UGC Wingman Release Notes

Released July 8, 2026

What is UGC Wingman?

UGC Wingman is an AI-powered copilot for beginner UGC (User Generated Content) creators. You give it a product or brand, answer a few questions about your style, and it walks you through an 8-step workflow that produces a hook, a structured script, and a shot-by-shot filming plan.

The goal is not to write your video for you. It's to remove the paralysis that stops most beginners before they ever start.

What's in this release

The core 8-step workflow

1. Entry confidence check — a quick emoji rating of how ready you feel before you start, so you can compare it to how you feel at the end
2. Creator voice profile — 5 quick questions about your storytelling style, tone, and energy so the tool can write more like you (fully skippable)
3. Product input — the product name, a brief description, and what your target audience is currently doing instead
4. Brand dossier — AI-researched brand profile covering target customer, brand tone, gap analysis, and a content angle for you to choose from
5. Hooks — 3 opening lines tailored to your chosen angle and voice profile
6. Script — a full structured script in the Hook / Problem / Experience / Result / CTA format, tuned to your target video length
7. Shot list + PDF export — a shot-by-shot filming plan with shot type, camera direction, and timing; downloadable as a PDF
8. Confidence layer + exit survey — coaching on whether your script is ready to film, plus a check on whether the experience moved the needle for you

Features worth knowing about

• Target video duration — pick 15s, 30s, or 60s and the script word count and shot plan adjust accordingly
• Live word count bar — shows in real time whether your script is on target, too long, or too short
• Sources panel — every brand dossier shows the real web sources the research drew from
• Creator voice persistence — your voice answers collapse to a summary bar so they stay visible without taking up space
• Feedback form — a short survey at the bottom of every page so you can tell me what worked, what didn't, and whether you'd pay $1 for this

Known limitations

• Mobile experience is not fully optimized. The app works on mobile but was built and tested primarily on desktop. Some layouts and touch targets may feel cramped on a small screen. A dedicated mobile pass is planned.
• AI scoring trends high. The built-in eval scoring uses the same AI model to grade its own output, a known bias called "self-grading." Scores near 100% should be read with that caveat in mind. Rubric calibration is on the backlog.
• Session data resets on server restart. The app runs on a free hosting tier where in-memory data clears when the server restarts or redeploys. This is expected for the beta.
• Deep Dive research mode is admin-only. The grounded web-search version of the brand dossier is reserved for admin accounts during beta to manage API costs. Most users will see Quick Research, which is still solid.

Known defects

None currently open. All defects found during internal testing have been resolved.

What's coming next

1. UI/UX polish pass — the app works, but it doesn't look as intentional as it should before I share it more widely. A visual refresh is the top priority before the wider cohort invite.
2. Mobile optimization — making the layout, touch targets, and navigation usable on a phone.
3. Slide deck and portfolio update — updating the demo slide deck with the live URL and app screenshots, and building a portfolio page that tells the story of how this was built.

Build stats (for the curious)

Security audit completed before beta — 11 findings reviewed, all medium-severity issues resolved.