead post-signup). Both arms keyed on quizVariant identify trait. Source: BigQuery dbt marts + Everflow. Data as of Jun 4, 2026 (window May 28 to Jun 3). Facts only.

Interactive pricing page prototype: subscribed/unsubscribed states and tiered plans bundling images + voice minutes (+5/$8wk, +30/$22, +500/$125). The longer you stay, the more images and minutes you get.

From one Slack mention to a shipped dashboard in ~5 minutes (down from 46). 8 specialized agents on Anthropic Managed Agents + Vercel + Slack + Metabase. Includes sequence diagrams, agent breakdown, and what's next.

Project codename generator with SFW/NSFW modes, favorites, history, and Space-to-roll.

End-to-end audit. 65 campaigns, $24K spend, 90-day window. TJ to EF reconciliation, per-campaign tracking status, working/broken inventory, and 3 launch-quality recommendations.

Aggregated audit + loss investigation. $6,342 spend, $55 revenue (ROAS 0.87%), 20.2% click loss. Root cause: Safari ITP and structural iOS WebKit drop. iOS converts 2.5x worse than Non-iOS. Includes recommendations for future campaign planning.

Interactive voice-call UX prototype: orb interaction, heat meter, combo streaks, photo unlock spinner, paywall flow.