---
title: "R&D — Blog"
description: "R&D posts from GC AI."
canonical: "https://gc.ai/blog/category/r-and-d"
last_updated: "2026-11-05"
---

# R&D — Blog

> R&D posts from GC AI.

- [“Find me a case that says…”](https://gc.ai/blog/find-me-a-case-that-says): How GC AI’s R&D attorneys built case law research that searches legal databases, reads full decisions, and follows local research methods.
- [Thinking Beyond MCP, What We Learned Building Integrations for Legal AI](https://gc.ai/blog/thinking-beyond-mcp): What GC AI learned building more than 20 Agent Connectors: how tool design, scoped outputs, and approval controls shape integrations for legal work.
- [What we learned building 38 projects with Jev in 12 hours](https://gc.ai/blog/what-we-learned-building-38-projects-with-jev-in-12-hours): We built 38 projects with Typesafe AI's new classification model, Jev in 12 hours. We're sharing demos, results, and lessons from the internal hackathon.
- [Beyond Dependabot: Agentic Supply Chain Security](https://gc.ai/blog/beyond-dependabot-agentic-supply-chain-security): Software supply chain security at GC AI: See how vulnerability triage and tested dependency fixes helped clear a backlog of security advisories.
- [The Exhaustive Query Problem](https://gc.ai/blog/the-exhaustive-query-problem): Why can’t AI find every matching contract? Learn how Contract Intelligence solves exhaustive queries using structured contract data.
- [From Big Law to (Building) Legal AI: Six Months as an R&D Attorney at GC AI](https://gc.ai/blog/from-big-law-to-building-legal-ai-six-months-as-an-r-d-attorney-at-gc-ai): Six months after leaving Big Law for GC AI, R&D attorney Christine Yan shares lessons on building legal AI, ambition, prioritization, and agency.
- [From Big Law to Legal AI: My First Month as an R&D Attorney at GC AI](https://gc.ai/blog/from-big-law-to-legal-ai-first-impressions): Christine Yan, R&D Attorney at GC AI, shares her move from Big Law to Legal AI and what lawyers should know about working in product and AI.
- [How GC AI Thinks: The Agentic Loops and Graphs Behind Every Answer](https://gc.ai/blog/how-gc-ai-thinks-the-agentic-loops-and-graphs-behind-every-answer): Loops and graphs explained for in-house counsel: how GC AI coordinates parallel checks, research, and citation verification behind every answer.
- [In-House Legal Bench: Evaluating AI Assistants for In-House Legal Work](https://gc.ai/blog/in-house-legal-bench-evaluating-ai-assistants-for-in-house-legal-work): GC AI scored 86.8% vs ChatGPT 79.8%, Claude 68.4%, Gemini 57.5% on 100 in-house legal tasks. See the full benchmark methodology and results.
