The app interface was not automatically included, so the output lacked built-in contextual visuals for the product.
What was measured
Product understanding
Whether the tool gets the product right—its features, positioning, and audience—or produces generic or inaccurate messaging.
decisive for this rankingtransformation
If the tool misstates the product or writes generic messaging, it fails to produce a usable ad for the intended offer. (3 of 3 judges)
What was given, what came back
Test input: Duolingo – Mobile App · text
Input — what we sent
The exact prompt
Product URL: https://www.duolingo.com/ Exact Script Hook: Learning a new language has never been this easy. Script: I've been using Duolingo for a few minutes every day, and it's made language learning simple and fun. The short lessons are easy to follow, and the daily practice keeps me motivated. If you're planning to learn a new language, give Duolingo a try. Output Requirements - Vertical (9:16) - 20–30 seconds - UGC-style AI presenter - Natural AI voice - Captions enabled
A short-form UGC-style video ad prompt for a consumer mobile app, designed to test whether a tool can explain app benefits simply and persuasively in a social ad format.
Why this input is hard
- · mobile app understanding
- · consumer app promotion
- · script quality
- · avatar realism
- · voice quality
- · caption quality
- · overall ad readiness
Output — unretouched
No output artifact
The verdict rests on the tester's written observation alone — no file was captured for this cell.
Also checked on this input — same tool, 3 other criteria
Ad-readiness◐ MixedThe export was clean and usable for professional platforms, but the workflow still needed extra editing to make the video more engaging.Script quality & persuasiveness◐ MixedThe delivery matched educational content, but it could feel slightly formal rather than highly engaging.Voice quality✓ WorkedThe voice output was stable and natural with no major inconsistencies.
Provenance
- Observation
- f9731c12-38f6-41b7-9d50-5328abaa1551
- Evidence run
- f91a51ec-b400-46fe-97f5-7e779fe17532
- Study
- Generate UGC-Style Video Ads With AI Avatars
- Research task
- 86baxegpg
- Tested at
- not recorded
- Source
- first-party
- Evidence state
- observed
- Proof shown
- input only
- 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: "veed-io"
})MCP · mcp.aidemos.com/api/mcp
Free with attribution.
Same input, same check — 4 other tools
measured on Product understanding
AKOOL⚠ StruggledFor app ads, the generator can omit app UI and fall back to a generic background, weakening product-specific messaging.Creatify.ai⚠ StruggledThe output does not clearly showcase the app interface and relies on generic background context, which weakens app-specific product understanding and relatability.Topview AI◐ MixedIt states the learning benefit clearly, but it does not surface app UI or language-learning context strongly enough.Vidnoz AI⚠ StruggledThe output uses a generic background and omits the app UI, so it does not strongly communicate the mobile-app product itself.
This evidence is published in
From the same study (page rebuilt from a later run)
Real inputs and real outputs, no retouching · every cell queryable via API & MCP · aidemos.com