Modern Legal Data Stack

Deploy grounded practice assistants, optimize workflows, and deliver premier legal services.

Thank you for joining Counsel Stack. Our team will reach out to discuss next steps.
Oops! Something went wrong while submitting the form.

Acquisition and Intake

We provide shared or exclusive leads for any practice area, and convert high value leads into clients.

Content and Compliance

We offer premier website design, SEO, digital advertising, and ADA Title III accessibility compliance services.

Research and Operations

We develop secure language model practice assistants, LPM integrations, and rule-based automations.

Legal Practice Assistants

LLM-Powered Assistants

We offer a unified platform for working with legal data and LLMs.

You control what data you import, analyze, and export. Total flexibility, all in one place.
A gavel on a black and gold background

Trusted Case Citations

Detect hallucinated citations before they happen to ensure reliable work product

LPM Integrations

Securely export your work product to practice management software like Clio, MyCase, Practice Panther, and more.

Legal Data Tools

Equip your practice assistant with search engines, website search, file read, citation check, and other tools,
lightning icon

Dynamic Workflows

Define and store tailored document review, assistant personas, custom tools, teams, workflows, and more.

Other Legal Services

The Productization of Legal Services

The legal industry is shifting towards productization. This trend began with quasi-legal services like business formation or tax filing, and continues to grow.

We help you build your own legal product.

The possibilities are endless. For example, we've automated client intake and qualification, engagement letter drafting, document assembly, contract redlining, interrogatories, pleadings, responsive pleadings, discovery requests, motions, and much more. Enter your email blow and we will reach out to discuss your vision.

Thank you for joining Counsel Stack. Our team will reach out to discuss next steps.
Oops! Something went wrong while submitting the form.

legal leads

Shared or exclusive leads, bulk discounts available, client intake reports

We source leads in-house and broker leads from the market to secure the most competitive pricing and quality. You tell us your practice area and whether you want shared or exclusive leads. We screen again for high quality leads and then integrate with your Counsel Stack practice assistant or external LPM software.
Thank you for joining Counsel Stack. Our team will reach out to discuss next steps.
Oops! Something went wrong while submitting the form.
Referral Network

Buy or sell referrals and track your payments

Legal referral markets are a great way to build relationships and grow your firm. We're a member of legal referral markets, allowing you to offer or accept referrals across the country. You can track referrals and ensure accurate payment.
Thank you for joining Counsel Stack. Our team will reach out to discuss next steps.
Oops! Something went wrong while submitting the form.
Web & marketing

Website Design, Content, SEO, and Compliance

If you don't have a site, we can make you one. If you already have a site, we offer content creation, SEO, and targeted advertising. We also help reduce the risk of lawsuits with WCAG and ADA Title III accessibility audits.
Thank you for joining Counsel Stack. Our team will reach out to discuss next steps.
Oops! Something went wrong while submitting the form.
LPM development

Augment Your LPM Software

Enhance your legal practice with private Clio apps, designed exclusively for your firm's needs. Integrate your practice assistants with Clio and export conversations directly to a specific client and matter.
Thank you for joining Counsel Stack. Our team will reach out to discuss next steps.
Oops! Something went wrong while submitting the form.

Custom Practice Assistants

Grounded Language Models for Law

Tell us your jurisdiction, practice area, and core workflows.

Request a Practice Assistant

Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.

Our Process

We work with young attorneys looking to start their own practice and law firms looking to expand into new practice areas.

Our process unfolds in four key stages, each mirroring a crucial phase of legal procedure.


First, we collaborate with your team to understand the unique needs of your practice area.

Think of it as filing the initial complaint or answer, but in this case, it's all about setting clear goals and expectations for your digital solutions.


In the discovery phase, we assess your firm's existing technology and workflows to determine exactly how Counsel Stack's grounded agents can add the most value to your team.


After we have a clear picture of your project requirements, we develop the grounded agents. We work with you to procure the right datasets and present various implementation options.

Then, we assemble and test the grounded agent internally. Counsel Stack's team of engineers, developers, and legal professionals, try to break your grounded agent before deployment. We call this process trial.


The legal process doesn't always end at trial, and neither does our commitment to you.

Once we deploy practice assistants to your organization, we help you refine them further with RLHF and other techniques. We also offer trainings and policy guidance. We call this the appeals process.
Attorneys and 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, 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.
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.
What risks should lawyers avoid when using language models?
Lawyers need to be cautious of hallucinations (false information) in outputs and ambiguous provenance (unclear sources) in training data. It's crucial to verify AI-generated information and be aware of the limitations of these models in legal contexts.
Why do hallucinations in language models occur, and how can they be addressed?
Hallucinations in language models occur not due to a lack of reasoning, but due to a lack of specific knowledge. These models might inaccurately recall or generate specific information. Addressing hallucinations involves explicit prompting against them, grounding the model with context, and verifying information with retrieved documents. This enhances the model's ability to reason over the knowledge it has access to.
What are the implications of hallucinations in language models like U.S. v. Cohen and Mata v. Avianca Inc. cases?
These cases illustrate the dangers of relying on language models without proper verification. In U.S. v. Cohen, AI-generated misinformation led to complications, while in Mata v. Avianca Inc., lawyers submitted non-existent judicial opinions. These examples underscore the need for careful review and human oversight in using language models in legal practice.
Can hallucinations in language model outputs be eliminated?
No. completely eliminating hallucinations in language model outputs is not currently possible. Language models are text prediction engines - they have to guess what the next word is. However, hallucinations can be significantly reduced through grounding, careful prompt design, and providing relevant context to language models. Check out the case law citation tool to learn more.
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 or redundant phrases. Adjusting these settings allows legal professionals to tailor the language model's responses, ensuring they are suitable for the specific requirements of brainstorming, legal research, drafting, or analysis.

How to Get in Touch