Close Menu
  • Home
  • AI Models
    • DeepSeek
    • xAI
    • OpenAI
    • Meta AI Llama
    • Google DeepMind
    • Amazon AWS AI
    • Microsoft AI
    • Anthropic (Claude)
    • NVIDIA AI
    • IBM WatsonX Granite 3.1
    • Adobe Sensi
    • Hugging Face
    • Alibaba Cloud (Qwen)
    • Baidu (ERNIE)
    • C3 AI
    • DataRobot
    • Mistral AI
    • Moonshot AI (Kimi)
    • Google Gemma
    • xAI
    • Stability AI
    • H20.ai
  • AI Research
    • Allen Institue for AI
    • arXiv AI
    • Berkeley AI Research
    • CMU AI
    • Google Research
    • Microsoft Research
    • Meta AI Research
    • OpenAI Research
    • Stanford HAI
    • MIT CSAIL
    • Harvard AI
  • AI Funding & Startups
    • AI Funding Database
    • CBInsights AI
    • Crunchbase AI
    • Data Robot Blog
    • TechCrunch AI
    • VentureBeat AI
    • The Information AI
    • Sifted AI
    • WIRED AI
    • Fortune AI
    • PitchBook
    • TechRepublic
    • SiliconANGLE – Big Data
    • MIT News
    • Data Robot Blog
  • Expert Insights & Videos
    • Google DeepMind
    • Lex Fridman
    • Matt Wolfe AI
    • Yannic Kilcher
    • Two Minute Papers
    • AI Explained
    • TheAIEdge
    • Matt Wolfe AI
    • The TechLead
    • Andrew Ng
    • OpenAI
  • Expert Blogs
    • François Chollet
    • Gary Marcus
    • IBM
    • Jack Clark
    • Jeremy Howard
    • Melanie Mitchell
    • Andrew Ng
    • Andrej Karpathy
    • Sebastian Ruder
    • Rachel Thomas
    • IBM
  • AI Policy & Ethics
    • ACLU AI
    • AI Now Institute
    • Center for AI Safety
    • EFF AI
    • European Commission AI
    • Partnership on AI
    • Stanford HAI Policy
    • Mozilla Foundation AI
    • Future of Life Institute
    • Center for AI Safety
    • World Economic Forum AI
  • AI Tools & Product Releases
    • AI Assistants
    • AI for Recruitment
    • AI Search
    • Coding Assistants
    • Customer Service AI
    • Image Generation
    • Video Generation
    • Writing Tools
    • AI for Recruitment
    • Voice/Audio Generation
  • Industry Applications
    • Finance AI
    • Healthcare AI
    • Legal AI
    • Manufacturing AI
    • Media & Entertainment
    • Transportation AI
    • Education AI
    • Retail AI
    • Agriculture AI
    • Energy AI
  • AI Art & Entertainment
    • AI Art News Blog
    • Artvy Blog » AI Art Blog
    • Weird Wonderful AI Art Blog
    • The Chainsaw » AI Art
    • Artvy Blog » AI Art Blog
What's Hot

Talent Intelligence and Strategy | Recruiting News Network

EU Commission: “AI Gigafactories” to strengthen Europe as a business location

United States, China, and United Kingdom Lead the Global AI Ranking According to Stanford HAI’s Global AI Vibrancy Tool

Facebook X (Twitter) Instagram
Advanced AI News
  • Home
  • AI Models
    • Adobe Sensi
    • Aleph Alpha
    • Alibaba Cloud (Qwen)
    • Amazon AWS AI
    • Anthropic (Claude)
    • Apple Core ML
    • Baidu (ERNIE)
    • ByteDance Doubao
    • C3 AI
    • Cohere
    • DataRobot
    • DeepSeek
  • AI Research & Breakthroughs
    • Allen Institue for AI
    • arXiv AI
    • Berkeley AI Research
    • CMU AI
    • Google Research
    • Meta AI Research
    • Microsoft Research
    • OpenAI Research
    • Stanford HAI
    • MIT CSAIL
    • Harvard AI
  • AI Funding & Startups
    • AI Funding Database
    • CBInsights AI
    • Crunchbase AI
    • Data Robot Blog
    • TechCrunch AI
    • VentureBeat AI
    • The Information AI
    • Sifted AI
    • WIRED AI
    • Fortune AI
    • PitchBook
    • TechRepublic
    • SiliconANGLE – Big Data
    • MIT News
    • Data Robot Blog
  • Expert Insights & Videos
    • Google DeepMind
    • Lex Fridman
    • Meta AI Llama
    • Yannic Kilcher
    • Two Minute Papers
    • AI Explained
    • TheAIEdge
    • Matt Wolfe AI
    • The TechLead
    • Andrew Ng
    • OpenAI
  • Expert Blogs
    • François Chollet
    • Gary Marcus
    • IBM
    • Jack Clark
    • Jeremy Howard
    • Melanie Mitchell
    • Andrew Ng
    • Andrej Karpathy
    • Sebastian Ruder
    • Rachel Thomas
    • IBM
  • AI Policy & Ethics
    • ACLU AI
    • AI Now Institute
    • Center for AI Safety
    • EFF AI
    • European Commission AI
    • Partnership on AI
    • Stanford HAI Policy
    • Mozilla Foundation AI
    • Future of Life Institute
    • Center for AI Safety
    • World Economic Forum AI
  • AI Tools & Product Releases
    • AI Assistants
    • AI for Recruitment
    • AI Search
    • Coding Assistants
    • Customer Service AI
    • Image Generation
    • Video Generation
    • Writing Tools
    • AI for Recruitment
    • Voice/Audio Generation
  • Industry Applications
    • Education AI
    • Energy AI
    • Finance AI
    • Healthcare AI
    • Legal AI
    • Media & Entertainment
    • Transportation AI
    • Manufacturing AI
    • Retail AI
    • Agriculture AI
  • AI Art & Entertainment
    • AI Art News Blog
    • Artvy Blog » AI Art Blog
    • Weird Wonderful AI Art Blog
    • The Chainsaw » AI Art
    • Artvy Blog » AI Art Blog
Advanced AI News
Home » Why It Makes Sense for Lawyers – Artificial Lawyer
Industry Applications

Why It Makes Sense for Lawyers – Artificial Lawyer

Advanced AI BotBy Advanced AI BotApril 28, 2025No Comments6 Mins Read
Share Facebook Twitter Pinterest Copy Link Telegram LinkedIn Tumblr Email
Share
Facebook Twitter LinkedIn Pinterest Email



By Antti Innanen.

Lawyers are famously allergic to buzzwords. So, when someone mentions ‘vibing’ with AI, red pens come out fast.

But Vibe Drafting, a term borrowed from AI researcher Andrej Karpathy’s vibe coding, offers more than a catchy label. It introduces a practical mental model for how lawyers can work with AI while keeping human expertise at the centre.

The Real Problem: Outdated Mental Models

Many lawyers treat AI like a glorified database or a search engine. They issue commands to the machine: ‘Fetch this, get that, search this.’ But this is not how AI works.

That kind of prompting leads to hallucinations, inconsistencies, and generic results.

As lawyers, we’re used to structured workflows and giving clear instructions to tools. But AI responds better to guidance than commands. A prompt like ‘Draft agreement X’ doesn’t give the tool much to work with.

AI thrives on clear direction, stylistic cues, and contextual nuance. Without those, it can’t determine key provisions or client-specific needs. These are judgment calls. And that’s where lawyers still matter.

What Vibe Drafting Actually Is

Vibe Drafting means guiding the AI with mood, tone, and reference. You describe how something should feel, not exactly how it should work. The AI then fills in the gaps.

Vibe Drafting isn’t about issuing one perfect prompt. Instead, you give the model small pieces of guidance and iterate the results. Think 100 light prompts instead of one heavy one.

You suggest something, see if it works, and either build on it or discard it. You stay in control, nudging the model and breaking the process into smaller, manageable steps.

At no point should you feel like you’ve outsourced your thinking to AI.

‘The parties are friendly. Keep the tone collaborative.’

‘This indemnity clause feels too aggressive for the situation.’

‘Do a readability check and remove jargon.’

‘Check that the cross-references work and the numbering is correct.’

You’re not commanding the machine. You’re in a dialogue with it. The workflow becomes a genuine partnership.

That said, vibing usually needs structure. Without it, you fall into the ’almost ready’ trap, endlessly tweaking and never shipping.

You might try something like this:

Plan the document with the help of AI

Provide contextual grounding from reliable sources

Create the first version

Refine section by section with focused prompts

Test for usability and readability

Switch AI tools or modes to refine the draft

Do a good, old-fashioned human review

It’s not a rigid formula. You can come up with your own. But a little structure helps you avoid getting stuck in the loop.

This kind of work is closer to sculpting or composing music than searching a database. Little by little, you shape the result you want. And the method keeps you engaged in the thinking process, not removed from it.

(Check out the video/post below to see how Vibe Drafting actually works.)

Produced by Antti Innanen, 2025.

Why It Works So Well

So, what’s the theory behind Vibe Drafting?

Language models map patterns from billions of examples. Your iterative, specific prompts guide the model toward the right ones. Each adjustment helps it better understand your intent. It’s a feedback loop that builds clarity and precision.

This works because of how large language models function. They operate in a massive latent space, a kind of conceptual map built from language patterns. When your prompt carries tone, reference, or stylistic intent, you are pointing the model toward a region of that space. It fills in the direction with plausible, relevant content.

AI doesn’t just follow instructions. It infers meaning. It works with ambiguity, incomplete inputs, and stylistic intent. Most importantly, it mirrors how humans already communicate:  through impressions, mood, and story.

That’s why Vibe Drafting feels natural. And that’s why it works.

More Responsible Than One-Shot Prompting

One common criticism of AI is that it makes us dumber. That we outsource too much of our thinking and lose touch with our skills.

Despite the dumb name, Vibe Drafting is the opposite of that.

This method keeps you involved. You stay on top of the work. You never lose sight of what’s happening. You catch issues early, before they become embedded in a draft.

You’re not feeding prompts into a black box and hoping for the best. You’re shaping, adjusting, and guiding at every step. And if it doesn’t work, you go back, refine, and try again.

You’re not outsourcing your thinking.

Not Everything Needs to Be Vibed

If you’re on your fifteenth identical NDA this month, use the template. Vibe Drafting is most valuable when a document needs customization and nuance.

Legal fundamentals still matter. Your understanding of law and business gives you the judgment to guide the AI. Vibe Drafting supports expertise. It doesn’t magically turn unskilled lawyers into great ones. You still need to know what good looks like.

The Future of Legal Drafting

Vibe Drafting blurs the line between thinking and doing. You think out loud and the model keeps up.

And yes, the term ’vibe’ probably won’t last. Next year, it might sound as dated as NFTs or the metaverse. But this way of working with AI is here to stay.

If the term makes partners uneasy or juniors cringe, rename it. Iterative prompting or structured collaboration works just as well. The name is flexible. The mindset shift is what matters.

And that shift is already underway. The first lawyers to adopt this approach won’t just save time. They’ll redefine expectations, cut costs, and lead the market, while others are still debating whether AI belongs in legal work at all.

—-

About the Author: Antti Innanen is a tech lawyer, legal design enthusiast, and an AI geek. His book ’Prompted: How to Create and Communicate with AI’ will be published by Routledge in 2025.

You can find more about Antti and his work here: Dot Legal: www.dot.legal and Legal Design School: www.legaldesignschool.com

—

Legal Innovators California Conference, San Francisco, June 11 + 12

If you’re interested in the cutting edge of legal AI and innovation, then come along to Legal Innovators California, in San Francisco, June 11 and 12, where speakers from the leading law firms, inhouse teams, and tech companies will be sharing their insights and experiences as to what is really happening and where we are all heading.

We already have an incredible roster of companies to hear from. This includes: Legora, Harvey, StructureFlow, Ivo, Flatiron Law Group, PointOne, Centari, eBrevia, Legatics, Knowable, Draftwise, newcode.AI, Riskaway, SimpleClosure and more.

See you all there!

More information and tickets here.



Source link

Follow on Google News Follow on Flipboard
Share. Facebook Twitter Pinterest LinkedIn Tumblr Email Copy Link
Previous ArticleBetter AI Stock: BigBear.ai vs. C3.ai
Next Article Google Used Search Signals & Data To Train Gemini AI Models
Advanced AI Bot
  • Website

Related Posts

Sweden blocks Tesla FSD-style testing in Stockholm

June 16, 2025

Meta buys stake in Scale AI, raising antitrust concerns

June 16, 2025

Tesla features used to flunk 16-year-old’s driver license test

June 16, 2025
Leave A Reply Cancel Reply

Latest Posts

Archaeologists Discover 75 Ancient Tombs in China

WCS Gala Honors Samper, Raising $2.5 Million

Grand Egyptian Museum Delays Grand Opening Again

Leonard Lauder, the cosmetics heir and billionaire art collector, dies

Latest Posts

Talent Intelligence and Strategy | Recruiting News Network

June 16, 2025

EU Commission: “AI Gigafactories” to strengthen Europe as a business location

June 16, 2025

United States, China, and United Kingdom Lead the Global AI Ranking According to Stanford HAI’s Global AI Vibrancy Tool

June 16, 2025

Subscribe to News

Subscribe to our newsletter and never miss our latest news

Subscribe my Newsletter for New Posts & tips Let's stay updated!

Welcome to Advanced AI News—your ultimate destination for the latest advancements, insights, and breakthroughs in artificial intelligence.

At Advanced AI News, we are passionate about keeping you informed on the cutting edge of AI technology, from groundbreaking research to emerging startups, expert insights, and real-world applications. Our mission is to deliver high-quality, up-to-date, and insightful content that empowers AI enthusiasts, professionals, and businesses to stay ahead in this fast-evolving field.

Subscribe to Updates

Subscribe to our newsletter and never miss our latest news

Subscribe my Newsletter for New Posts & tips Let's stay updated!

YouTube LinkedIn
  • Home
  • About Us
  • Advertise With Us
  • Contact Us
  • DMCA
  • Privacy Policy
  • Terms & Conditions
© 2025 advancedainews. Designed by advancedainews.

Type above and press Enter to search. Press Esc to cancel.