AI Systems · 2026
Signal
A self-auditing Qwen agent that fact-checks its own recommendation before a human signs off.
- My role
- Builder · Qwen Cloud AI Hackathon, Track 4
- When
- 2026
- Status
- Live on Alibaba Cloud
- Stack
- Qwen Model Studio, Alibaba Cloud Function Compute, TypeScript
01
Where it started
Growth teams keep having to decide which ad creative to refresh, retire or scale, with the evidence scattered across ad libraries and campaign pages. A generic chatbot gives them no workflow, no structured evidence and no accountability.
02
What I owned
Builder · Qwen Cloud AI Hackathon, Track 4
03
How I built it
- Collected live owned and competitor creative observations through Qwen web search and normalised them into typed creative families.
- Added a second, adversarial Qwen pass that grades every factual claim and fetches every cited URL to check it against the live web.
- Routed each run into an append-only review ledger where an operator must acknowledge every checkpoint, then deployed to Alibaba Cloud Function Compute.
04
What changed
Live endpoints return pre-audited decision packets held at pending human review: a decision with an audit trail, not a chat reply.
Qwen Model StudioAlibaba Cloud Function ComputeTypeScriptPython