Referent

Product Hunt 08/26/26, 10:25 AM Products

legal-ai practice-management crm software law-firms ai-native productivity-tools

Summary

Referent is an AI-native legal practice management platform that combines AI, CRM, and workflow tools to help law firms streamline operations.

<p> The AI-native OS for modern law firms </p> <p> <a href="https://www.producthunt.com/products/referent?utm_campaign=producthunt-atom-posts-feed&utm_medium=rss-feed&utm_source=producthunt-atom-posts-feed">Discussion</a> | <a href="https://www.producthunt.com/r/p/1232856?app_id=339">Link</a> </p>

Original Article

View Cached Full Text

Cached at: 08/30/26, 07:59 AM

# Referent: Legal AI Agents Platform for Lawyers and Law Firms | Product Hunt Source: [https://www.producthunt.com/products/referent](https://www.producthunt.com/products/referent) Referent is AI\-native legal practice management software for lawyers and law firms\. It combines Legal AI, Legal CRM, client intake, matter management, documents, deadlines, email workflows, follow\-ups, and billing prep to help turn any law firm into an AI\-native law firm\.

Similar Articles

Re_gent

Product Hunt

Re_gent is a version control tool for tracking and managing AI agent activity.

Claude for Legal (GitHub Repo)

TLDR AI

Anthropic released an open-source GitHub repository featuring reference agents, skills, and data connectors for legal workflows, deployable via Claude Cowork, Claude Code, or the Managed Agents API with guardrails for attorney review.

Relaticle

Product Hunt

# Relaticle: Open-source CRM with approval-gated AI writes | Product Hunt Source: [https://www.producthunt.com/products/relaticle](https://www.producthunt.com/products/relaticle) Most CRMs bolt AI on\. Relaticle is built agent\-first: any MCP client gets 37 first\-party tools over OAuth, with workspace custom fields in each agent's schema automatically\. The in\-app assistant is stricter: every write is a proposal showing the exact change, approved record by record\. Self\-host everything under

Which Changes Matter? Towards Trustworthy Legal AI via Relevance-Sensitive Evaluation and Solver-Grounded Reasoning

arXiv cs.AI

This paper introduces a relevance-sensitive evaluation suite for legal AI, demonstrating that LLMs are overly sensitive to legally irrelevant perturbations, and proposes LexGuard, an adversarial multi-agent framework using formal reasoning to improve legal reasoning reliability.

Customizing models for legal professionals

OpenAI Blog

Harvey, a generative AI platform for legal professionals, partnered with OpenAI to create a custom-trained case law model that reduces hallucinations and improves reasoning for complex legal tasks like document drafting and contract analysis. The custom model, trained on 10 billion tokens of U.S. case law, achieved 97% lawyer preference over standard foundation models.