{"id":3722,"date":"2026-07-20T03:40:38","date_gmt":"2026-07-20T03:40:38","guid":{"rendered":"https:\/\/tucumandevelopers.com\/index.php\/2026\/07\/20\/we-built-an-ai-board-of-directors-on-qwen-then-we-asked-it-whether-we-should-migrate-to-qwen\/"},"modified":"2026-07-20T03:40:38","modified_gmt":"2026-07-20T03:40:38","slug":"we-built-an-ai-board-of-directors-on-qwen-then-we-asked-it-whether-we-should-migrate-to-qwen","status":"publish","type":"post","link":"https:\/\/tucumandevelopers.com\/index.php\/2026\/07\/20\/we-built-an-ai-board-of-directors-on-qwen-then-we-asked-it-whether-we-should-migrate-to-qwen\/","title":{"rendered":"We built an AI board of directors on Qwen. Then we asked it whether we should migrate to Qwen."},"content":{"rendered":"
\n
\n

Full honesty: the bare model tied us on naming missing inputs and reversal conditions. A single good prompt gets you further than people admit. But the structure wins exactly where structure should: dissent, per-option verdicts, calibrated confidence, and not inventing a “Steering Committee” that doesn’t exist.<\/p>\n

<\/a> The demo decision we couldn’t resist <\/h2>\n

For the video we gave the board a real question: “Should we migrate our core inference backend from OpenAI to Qwen to cut costs?”<\/em> A Qwen-powered board, deliberating about Qwen, at a Qwen hackathon. We expected either comedy or sycophancy.<\/p>\n

We got neither. The verdict came back Conditional, medium confidence<\/strong>. It flagged pricing we hadn’t verified, missing production observability, and customer-trust risk from silent output regressions, then recommended phased validation instead of a leap. The Skeptic forced two full rounds of revisions. There’s a weird pride in watching your own product decline to flatter the sponsor.<\/p>\n

<\/a> Then we pointed the society at itself <\/h2>\n

Near the end (in that dangerous hackathon phase where you should be recording your video and instead you’re building) we applied the same architecture to the product. A Feedback Intelligence Council reads user feedback and produces a ranked need-brief. A Feature Delivery Loop has an SWE agent draft a build spec and a QA agent tear it apart, bounded to two rounds. It proposes; a human merges. My favorite behavior: it refused to build a feature because “only 3 feedback notes” was insufficient signal. We built an agent that says no, and that felt right for this product.<\/p>\n

<\/a> What actually bit us <\/h2>\n

Sharing these because build journals that skip the bugs are ads:<\/p>\n