{"id":134295,"date":"2025-10-02T15:29:07","date_gmt":"2025-10-02T23:29:07","guid":{"rendered":"https:\/\/xira.com\/p\/2025\/10\/02\/exclusive-altorney-launches-marc-gen-ai-powered-system-automates-first-pass-review-targeting-major-savings-in-e-discovery\/"},"modified":"2025-10-02T15:29:07","modified_gmt":"2025-10-02T23:29:07","slug":"exclusive-altorney-launches-marc-gen-ai-powered-system-automates-first-pass-review-targeting-major-savings-in-e-discovery","status":"publish","type":"post","link":"https:\/\/xira.com\/p\/2025\/10\/02\/exclusive-altorney-launches-marc-gen-ai-powered-system-automates-first-pass-review-targeting-major-savings-in-e-discovery\/","title":{"rendered":"Exclusive: Altorney Launches MARC; Gen AI-Powered System Automates First-Pass Review, Targeting Major Savings In E-Discovery"},"content":{"rendered":"

The post Exclusive: Altorney Launches MARC; Gen AI-Powered System Automates First-Pass Review, Targeting Major Savings In E-Discovery<\/a> appeared first on Above the Law<\/a>.<\/p>\n

The legal technology company Altorney<\/a> today announced the general availability of MARC, a generative AI-powered document review system designed to automate first-pass review decisions before documents enter traditional review platforms.<\/p>\n

After first announcing MARC<\/a> last March and going through a pilot period with corporate legal departments, the company is now releasing the product for general availability to corporate legal teams, litigation service providers and law firms.<\/p>\n

The Problem MARC Addresses<\/strong><\/h3>\n

The product tackles a core inefficiency in e-discovery workflows: organizations typically load entire document sets into expensive review platforms, only to cull large portions as non-responsive. Shimmy Messing<\/a>, Altorney\u2019s CEO and co-founder, says this approach creates unnecessary costs and security risks.<\/p>\n

\u201cIf you\u2019re loading your million documents into a review platform, as an example, and then immediately culling out 800,000 of them for not hitting keywords or not being part of TAR or whatever, you still have these 800,000 documents sitting there in your database that you\u2019re paying for and that are exposed from a risk factor after leaving your corporate environment,\u201d Messing said during a demonstration of the product for LawSites.<\/p>\n

MARC\u2019s approach is to automate the culling and initial review decisions before documents reach the review platform, ideally within the organization\u2019s own environment. This means only relevant documents \u2013 already tagged with first-pass decisions on issues like privilege, confidentiality and responsiveness \u2013 are loaded into expensive hosting platforms.<\/p>\n

How MARC Works<\/strong><\/h3>\n

MARC operates as a text analytics tool that sits between data collection and the review platform. The system is agnostic about which large language model (LLM) it uses. Organizations can deploy MARC with Altorney\u2019s provided Llama model installed locally, or integrate it with their preferred approved models, including those from Azure or OpenAI.<\/p>\n

MARC can operate entirely within an organization\u2019s firewall, with no data transmitted externally. \u201cAll the data can stay there,\u201d Messing said. \u201cNothing has to go out to OpenAI or Azure AI \u2013 it can all be contained in a local environment.\u201d<\/p>\n

This approach provides security while also reducing costs, as local LLMs avoid the per-token charges associated with cloud-based AI services.<\/p>\n

Rachi Messing<\/a>, Altorney\u2019s co-founder, said that installation typically requires just 30-40 minutes of IT time, after which the system is largely self-managing.<\/p>\n

Protocol Analysis, Not Prompt Engineering<\/strong><\/h3>\n

Among MARC\u2019s distinguishing features is its deliberate avoidance of requiring prompt engineering by users.<\/p>\n

Rather than requiring users to craft precise prompts \u2013 a skill Rachi Messing described as \u201creally hard to master\u201d and prone to inconsistency \u2013 MARC uses what it calls a \u201cprotocol analysis\u201d approach.<\/p>\n

\"\"<\/a><\/p>\n

Creating the MARC relevancy protocol from the background materials.<\/strong><\/p>\n<\/div>\n

With this approach, users upload background materials about a case into a folder. These materials might include complaints, subpoenas, counterclaims, pleadings, or even informal documents like an email from in-house counsel outlining a new matter or an HR complaint in an internal investigation.<\/p>\n

MARC then generates a comprehensive protocol document in Microsoft Word format. This protocol includes:<\/p>\n