# Shane Barakat
> I'm currently building Polarity, an applied research lab building self-improving models, on leave from engineering at UWaterloo.

## For agents
Structured JSON (recommended): https://shanebarakat.com/content.json
Plain text summary: https://shanebarakat.com/llms.txt
Research PDFs are linked from content.json and the Research page.

## Home
I'm currently building Polarity, an applied research lab building self-improving models, on leave from engineering at UWaterloo.
I'm passionate about building agents and post-training research. The field moves fast and I find that exciting. My take on the future is that the frontier era is almost over, the moat is drying up, and the models that define what comes next will be open-source and built through RL, not gated behind a handful of labs. I want to work on systems that improve from their own experience instead of waiting on the next release.

## Socials
- GitHub: https://github.com/shanebarakat
- LinkedIn: https://www.linkedin.com/in/shane-barakat/
- X: https://x.com/shanebarakat_

## Work — Currently
- Polarity (Present)
  Role: Co-Founder & CTO
  Post-training models to build collective intelligence. Backed by Afore Capital.
  https://polarity.cc

## Work — Previously
- Shopify (2025)
  Role: Engineering
  Built and rolled out onboarding agents to millions of merchants.
  https://www.shopify.com/ca
- IntouchCX (2025)
  Role: Engineering
  Built out enterprise internal workflow systems end to end.
  https://www.intouchcx.com
- UWaterloo (2025)
  Role: Undergraduate Research Assistant under Dr. Ken McKay
  Built models and solutions for the Chicago Bureau of Police.
- (2024 and before)
  A bunch of startups and other roles.

## Projects
- Zenith
  Sub-millisecond p95 at a billion rows. Beats Postgres and ClickHouse on agent trace benchmarks. 130+ GitHub stars.
  https://zenith.polarity.so/
- Palkia
  RAG context engine for retrieving relevant codebase context and generating structured bug reports. Won Google's AI Innovation Award.

## Research
- Behavioral Hot Paths (2026)
  Author, Polarity Labs
  Discrete, cost-aware discovery of recurring agent behaviors for self-specializing agents.
  PDF: https://shanebarakat.com/research/hotpaths.pdf
- QA-Bench (2026)
  Co-author, Polarity Labs
  Benchmark for evaluating agent QA across bug detection, test generation, and regression testing on 506 real-world tasks.
  PDF: https://shanebarakat.com/research/qa-bench.pdf
- Omnigrep (2025)
  Co-author, Polarity Labs
  Multi-turn agentic code search. 33% relative improvement over Claude Code on CodeSearchEval.
  PDF: https://shanebarakat.com/research/omnigrep.pdf

## Pages
- Home: https://shanebarakat.com
- Work: https://shanebarakat.com/work
- Projects: https://shanebarakat.com/projects
- Research: https://shanebarakat.com/research