Hoag Law.ai

Tag: legal tech

  • KJedi: a local, open-source contract review tool for California AI-focused SaaS attorneys

    KJedi: a local, open-source contract review tool for California AI-focused SaaS attorneys

    Solo and small-firm attorneys have five real ways to use AI for client work. Each trades off privilege, convenience, and cost differently.

    The five options

    OptionPrivilege-safe?EffortCost (typical)
    Consumer chat (ChatGPT free/Pro, Claude.ai Pro)No — Consumer Terms include training opt-out and weaker retentionLowest$0–$20/month
    Commercial API + your own wrapperYes — Commercial Terms, no training, includes DPAHighest (you build it)~$100–500/month depending on volume
    Managed legal-AI SaaSYesLowest~$500/month and up
    AI-in-a-box applianceYes — data never leaves the deviceMedium (setup + hardware)~$500–700/month equivalent
    On-prem frontier model on your own hardwareYesHighest$10K+ hardware, ongoing setup
    Top-spec Mac Studio running local LLMsYes — data never leaves the deviceHigh (RAG setup, model selection, ongoing tuning~$10K up front, plus your time

    Consumer plans are cheap because they’re subsidized. The subsidy comes with terms of service that make those tiers inappropriate for privileged content.

    Every option that’s honest about privilege costs real money, because frontier intelligence at attorney-workload volume costs real money to deliver. The legitimate options cluster in roughly the same price band.

    One caveat worth naming about the local-hardware options: they run open-weights models — GPT-OSS, Gemma, Llama, Qwen, DeepSeek — rather than proprietary frontier models. As of 2026, that’s much less of a capability gap than it used to be; OpenAI’s GPT-OSS-120B and others are genuinely strong on reasoning benchmarks and run on a maxed Mac Studio. But for legal work specifically, the gap is unknown in any rigorous sense — there’s no public benchmark for “which model spots the most issues in a SaaS MSA” — and proprietary models still hold edges on coding, long-context, and agentic tasks. The right way to evaluate this for your practice is to actually try the same contract through both and see.

    So that leaves two practical paths for solos:

    (1) pay for a managed platform;

    (2) Build a thin wrapper around the commercial API.

    KJedi is the second option.

    What KJedi is

    KJedi is a small open-source Next.js web app that runs only on your laptop. Upload a contract (PDF or DOCX), chat with Claude (Opus 4.7 as of this writing) about the terms, generate a red/yellow/green review memo.

    • Localhost only. No hosted service. Outbound traffic goes to the Anthropic API only.
    • Your API key, server-side. Lives in .env.local. Never touches the browser.
    • Nothing persists. No database, no logs, no analytics. Document and chat history live in memory only and clear on tab close.
    • System prompt is yours. Plain TypeScript file at lib/system-prompt.ts. Read, edit, fork.

    What it’s tuned for

    California AI/SaaS tech-transactions:

    • AI-specific clauses (training data rights, output ownership, IP indemnity for AI outputs, model substitution, accuracy disclaimers, prompt/output confidentiality, upstream-model-provider disclosure)
    • Vendor agreements with AI components (OpenAI, Anthropic, AWS Bedrock, Google Vertex)
    • Privacy: CCPA/CPRA, GDPR, DPAs
    • IP assignments, contractor and employee IP/confidentiality, NDAs
    • Open-source compliance and AI training-data provenance

    Not tuned for other practice areas or litigation. KJedi flags when a contract is outside its lane. Fork the system prompt for your own practice areas.

    What it costs to run

    A typical contract review session (upload, several follow-up questions, generate memo) should run just a few dollars in API costs. Steady client volume could therefore cost a few hundred dollars per month. Comparable to the managed platforms, with the wrapper logic and system prompt in your control.

    Before using it on client work

    1. Verify your Anthropic account is on Commercial Terms, not Consumer Terms. API access via the console defaults to Commercial Terms once you add a payment method. Claude.ai Pro/Max is governed by Consumer Terms. Confirm in your Anthropic console.
    2. This is open-source experimental software, not a vetted vendor product. Read the code, audit the dependencies, verify the system prompt is adequate for your needs, and verify your own machine’s configuration.
    3. Verify every citation before relying on it. Treat the output as a junior associate’s first pass, never the final word, including in the system prompt.

    Setup Instructions

    Visit: github.com/marchoag/kjedi

    git clone https://github.com/marchoag/kjedi.git
cd kjedi
npm install
cp .env.example .env.local   # add your ANTHROPIC_API_KEY
npm run dev

    Open http://localhost:XXXX (default is usually 3000).

    Questions? Feel free to reach out.

  • Everything you need to know about California’s SB 574: The first state law to regulate AI in legal practice

    Everything you need to know about California’s SB 574: The first state law to regulate AI in legal practice

    This is educational material and does not constitute legal advice nor is any attorney/client relationship created with this article, hence you should contact and engage an attorney if you have any legal questions.

    If you’re a California attorney using generative AI — and at this point, who isn’t — you need to know about SB 574. Also, it’s inevitable that it will soon be ethical malpractice not to use AI in the practice of law, so what follows is essential knowledge.

    Introduced by Senate Judiciary Chair Tom Umberg (D-Santa Ana), SB 574 would create the first U.S. statute specifically governing how lawyers and arbitrators use generative AI.

    What SB 574 requires

    The bill creates three distinct regulatory tracks: one for attorneys, one for court filings, and one for arbitrators.

    Attorneys’ duties when using AI

    SB 574 would impose four statutory duties on any attorney using generative AI to practice law:

    Protect confidential data. Don’t feed confidential, personally identifying, or other nonpublic information into a public generative AI system. Note the qualifier — “public.” This is the bill drawing a line between consumer-facing tools (think free-tier ChatGPT) and enterprise-grade deployments with contractual data protections. The distinction matters; see below.

    Prevent discrimination. Ensure your use of AI doesn’t unlawfully discriminate against individuals or protected groups. This goes beyond what most attorneys probably think about when using AI for drafting or research, but consider: if you’re using AI to screen documents, evaluate claims, or prioritize case intake, bias in the model becomes your bias.

    Verify and correct. Take reasonable steps to verify the accuracy of any AI-generated material, correct hallucinated or misleading content, and remove biased or harmful output. “Reasonable steps” will inevitably be the subject of future litigation, but the intent is clear — you can’t blindly copy-paste.

    Consider disclosure. Consider whether your use of AI should be disclosed when producing content provided to the public. Note: this is a “consider” requirement, not a mandate. The bill leaves disclosure to professional judgment rather than imposing a blanket rule.

    Court filings and citation verification

    The bill would amend CCP § 128.7 — the sanctions statute — to make it explicitly unlawful for any court filing to contain a citation the attorney hasn’t personally read and verified, including citations provided by generative AI. This is therefore a direct response to the hallucination problem; SB 574 converts the formerly implicit “don’t do this” into a statutory prohibition with teeth: sanctions under the existing § 128.7 framework.

    For practitioners, this means building verification checkpoints into your workflow. If you’re using AI for legal research — and again, you probably are — the days of trusting the output without reading every cited case yourself are formally numbered.

    Arbitrator limits on AI

    This is the most forward-looking piece of the bill, and it arrives at an interesting moment.

    SB 574 would impose three constraints on arbitrators:

    No AI delegation. An arbitrator cannot delegate any part of their decision-making process to any generative AI tool.

    Record-only reliance. Arbitrators can’t rely on AI-generated information from outside the record without disclosing that use to all parties.

    Human responsibility. The arbitrator must assume full responsibility for the award regardless of any AI assistance.

    As a practical matter, if SB 574 passes in its current form, California-based arbitrations would effectively be unable to use the AAA-ICDR’s AI arbitrator product, at least without significant structural changes to ensure the human arbitrator retains genuine decision-making authority rather than rubber-stamping AI output.

    What SB 574 does NOT do

    A few important negatives worth flagging:

    It does not ban attorneys from using AI. This is regulation, not prohibition.

    It does not prescribe specific tools or require AI registration, audits, or approved-vendor lists.

    It does not create new criminal penalties. Enforcement is through existing mechanisms: court sanctions under § 128.7 and State Bar disciplinary proceedings. The bill doesn’t currently specify any enforcement mechanism for arbitrators, which is a gap worth watching.

    The bigger picture

    California has been on a regulatory tear: SB 53 (the Transparency in Frontier Artificial Intelligence Act, signed September 2025) established the first U.S. safety framework for frontier AI models. SB 243 regulates AI companion chatbots. AB 853 expands AI content disclosure requirements.

    SB 574 is the profession-specific layer on top of that broader regulatory stack. And if California’s pattern holds — see: CCPA becoming the de facto national privacy standard, vehicle emission rules setting the industry baseline — expect other states to follow with similar attorney AI regulations.

    These are exactly the kinds of issues I work on every day at Hoag Law.ai and as Chair of the Beverly Hills Bar Association’s AI and the Law Section, alongside Vice-Chair Amanda Harris. If you’re building AI products, navigating AI compliance, or just trying to figure out how to use these tools responsibly in your practice, let’s talk.