The ad includes relevant running B-roll timed to the copy, but the runner shown is a visibly different person from the presenter, so the first-person testimonial premise is only partly preserved.
What was measured
B-roll / product integration
Relevant supporting footage or product shots, when the tool offers them.
decisive for this rankingtransformation
Relevant product shots and supporting footage help determine whether the ad feels complete and convincing. (3 of 3 judges)
What was given, what came back
Test input: Nike Pegasus 41 – Physical Product · mixed · group: ugc-style-video-ads
Input — what we sent
Input, verbatim
Product URL: https://www.nike.com/t/pegasus-41-mens-road-running-shoes-LMhrRG/FD2722-002 Exact script: Hook: These are my new favorite running shoes. Script: I've been wearing the Nike Pegasus 41 for my daily runs, and they've been incredibly comfortable from day one. They're lightweight, well-cushioned, and great for everyday training. If you're looking for dependable running shoes, they're definitely worth considering. Output requirements: - Vertical (9:16) - 20–30 seconds - UGC-style AI presenter - Natural AI voice - Captions enabled
A short-form UGC testimonial prompt for a physical consumer product, designed to test product comprehension, believable praise for a running shoe, and ad-style video generation quality.
Why this input is hard
- · Physical product understanding
- · UGC testimonial quality
- · Product presentation
- · Avatar realism
- · Voice quality
- · Commercial ad readiness
Output — unretouched
Also checked on this input — same tool, 5 other criteria
Ad-readiness◐ MixedThe output is close to shippable, but the mismatched runner undercuts the "I've been wearing these" testimonial premise enough that it still needs review before paid use.Avatar realism✓ WorkedThe on-camera presenter reads as a believable real person with a clean UGC look, and the report notes natural hand rendering and consistent identity throughout the clip.Caption quality◐ MixedCaptions are present and advance with the copy, but the report does not separately verify timing or styling on this input beyond the visible subtitle progression.Product understanding✓ WorkedThe tool correctly renders a gray Nike Pegasus shoe with the swoosh, colorway, and AIR ZOOM sole detail, matching the product prompt instead of generic running shoes.Script quality & persuasiveness✓ WorkedThe full script plays through naturally to the final word "considering," so the testimonial read is complete and holds together as a short-form ad script.
Provenance
- Observation
- 2d49686c-92bf-43cd-851e-8105079a6731
- Evidence run
- 9fdbb84b-4aa0-484d-8f89-5c46608019a5
- Study
- Generate UGC-Style Video Ads With AI Avatars
- Research task
- 86baxegpg
- Tested at
- not recorded
- Source
- first-party
- Evidence state
- verified
- Proof shown
- input + output shown
- Cost / latency
- not captured
- Repeat run
- not captured
- Tester
- not captured
The last three rows are honest blanks, not placeholders — our capture has no field for them yet.
Query this
get_evidence({
tool: "invideo-ai",
scenario: "ugc-style-video-ads"
})MCP · mcp.aidemos.com/api/mcp
Free with attribution.
Same input, same check — 6 other tools
measured on B-roll / product integration
AKOOL⚠ StruggledDoes not strongly highlight the shoes visually, so product integration stays weak.HeyGen◐ MixedThe Nike output includes relevant running lifestyle b-roll, but one outdoor running shot contains a visible semi-transparent smear/compositing glitch on the runner's leg.JoggAI✗ FailedThe tool can omit all product-supporting footage, producing a tight face-only crop with no held-up product, no B-roll, and no scene variety.Topview AI⚠ StruggledThe clip shows the presenter in a car without any shoe shots or other product visuals, so the Nike product is not visually integrated.VEED⚠ StruggledThe Nike output relies on a seated presenter, headline typography, and captions, but the report says product visuals were not strongly integrated by default.Vidnoz AI✗ FailedDoes not integrate product shots or supporting visuals; the finished clip stays on a plain talking-head background with no strong shoe emphasis.
This evidence is published in
Real inputs and real outputs, no retouching · every cell queryable via API & MCP · aidemos.com
