This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady
What I Built
QuantCoach — a voice-first AI learning and research copilot for quant finance, DSA, and WorldQuant BRAIN-style alpha ideation.
It solves a very specific, very lazy-friendly problem: quant researchers waste enormous energy on remembering, repeating mistakes, and manually checking for pitfalls. You shouldn't have to dig through old notes, re-derive why a previous attempt failed, or scan every idea for lookahead leakage by hand. QuantCoach takes that busywork off your plate.
The core loop is simple. A researcher speaks an alpha intuition out loud, and the coach returns a candidate BRAIN-style Fast Expression plus the math behind it — read back aloud so their hands never leave the keyboard. Every idea, every dead end, and every DSA question gets stored, so the coach remembers the research history that the researcher would otherwise forget.
With QuantCoach, a researcher can:
- Ask questions or describe an alpha intuition out loud and get structured quant/DSA/math explanations plus a candidate Fast Expression
- Let the system remember every failed alpha idea, so they stop re-doing the same work
- Automatically trigger a quantitative rigor checklist: lookahead leakage, turnover drag, overfitting/p-hacking, and correlation warnings
- Keep asking follow-up questions in the same session without context-switching between notes, docs, and code
Who gets to be lazier: self-driven quant learners, WorldQuant BRAIN candidates, and anyone who would rather spend energy on thinking than on remembering where they left off last week.
Why it matters: one real quant learner put it simply — "The weak-spot tracker alone saved me hours of re-reading old notes." That is time handed straight back.
That is the whole idea behind Slow and Steady: stop sprinting between notebooks, docs, and code. Let the system hold the context. Think slowly, think steadily, and let the copilot do the tedious parts.
Demo
⚠️ Hosted on Render's free tier — the first visit can take 30–60 seconds to wake up. Fittingly on-theme for Slow and Steady. Thanks for your patience.
Code
Worth inspecting in the repo:
-
utils/prompts.py— the specialized BRAIN Fast Expression system prompt, fully inspectable and forkable -
.env.example— every key you need to run it locally -
README.md— architecture notes, the open-source rationale, and pricing logic
How I Built It
QuantCoach is built with open-source AI and open-weight models at its core. It is not a closed API with a UI wrapped around it. Open inference, an open memory layer, and model portability are the skeleton of the product.
The voice-first pipeline
Voice → ElevenLabs Scribe STT → Backboard Memory → Groq (open-weight)
→ Fast Expression + reasoning → Backboard save
→ ElevenLabs TTS → Voice Out
The stack
| Layer | Technology | Why the open approach matters |
|---|---|---|
| Inference | Groq + open-weight models | Low latency, and the model is swappable — change GROQ_MODEL_NAME in .env and the system upgrades |
| Persistent memory | Backboard | Stores every alpha idea, failure reason, and weak spot, so remembering doesn't depend on the user |
| Voice in | ElevenLabs Scribe STT | Hands-free input for thinking out loud |
| Voice out | ElevenLabs TTS | Reads explanations and expressions back, keeping hands on the keyboard |
| Frontend | Streamlit | A warm almond/crimson "editorial quant" workstation with custom Lucide SVG icons |
| Optional persistence | MongoDB Atlas | Powers the weak-spot tracker and progress dashboard; falls back gracefully to in-memory if not configured |
The alpha generator's rigor checklist
This is where the lazy payoff is concentrated. The system prompt actively checks for:
- Lookahead leakage — preventing future information from contaminating the idea
- Turnover drag — flagging turnover cost
- Overfitting / p-hacking — warning about overfit risk
- Correlation — noting likely overlap with existing factor families
These checks are not left to the user's memory. The system runs them for you, every time.
Laziness by design
The architecture is deliberately built so the researcher does less:
- One voice input replaces typing out a full Fast Expression
- Persistent memory replaces re-reading old notebooks
- Automatic pitfall warnings replace manually checking for lookahead leakage
- TTS readback replaces squinting at documentation while coding
The researcher thinks. The coach does the rest.
Why Does Open Innovation Matter?
1. Alpha ideas are proprietary. Privacy is a hard requirement.
An alpha hypothesis is the core IP of a quant researcher. Running open-weight models on Groq and keeping research context in Backboard's memory layer means the research context does not enter a closed commercial model's training pipeline. For anyone doing serious alpha work, this is not a nice-to-have — it is the reason the product can exist at all. No serious researcher is going to paste their alpha thesis into a closed API just to get syntax help.
2. Model portability is a research edge.
If a better open-weight model drops tomorrow, changing one line in .env is enough. No rewrite, no waiting on a closed vendor's roadmap, no negotiating for access. That kind of swappability is a research advantage that only an open stack provides — and for a side hustle, it's a moat.
3. Zero cost to the learner.
The entire stack runs on free tiers. Quant education is already gated by expensive data subscriptions and paid courses; the tooling shouldn't add another layer. Open AI makes this genuinely usable for anyone with curiosity and a laptop. And because open inference is cheap, the unit economics actually work at $29/month instead of collapsing the moment usage grows.
4. Inspectable reasoning, not a black box.
The prompts are in the repo, the models are open-weight, and anyone can inspect exactly how the coach reasons about alphas. For a tool that teaches quant thinking, black-box reasoning is unacceptable.
With a purely closed stack, this product would be either unsafe, unaffordable, or both. Open innovation is what made it possible to build something a quant researcher could actually trust with proprietary work — and trust enough to pay for.
The Lazy Payoff
This tool has already been tested on a real user, in the exact workflow it was built for: WorldQuant BRAIN preparation and alpha ideation.
- 6 ideation sessions over 4 days
- User feedback: "The first time it read back a Fast Expression with the math explained out loud, I actually understood why my previous attempt failed. That's never happened before. I didn't have to dig through old notes or try to remember what I was thinking three days ago. It just remembered for me." On the tracker: "The weak-spot tracker alone saved me hours of re-reading old notes. And asking follow-up questions out loud while I'm sketching ideas is way better than typing."
The lazy payoff breaks down into three concrete shifts:
| What you used to do | What QuantCoach does for you |
|---|---|
| Dig through old notes to remember why the last attempt failed | Persistent memory recalls weak spots automatically |
| Manually check lookahead / turnover / correlation | The rigor checklist surfaces them automatically |
| Switch between docs, code, and notes repeatedly | Voice interaction + TTS readback keeps you in one workflow |
When asked whether they'd pay $29/month, the user said: "Immediately, yes — I spend more than that on coffee in a week and this saves me hours."
At that price, the savings aren't a few minutes. They're an entire wasted research cycle avoided. That is the slow and steady payoff: less churn, fewer dead ends, and a research journal that stays alive instead of turning into a graveyard of half-finished ideas.
Prize Categories
Featured categories
- Best Use of Render — the demo is deployed directly on Render as the project's AI runtime and frontend host
Partner categories
- Best Use of Backboard — the persistent memory layer makes "remembering weak spots" a core product feature rather than an add-on
- Best Use of ElevenLabs — the full voice loop (Scribe STT + multilingual TTS) makes hands-free interaction the primary interface
- Best Use of MongoDB Atlas — optional persistence unlocks cross-session progress tracking and weak-spot analytics, with graceful in-memory fallback
QuantCoach is trying to prove one thing: open AI can make quant research both safer and lazier — handing the busywork to the system and leaving the thinking to the human. 🦥
Top comments (0)