# GitHub Legal Team Builds AI Tools _GitHub's legal team used GitHub Copilot CLI to build custom AI tools for contract drafting and code analysis, boosting productivity._ **Published:** 2026-08-04 **Source:** https://www.startuphub.ai/ai-news/artificial-intelligence/2026/github-legal-team-builds-ai-tools --- A team of lawyers and program managers at GitHub has demonstrated that sophisticated AI tooling is no longer the exclusive domain of seasoned engineers. Using [GitHub Copilot CLI](https://github.blog/ai-and-ml/github-copilot/how-the-github-legal-team-used-copilot-cli-to-streamline-their-workflows/), individuals without traditional coding backgrounds were able to build custom applications that automate complex legal workflows, significantly enhancing productivity. This approach offers a compelling blueprint for how non-technical departments within organizations can leverage AI to solve their specific challenges. Repetitive Legal TasksDriver contract review and answering recurring legal questions required significant manual effortFrom the articleThe core idea behind this internal project was to tackle repetitive tasks common in legal work, such as contract review and answering recurring legal questions.faced byGitHub Legal TeamCorelawyers and program managers without traditional coding backgrounds built custom toolsFrom the article 5 mentionsBy employing Copilot CLI, which allows users to define desired functionalities in plain language, the GitHub legal team found they could create bespoke tools without writing extensive code.usedGitHub Copilot CLICoreused to define desired functionalities in plain language without writing extensive codeFrom the article 4 mentionsUsing GitHub Copilot CLI, individuals without traditional coding backgrounds were able to build custom applications that automate complex legal workflows, significantly enhancing productivity.to buildCustom AI ToolsEffectbuilt for contract drafting, code analysis, and automating DMCA noticesFrom the article 8 mentionsNgandu Kasuku, Principal Product Counsel, shared his experience building a contract drafting tool named terms-ai.Enhanced ProductivityOutcomesignificantly boosting productivity by automating complex legal workflows and tasksFrom the article 2 mentionsThis structure enhanced consistency and reduced manual effort.Internal Style GuideEffectFrom the articleA central feature of terms-ai is its internal drafting style guide, emphasizing plain language over archaic legal jargon.Automated DMCA NoticesEffectstreamlined the process of generating and sending Digital Millennium Copyright Act noticesFrom the articleJesse Geraci, Online Safety Counsel, focused on a critical need: rapidly analyzing source code to evaluate Digital Millennium Copyright Act (DMCA) notices.enablesDemocratized Tool-BuildingContextnon-technical departments can leverage AI to solve specific internal challengesFrom the articleThis democratization of tool-building has led to a cultural shift within the team, where previously hesitant individuals are now actively developing AI-powered solutions. The core idea behind this internal project was to tackle repetitive tasks common in legal work, such as contract review and answering recurring legal questions. Traditionally, these tasks involved significant manual effort and a reliance on copy-pasting existing guidance. By employing [Copilot](https://github.blog/ai-and-ml/github-copilot/how-the-github-legal-team-used-copilot-cli-to-streamline-their-workflows/) CLI, which allows users to define desired functionalities in plain language, the GitHub legal team found they could create bespoke tools without writing extensive code. This democratization of tool-building has led to a cultural shift within the team, where previously hesitant individuals are now actively developing AI-powered solutions. ## Internal Drafting Style Guide with terms-ai Ngandu Kasuku, Principal Product Counsel, shared his experience building a contract drafting tool named terms-ai. Kasuku, whose practice includes significant commercial work involving complex data and infrastructure deals, found himself bogged down by the unique nature of each partnership agreement. He initially used Copilot CLI for individual tasks but soon realized the potential for a more integrated solution. By scaffolding the project and storing key documents, instructions, and workflows in a repository, he created a version-controlled system for his AI prompts. This structure enhanced consistency and reduced manual effort. A central feature of terms-ai is its internal drafting style guide, emphasizing plain language over archaic legal jargon. Kasuku integrated principles from a broader legal drafting movement advocating for clarity. The tool also draws upon a library of previously completed agreements. When a partner submits an addendum or a new agreement, terms-ai can reference this existing, approved work. Sensitive information remains within an access-controlled internal environment, separate from the open-source tool's workflow. Kasuku reported that this tool has effectively halved his review and drafting time, leading to more consistent provisions and a preferred plain-language style. ## Automating DMCA Notices and Beyond Jesse Geraci, Online Safety Counsel, focused on a critical need: rapidly analyzing source code to evaluate Digital Millennium Copyright Act (DMCA) notices. The initial project involved creating GitHub Copilot instructions for recurring tasks like DMCA triage, code comparison, license checks, and circumvention reviews. The goal was to transform ad-hoc, individual prompt work into a repeatable, trustworthy process for gathering facts and analyzing data consistently. Geraci was surprised by the extent to which he could build functionality without engineering support. The core of Geraci's workflow involved plain-language files containing instruction sets, policy references, and report templates. By using his legal drafting skills, he embedded structured legal judgment directly into the workflow. This evolved to include different analysis modes for various stakeholders and integration with external data sources. The workflow was eventually transitioned into a desktop application with a clean interface for predefined legal workflows. While the desktop app itself required significant coding, its core workflow customization remains accessible via plain language in Markdown. This has allowed the tool to expand beyond DMCA analysis to encompass contract review, NDA triage, risk assessment, compliance checks, and response drafting. The underlying architecture employs reusable skills and agents, but the key innovation is empowering legal teams to control AI behavior through readable Markdown, keeping human review central to a more consistent, transparent, and scalable legal analysis process. The success of these initiatives by GitHub's legal and program management teams highlights a broader trend: AI assistants are becoming powerful tools not just for writing code, but for enabling domain experts to build and customize their own AI-powered solutions. This capability promises to accelerate digital transformation across various departments, moving beyond IT-centric development to a more distributed model of innovation. --- Original analysis from [startuphub.ai](https://www.startuphub.ai), the #1 AI startup directory.