The project can be reopened after generation and the script/avatar settings edited in place, with updated generate settings visible before rerendering.
What was measured
Editing/refinement
Whether the user can change the script, avatar, voice, captions, or hook without rebuilding the ad from scratch.
context, not decisivecapability
Editing flexibility matters for workflow and iteration, but it is not the core measure of whether the generated ad itself is good. (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
Also checked on this input — same tool, 5 other criteria
Ad-readiness◐ MixedThe platform exports a complete video, but the output remains generic enough that it would likely need polishing before paid use.Avatar realism⚠ StruggledThe presenter still reads as AI-generated compared with higher-end tools.Platform formats✓ WorkedProduced a vertical 9:16 short-form video export, matching the TikTok/Instagram Reels/YouTube Shorts format the report targets.Product understanding⚠ StruggledFor app ads, the generator can omit app UI and fall back to a generic background, weakening product-specific messaging.Script quality & persuasiveness⚠ StruggledThe tool can keep an educational script easy to understand, but the delivery feels slightly flat and less engaging.
Provenance
- Observation
- 53d705e0-3026-42e6-ab29-910a6d9ca3c6
- 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
- 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: "akool"
})MCP · mcp.aidemos.com/api/mcp
Free with attribution.
Same input, same check — 0 other tools
measured on Editing/refinement
No other tool was measured on this criterion for this input.
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