The core difference is data and design. ChatGPT and other legal AI tools work from the same public internet everyone has access to and are built as chatbots. OurFirm.ai is built on a proprietary dataset, thousands of judicial opinions, transcripts, docket entries, and behavioral signals extracted from cases across the United States. That data is what lets us tell you not just what the law says, but how your specific judge has actually ruled on your specific issue, how opposing counsel argues, and where the strategic leverage is. To match that data advantage, we have built a state-of-the-art agentic system that mirrors the functional depth of a full-service litigation firm. The data is the moat. The way it's delivered is a moat. The outcomes are a moat.

Our Legal Assistant is OurFirm.ai's agentic drafting and research engine, built on a swarm architecture where multiple specialized sub-agents handle research, drafting, citation verification, and formatting in parallel. You upload your case file, transcripts, exhibits, prior orders, client materials, instruct it what you need, and it retrieves the relevant context from your materials, applies jurisdiction-specific formatting and citation rules, and produces a complete, file-ready draft. The result is faster output and higher accuracy than any single-model approach.

Every system message, prompt, and workflow was engineered by a practicing trial attorney, not just a prompt engineer, and tested in live litigation before release.

OurFirm.ai supports federal and state courts across the country. Our data is updated daily.

Our PACER database is semantically searchable and updated daily. We are going state by state to provide full docket access as well, New York is complete, with California, Florida, Texas, and Illinois in the pipeline and national expansion underway.

For the majority of litigation research tasks, yes. OurFirm.ai retrieves controlling and persuasive authority faster and with higher relevance than legacy platforms. It surfaces case holdings, posture, and must-cite passages, not just a list of cases to read.

We also offer semantic docket search across NYSCEF and PACER, letting you search by fact pattern, argument type, judge, or attorney, something Westlaw and Lexis cannot do.

That said, we don't prevent you from using other tools. Many attorneys use OurFirm.ai to handle 80-90% of their research and drafting workflow, and supplement with other platforms for specific needs.

OurFirm.ai covers the full litigation document stack, including:

• Motions (MTD, MSJ, MIL, to compel, to suppress, omnibus, OTSC)
• Oppositions and replies
• Discovery demands and responses
• Sentencing memoranda and bail applications
• Mediation statements and settlement agreements
• Exhibit lists and trial preparation materials
• Trial openings and closings
• Direct and cross-examination outlines
• Letters and correspondence
• Stipulations and notices
• Appellate briefs

The platform currently includes thousands of jurisdiction-specific litigation templates. Five minutes from prompt to complete draft is our average.

Check My Cites is our multi-step citation verification pipeline. Every citation generated by our Legal Assistant, or submitted manually, runs through the following steps:

• Extraction: All citations are identified and parsed from the document, including embedded parenthetical citations
• Treatment Check: Each citation is checked for current validity and negative treatment (Shepardization equivalent)
• Quote verification: Quoted language is confirmed against the actual opinion text
• Pin cite confirmation: Pin cites are verified against the correct page of the opinion
• Proposition analysis: The proposition for which each case is cited is checked against the holding

You receive a verification report alongside your draft, red-flagging any citation that could not be confirmed. Zero hallucinated citations have been filed by OurFirm.ai users.

Yes, this is the core use case. Upload your case file: transcripts, prior orders, exhibits, depositions, contracts, medical records, or any other materials. Our Legal Assistant retrieves the relevant context from your documents and grounds every draft in your actual record.

Every factual assertion in a generated draft is backed by an in-text citation to the underlying source document, transcript page, exhibit number, or case record. You can click any citation footnote to instantly review the original source material. OurFirm.ai does not generate facts. It drafts from what is in your case file.

Yes. Upload a deposition, trial transcript, hearing transcript, or any other record, and OurFirm.ai will digest it automatically, summarizing testimony, identifying contradictions, flagging key admissions, and outputting ready-to-use cross-examination or impeachment points with precise transcript citations.

OurFirm.ai has built behavioral profiles on federal judges by processing thousands of opinions, transcripts, hearing recordings, and docket entries through a proprietary data extraction architecture drawing on hundreds of behavioral signals from decades of real courtroom data.

These profiles surface the things that actually matter in litigation: MSJ grant rates, oral argument frequency, motion-to-compel outcomes, preferred citation style, footnote tolerance, average decision time, and how the judge responds to specific argument types, derived from actual docket data, not surveys or summaries.

The result is that you know, before you file, how your judge has historically ruled on your exact issue, and you can tailor your brief accordingly.

Judge AI is an upcoming feature, currently in beta, that creates interactive behavioral AI profiles of judges trained on their actual transcript and opinion data. You can use Judge AI to test your arguments, forecast judicial reactions, anticipate bench questions, and stress-test your theory of the case before entering the courtroom.

The first Judge AI profiles are being built on SDNY judges, beginning with judges who have extensive transcript records. Beta access is available for select enterprise clients.

Judicial profiles are updated on a continuous basis as new opinions, orders, and docket entries are published. We do not rely on static snapshots. The behavioral analytics layer is live and pulls from every new decision that is filed.

Yes. OurFirm.ai is built on enterprise-grade infrastructure with the following protections:

• Encryption: TLS 1.3 in transit, AES-256 at rest
• Isolated storage: Per-firm, per-attorney, and per-conversation isolation and storage, your data is never co-mingled with another firm's
• No training on client data: Your documents are never used to train any AI model, ever
• Compute: AWS EKS (Kubernetes, multi-AZ) with 99.9% SLA and multi-region failover
• Access controls: Role-based permissions with full audit logging
• Deletion: 24-hour data purge on request, fully auditable

SOC 2 Type II certification is underway.

OurFirm.ai was architecturally designed with privilege in mind, and specifically post-Heppner v. United States (Feb. 2026), the first federal ruling to address attorney-client privilege in the context of AI-assisted legal work.

Key protections include: a privilege-protected client portal that keeps client communications within the attorney's controlled environment; BAAs executed with both Anthropic and OpenAI prohibiting model training on your data; per-firm isolated data pipelines; and zero data retention beyond session for AI inference calls. Client data never enters the AI provider's training pipeline, this is contractually enforced, not just policy.

Our MSA and DPA are available for review. We accept custom redlines from enterprise clients.

Yes. We support HIPAA-aligned workflows for clients who handle protected health information. Our Business Associate Agreement (BAA) is HIPAA-aligned, and we have executed BAAs with our AI subprocessors. Our DPA and subprocessor list are available on request. Contact us to discuss your firm's specific compliance requirements.

We provide a full enterprise security package on request, including:

• Master Service Agreement (custom redlines accepted)
• Data Processing Agreement (GDPR/CCPA-aligned)
• Business Associate Agreement (HIPAA-aligned)
• SOC 2 Type I Report (under NDA)
• Subprocessor List
• Penetration Test Summary

We are available to speak directly with your GC, IT security team, or malpractice carrier. Contact andrew@ourfirm.ai to schedule.

Yes. We offer a two-week pilot program with 10-20 seats for your team under a simple evaluation license, no commitment required. The pilot runs on real cases, not demo data, so you can measure the actual impact on your workflow before making any decision.

OurFirm.ai offers two tiers:

• Professional: $150/month base plus usage, structured to be billable directly to clients as a disbursement
• Enterprise: Custom pricing for firms requiring volume licensing, dedicated infrastructure, or custom MSA terms. API access coming in the near future.

Usage costs are designed to be passed through to clients as a line item, just as you would bill for Westlaw or Lexis research time. Pricing scales with the size of your practice and your adoption goals.

Immediately. Solo practitioners and pilot teams can get started through our touchless onboarding process, no calls, no setup delays. Enterprise clients requiring custom MSA terms, dedicated infrastructure, or security review are typically onboarded within 24 hours of contract execution.

Integrations with iManage, Sharepoint, Dropbox, and Box are live and others are on the short-term roadmap. Case materials can also be uploaded directly to the platform via a secure file upload interface.

...a few weeks away.

OurFirm.ai was founded by Andrew Mancilla, a trial attorney with 15 years of experience admitted in New York, New Jersey, California, and federal courts, with a practice spanning criminal, civil, and appellate litigation. Every feature, prompt, and workflow on this platform was designed by someone who has used it in a live courtroom, not just a product team.