Building a 13-Agent Marketing Society on Qwen Cloud — What Actually Broke, and What I Learned Fixing It

A developer built Nexus AI, a 13-agent marketing society on Qwen Cloud, where specialized agents like Social Manager and Brand Guardian independently review each other's work. The project revealed critical bugs: silent data routing failures where agents returned wrong outputs due to naive keyword matching, and a mid-project migration from async PostgreSQL to sync SQLite that left the codebase broken. Fixing these required re-keying agent routing off fixed system prompts and systematically auditing every agent's output.

Written for the Qwen Cloud Global AI Hackathon 2026 — Track 3: Agent Society. Most "AI marketing" tools are one LLM wearing a lot of hats — a single prompt that generates a social post, then a different prompt that pretends to be an ads analyst, then another that pretends to audit its own compliance. Track 3 of this hackathon asks for something different: an agent society — specialized agents that actually divide the work and can disagree with each other, the way a real team does. That's what I set out to build with Nexus AI : 13 specialized agents — Social Manager, Brand Guardian, Digital Marketer, Ads Manager, SEO Expert, Analytics, Conversion Optimizer, Community Engagement, Market Intelligence, Dynamic CFO, Security SRE, Calendar Planner, and Media Generator — coordinated by a central orchestrator, all powered by Qwen-Max through Alibaba Cloud's DashScope SDK . The feature I care about most isn't any single agent — it's what happens between two of them. Social Manager drafts a LinkedIn post. Before anything gets auto-published, Brand Guardian independently reviews that exact draft. In one real run, Social Manager's draft included the line "Guaranteed 4.2x ROAS in 14 days, or your money back." Brand Guardian caught it, flagged it as an That's the whole pitch, actually working: two agents, one veto, a real reason attached. Not a shared script producing two outputs that happen to look different. The honest version of this build: the codebase I inherited had been through a mid-project migration — from an async PostgreSQL design to a synchronous SQLite one — that never finished. The database layer had moved to sync, but every router still expected an async session; the config file had been rewritten with different field names than the code still expected; the test suite's fixtures were still async. None of it would even boot. Getting to a working demo meant tracing that mismatch through the entire stack before a single agent could run — config, database session handling, every router, the orchestrator, the test fixtures. Once it booted, the harder bug was quieter: some agents were silently returning the wrong shaped data. A social post that happened to mention "SEO" as a topic would make Brand Guardian's review get hijacked by the SEO agent's response template instead of its own, because the underlying simulator routed responses by naive keyword matching, and "SEO" is a normal thing for a marketing post to mention. I only found this by refusing to trust "the API call returned 200" as proof of correctness, and instead systematically auditing what every one of the 13 agents actually produced, end to end, for a full cycle. Two of thirteen were quietly wrong. Fixing it meant re-keying every agent's routing off something that can never collide with user content: each agent's own fixed system prompt, instead of generic words its output might happen to share with someone else's. The integration itself, once the plumbing was fixed, was straightforward: dashscope.Generation.call against Alibaba Cloud's native endpoint, one unified QwenClient that every agent shares, with a high-fidelity local simulator as a fallback so a demo never depends on live network conditions or API quota. I verified the real path independently of the simulator — sent a literal "reply with exactly: REALAPIWORKED" through the actual client class, got the real word back from Qwen-Max, confirmed the simulator wasn't quietly intercepting it. Real OAuth so the agents can act on real social accounts starting with X/Twitter , and deployment so this isn't just a local demo. The agent logic and the Qwen integration were always the easy part in hindsight — the real work was making sure "multi-agent" was a fact I could prove, not a claim I could just assert. Built for the Qwen Cloud Global AI Hackathon 2026, Track 3: Agent Society. Code: github.com/MelekhYomi/mark-agen-nexus-ai Whatsapp +2347068561873