About Counsel Stack

Empowering the next generation of legal professionals

Counsel Stack is a legal research platform born from necessity. We built our first prototype to study for the bar exam and the prototype evolved into something bigger.

Our Story

We are venture-backed and based in Pittsburgh. Our team combines licensed attorneys, law students, senior software engineers, and technical advisors from leading institutions. We spent our first year in the field learning how lawyers actually use legal technology. In our second year, we obtained SOC 2 compliance and are actively partnering with forward-thinking law firms to develop our research and document review capabilities.

Why Now

Language models present a unique opportunity for legal professionals. We are positioned to make the most of this technology for several key reasons.

(1) Lawyers are society's most highly trained readers and writers. This means we're particularly skilled at instructive delegation and critical analysis. By this logic, we can and should be power users of language models.
‍
(2) People need human connection during stressful times. Legal issues create stress. In response, people seek advocates they trust and fiduciaries bound to represent their best interests. While we can benefit from using language models for research and administration, lawyers' core service is, and always has been, human support.

(3) There's an argument that language models could substantially increase, not decrease, the demand for legal services. Language models will exacerbate existing legal issues and create new ones. They'll also help nonlawyers issue spot and understand when they might have recourse. Informed clients are much easier to work with. This will shift the practice of law legal in a positive direction.

Counsel Stack is designed with this sort of future in mind.

Learn More Sign Up

Legal AI

Frequently asked questions

Common questions about language models in legal practice

Why should lawyers care about language models?

Lawyers should be interested in language models because they offer significant advantages in legal research, align with ABA guidance on maintaining competence, and enhance cost efficiency. These models can automate and streamline many routine tasks, freeing lawyers to focus on more complex aspects of their cases.

What is the ABA's stance on AI and legal practice?

The ABA has adopted resolutions 604, 608, 609, and 610 emphasizing responsible AI development and use, promoting ethical, transparent, and accountable deployment of AI in the legal sector. These resolutions also focus on enhanced cybersecurity, guidelines for organizations engaging in AI, and integrating cybersecurity education into law school curricula.

Must I disclose my use of Counsel Stack to clients or courts?

We recommend attorneys using our platform follow the rules of professional conduct, standing orders, and other laws or regulations that govern the profession in their respective jurisdiction and practice area. But as a software company we aren't in a position to prescribe legal advice or a specific course of action. Some jurisdictions require that sort of disclosure, others don't.

How do large language models work?

Language models are next word predictors. Large language models like GPT-4, Llama 2, and Mistral utilize training data, attention, and transformers. These mechanisms help the model capture nuanced semantic relationships between words and sentences, enabling them to generate coherent text.

How can litigators benefit from using language models?

Litigators can benefit significantly from language models by leveraging them for efficient legal research, strategic development, jury analysis, and enhancing overall litigation planning. These tools can streamline various aspects of legal practice, making processes more efficient and data-driven.

How do language models increase capital efficiency in legal practice?

Properly developed language models enhance capital efficiency in legal practice by accelerating tasks and making sophisticated legal analysis more accessible. This is particularly beneficial for less experienced practitioners, leveling the playing field in terms of resource availability and expertise.

How can response quality be improved when using language models in legal contexts?

Enhancing response quality with language models in legal contexts involves prompt engineering and grounding techniques, which provide the language model with necessary contextual information. This approach ensures clear, context-aware, and accurate language model responses, effectively utilizing the model's reasoning capabilities over the provided knowledge.

What is prompt engineering in the context of language models and law?

Prompt engineering involves designing specific queries or instructions to guide AI models towards generating more accurate and contextually appropriate responses. It's a critical skill for legal professionals using AI, ensuring that the technology aligns with the specific needs and nuances of legal cases.

What are some basic prompting techniques to improve response quality in language models

A few basic techniques to improve response quality in language models include (1) specifying clear task formats and tone, (2) encouraging step-by-step thinking through a chain of thought approach, and (3) persona prompting. These techniques help in eliciting more precise and relevant responses.

What is "grounding" a language model?

Grounding a language model is connecting it to a reliable datasource. Grounding with Retrieval Augmented Generation (RAG) helps mitigate hallucinations while enhancing the model's accuracy. This process involves providing the language model with a rich context or specific information to base its responses on, leading to more accurate and reliable outputs.

What are hyper parameters in language models, and how do they change outputs?

Hyperparameters in language models, such as temperature, token window, and penalties, significantly influence the model's outputs. The temperature setting affects the creativity or randomness of the response, the token window determines the scope of the output, and penalties help prevent repetitive phrases or redundant content. Adjusting these settings allows you to tailor the language model's responses, ensuring they are suitable for the specific requirements of brainstorming, legal research, drafting, or analysis.

Empowering the next generation of legal professionals

Our Story

Why Now

Frequently asked questions

Contact Us