DEV Community: Rozoa

Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady Submission — QuantCoach

Rozoa — Wed, 21 Oct 2026 04:33:53 +0000

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

🚀 Try the Live Demo on Render

⚠️ 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

🔗 GitHub Repository

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. 🦥

# Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle Submission

Rozoa — Tue, 13 Oct 2026 13:15:19 +0000

Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle Submission

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle

What I Built

QuantCoach — a voice-first alpha research copilot for quant researchers grinding through WorldQuant BRAIN.

My friend was stuck in a loop every quant researcher knows too well: sketch an alpha idea on paper → try to write it as a BRAIN Fast Expression → get stuck on the math or operator syntax → lose momentum. The next day they'd forget why the previous attempt failed. Their research notebook was a graveyard of half-finished ideas with no thread connecting them.

QuantCoach is the tool they'd pay for to fix this.

It's a voice-first workspace where a quant researcher can:

Describe an alpha intuition out loud ("combine improving margins with a short-term reversal filter")
Get back a candidate BRAIN-style Fast Expression plus the math behind it
Hear the explanation read aloud so they keep their hands on the keyboard
Build a permanent memory of which factor families worked and which ones burned them
Ask follow-up DSA/math questions in the same session without breaking flow

Who pays for this: Quant researchers, retail quants, quant students, and anyone doing systematic alpha research.

Why they'd pay: Serious quant researchers already spend $100–500+/month on data subscriptions, courses, and tooling. A $29/month IDE-style copilot that remembers your research history, generates Fast Expression drafts, and warns you about lookahead leakage before you waste a week — that's a rounding error against the cost of one wasted research cycle.

It's a thinking partner for alpha ideation and quantitative learning. Not a black box promising returns. Not a signal service. An IDE for alpha ideas.

Demo

🚀 Try the Live Demo on Render

⚠️ Hosted on Render's free tier — it may take 30–60 seconds to wake up on the first visit. Thanks for your patience.

Code

🔗 GitHub Repository

The repo includes:

utils/prompts.py — the specialized BRAIN Fast Expression system prompt (inspectable, forkable)
.env.example — every key you need to run it locally
README.md — quickstart, architecture diagram, and pricing rationale

How I Built It

QuantCoach is built with open-source AI at its core, using a modular stack designed for privacy and speed — both of which are non-negotiable for quant work.

The voice-first pipeline

Voice → ElevenLabs STT → Backboard Memory → Groq LLM
     → Fast Expression + reasoning → Backboard save
     → ElevenLabs TTS → Voice Out

The stack

Layer	Technology	Why
Inference	Groq + GPT-OSS 120B (open-weight)	Ultra-low-latency. Fast enough that the voice loop feels conversational.
Memory / RAG	Backboard	Every alpha idea, every DSA question, every failure — stored so the coach remembers your research history.
Voice In	ElevenLabs Scribe STT	Multilingual speech-to-text. Hands-free is the whole point.
Voice Out	ElevenLabs TTS	Reads back explanations and BRAIN expressions. Keeps hands on keyboard.
Persistence	MongoDB Atlas (optional)	Powers weak-spot tracker and progress dashboard. Falls back to in-memory if not configured.
Frontend	Streamlit	Warm almond/crimson "editorial quant" aesthetic with custom Lucide SVG icons.

The alpha generator's system prompt does four things

Translates natural language intuition into BRAIN Fast Expression syntax
Calls out common pitfalls — lookahead leakage, turnover drag, overfitting across lookback windows
Warns when an idea is likely correlated with known industry factors
Refuses to promise performance — it's an ideation tool, not a signal service

The prompts live in utils/prompts.py. Anyone can inspect exactly how the coach reasons about alphas.

Why Does Open Innovation Matter?

Open-source AI wasn't a checkbox here. It was the entire reason this project is safe for a quant researcher to use — and safe enough that they'd pay for it.

1. Alpha ideas are proprietary. This is the whole game.

My friend is developing factor hypotheses that could be worth real money. Sending those prompts to a closed API means they enter someone else's training pipeline. Running open-weight models through Groq and storing memory in Backboard means the research context stays private.

For anyone doing serious quant work, this is non-negotiable. No serious researcher is going to paste their alpha thesis into a closed API just to get syntax help. The privacy angle is not a nice-to-have — it's the reason the product can exist at all.

2. Model portability is a research edge.

The alpha landscape moves fast. When a better open-weight model drops, they swap GROQ_MODEL_NAME in .env and the whole system upgrades. No rewrite. No negotiation with a closed vendor's roadmap. No waiting for someone else's product decision.

For a side hustle, that's also a moat. I'm not locked into one vendor's pricing or terms.

3. Zero cost to the learner.

Quant education is already gated by expensive data subscriptions and paid courses. The tooling shouldn't add to that. The entire QuantCoach stack runs on free tiers, making it accessible to anyone with curiosity and a laptop.

That said — the business works because the costs are near-zero at small scale. Once a researcher finds value, $29/month is trivially affordable against what they're already spending.

4. Transparency matters for a coach.

Because the model is open-weight and the prompts are in the repo, anyone can inspect exactly how the coach reasons about alphas. With a closed API, that reasoning is a black box. For a tool that's teaching someone quant thinking, black-box reasoning is unacceptable.

5. The side-hustle economics work because open AI is cheap.

Closed inference APIs would make this $29/month product unprofitable at any real usage volume. Open-weight models on Groq make the unit economics work — which is exactly why this can be a sustainable side hustle instead of a hobby that dies when the bill arrives.

My First User

My original user is the person this was built for — a quant researcher grinding through WorldQuant BRAIN. Here's what happened when they tried it:

Used it for: 6 alpha ideation sessions over 4 days
What they said: "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."
Did they pay? Not yet — it's still on free tier. But when I asked if they'd pay $29/month for it, they said "immediately, yes — I spend more than that on coffee in a week and this saves me hours."
What they asked for next:
- "Can it track which factor families I've already tried so I stop re-doing the same idea?"
- "Can it warn me when two alphas are probably correlated?"
- "Can I export my session history as a research journal?"

Those three asks are on the roadmap. The fact that they came up unprompted — from a real user, mid-session — is the strongest signal that this is a product, not a demo.

Would they pay? Yes. Would a quant student pay? Yes, at a lower tier. Would a small fund pay? Yes, at a team tier. The pricing tiers are already sketched in the README.

Prize Categories

I'm entering the following partner categories, each of which is genuinely load-bearing in the project:

Featured categories

Best Use of Render — Frontend and AI runtime hosted on Render
Best Use of Groq — Open-weight model inference for real-time alpha ideation

Partner categories

Best Use of Backboard — Memory & RAG powering the persistent research context. Every alpha idea, every failure, every DSA question is stored so the coach remembers the researcher's history.
Best Use of ElevenLabs — Full voice loop (Scribe STT + multilingual TTS) for hands-free alpha research. This is what makes the tool usable without breaking keyboard flow.
Best Use of MongoDB Atlas — Optional persistence layer for the weak-spot tracker and progress dashboard. Falls back to in-memory storage gracefully if not configured.

QuantCoach: An Open-Source Alpha Research Copilot for My Quant Friend

Rozoa — Sat, 03 Oct 2026 19:58:41 +0000

This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend

What I Built

I built QuantCoach, a voice-enabled open-source AI research copilot for my friend who is grinding through WorldQuant BRAIN.

My friend was stuck in a specific loop: they'd sketch an alpha idea on paper, try to write it as a BRAIN Fast Expression, get stuck on the math or the operator syntax, and lose momentum. The next day they'd forget why the previous attempt failed. Their research notebook was a graveyard of half-finished ideas with no thread connecting them.

QuantCoach fixes this. It's a voice-first workspace where they:

Describe an alpha intuition out loud ("combine improving margins with a short-term reversal filter").
Get back a candidate BRAIN-style Fast Expression plus the math behind it.
Hear the explanation read aloud so they can keep their hands on the keyboard.
Build a permanent memory of which factor families worked and which ones burned them.
Ask follow-up DSA/math questions in the same session without breaking flow.

It's a thinking partner for alpha ideation and quantitative learning, not a black box that promises returns.

Demo

🚀 Try the Live Demo on Render

(Note: Hosted on Render's free tier, so it may take 30–60 seconds to wake up on the first visit. Thanks for your patience!)

Code

🔗 GitHub Repository

How I Built It

QuantCoach is built with open-source AI at its core, using a modular stack designed for privacy and speed:

Groq — Ultra-low-latency inference on open-weight models (GPT-OSS 120B). Fast enough that the voice loop feels conversational.
Backboard — Persistent Memory & RAG. Every alpha idea, every DSA question, every "that one didn't work" gets stored so the coach remembers the researcher's history.
ElevenLabs — Scribe STT for voice input, multilingual TTS for reading back explanations and BRAIN expressions. This is what makes hands-free research actually usable.
MongoDB Atlas (Optional) — Powers the weak-spot tracker and progress dashboard. If not configured, the app falls back to in-memory storage with no crashes.
Streamlit — The entire interface, styled with a warm almond/crimson "editorial quant" aesthetic and a custom Lucide SVG icon system.

The alpha generation flow is a straight pipeline:
Voice → ElevenLabs STT → Backboard Memory → Groq LLM (BRAIN-style prompt) → Fast Expression + reasoning → Backboard save → ElevenLabs TTS → Voice Out.

The alpha generator uses a specialized system prompt that:

Translates natural language intuition into BRAIN Fast Expression syntax
Calls out common pitfalls (lookahead leakage, turnover drag, overfitting across lookback windows)
Explicitly warns when an idea is likely to be correlated with known industry factors
Refuses to promise performance — it's an ideation tool, not a signal service

Why Does Open Innovation Matter?

Open-source AI wasn't a checkbox here. It was the entire reason this project is safe for a quant researcher to use.

Alpha ideas are proprietary. This is the big one. My friend is developing factor hypotheses that could be worth real money. Sending those prompts to a closed API means they enter someone else's training pipeline. Running open-weight models through Groq and storing memory in Backboard means the research context stays private. This is non-negotiable for anyone doing serious quant work.
Model portability is a research edge. The alpha landscape moves fast. When a better open-weight model drops, they swap GROQ_MODEL_NAME in .env and the whole system upgrades. No rewrite. No negotiation with a closed vendor's roadmap.
Zero cost to the learner. Quant education is already gated by expensive data subscriptions and paid courses. The tooling shouldn't add to that. The entire QuantCoach stack runs on free tiers, making it accessible to anyone with curiosity and a laptop.
Transparency matters for a coach. Because the model is open-weight and the prompts are in the repo (utils/prompts.py), anyone can inspect exactly how the coach reasons about alphas. With a closed API, that reasoning is a black box.

Prize Categories

Best Use of Render — Frontend and AI runtime hosted on Render
Best Use of Backboard — Memory & RAG powering the persistent research context
Best Use of ElevenLabs — Full voice loop (STT + TTS) for hands-free alpha research
Best Use of MongoDB Atlas — Optional persistence layer for the weak-spot tracker
Best Use of Groq — Open-weight model inference for real-time alpha ideation

TY for this ossum opportunity...

Intro

Rozoa — Thu, 01 Oct 2026 17:03:42 +0000

Hi guys! I'm Aaryan from India. I just joined this community because I'm really passionate about Machine Learning and Artificial Intelligence. I’m currently exploring [mention 1 specific thing, e.g., Deep Learning / NLP / Computer Vision] and would love to connect with like-minded people. Excited to be here!