I got tired of vibe investing, so I built an AI committee that shows its work

We have vibe coding now — so I guess we have vibe investing too. Most "AI stock picker" tools work the same way: you feed in a ticker, and out comes "BUY — confidence 87%" with no way to see why. You're not analyzing anything; you're trusting a vibe. If I can't inspect the reasoning, I can't trust the call, and I definitely can't learn from it.

So I built the opposite: a multi-agent committee where the output isn't a score — it's an auditable trail from raw evidence to a final trade thesis. Bull and bear analysts argue the ticker out, a risk manager signs off, and the final decision is required to cite the specific evidence it rests on. I called it VerumTrade (Latin verum, "truth"). It's open source (Apache-2.0), and this post is about how it's put together, not a pitch.

The core idea: audit the call instead of trusting the vibe

The design constraint that drove everything: at every step, you should be able to read the reasoning and inspect the evidence it was built on. No black box. That turned out to map naturally onto a multi-agent graph, where each stage produces structured output the next stage consumes.

The pipeline runs six stages:

1. 
   Analysts gather market, news, social, fundamental, and catalyst evidence in parallel.


2. 
   Evidence graph distills those raw findings into structured, deduplicated facts — each with a stable ID.


3. 
   Bull/Bear debate — two agents argue the thesis from opposite sides.


4. 
   Trader plan turns the debate into an actionable proposal.


5. 
   Risk review checks sizing, timing, concentration, and downside.


6. 
   Decision records the final rationale plus the full trace.

Each arrow in that chain is a structured handoff, not a vibe. The debate step was the one that surprised me most — forcing an explicit adversarial pass (a Bear agent whose only job is to attack the thesis) catches a lot of motivated reasoning that a single "analyst" agent happily glosses over.

Standing on a predecessor's shoulders — and what I added

I'll be upfront: VerumTrade started from

I'd genuinely like feedback on the evidence-graph and the "decision must cite its evidence" constraint — what would you want to see in the trace to actually trust a recommendation? That question is most of why I open-sourced it.