Sid Probstein

I just recorded a brief video overview of SWIRL AI Legal Search! youtube.com/watch?v=TQthJN… If you're in a law firm and trying to speed through internal data with AI, this is for you. In the video, I cover: • Why SWIRL helps firms get answers from internal systems ... fast • How SWIRL runs privately (not hosted) and does not require ingestion, indexing, copying, or data curation • How users log in with existing credentials (Microsoft, Ping Federate, etc.) • How to search across multiple systems and slice through the results • How AI generates insights grounded in the retrieved documents • How every insight can be verified via deeplinks to the exact source document and contributing text No black box. No data duplication. No mystery answers. Please take a look. I’d genuinely appreciate feedback. Thank you.

Bags at Crystal Ballroom wow

Early ideas about immortality have focused on uploading to some cloud or silicon existence, and perhaps someday, we will model in silicon or some other substrate the ability to transfer or sustain consciousness in a way that feels continuous and real. But something quieter, and arguably more immediate, is already happening. By using ChatGPT, just that, we fill its memory with our interests, desires, hopes, dreams etc, and in doing so we create a living record of how we think, how we respond, what we value, and how we make sense of the world around us. This is not speculative. This is not decades away. This is now. Someday we will pass, but it is no stretch of the imagination whatsoever to know that our relatives, friends and colleagues will be able to interact with those things, not as static artifacts like letters or photos, but as something dynamic that can respond, reflect, and extend the patterns we left behind. It is a form of immortality. Not the hard problem of consciousness solved. Not a literal continuation of self. But something that captures voice, intent, and perspective in a way that persists beyond biology. For most of human history, what we left behind was fixed. Books. Recordings. Memories in other people’s minds. Now what we leave behind can answer back. It will not be us… but it will not be nothing, either. Our agentic future selves may posthumously promote causes we cared about, explain actions others found bewildering, even apologize… search for long-lost people… or perhaps endlessly retcon our lives. It is immortality of a sort.

Students who took notes by hand scored ~28% higher on conceptual questions than laptop note-takers. Writing forces your brain to process and compress ideas instead of copying them.

Law firms are not resistant to AI. They are resistant to uncontrolled risk. Large language models introduce extraordinary capability... but also legitimate concern about data leakage, retention ambiguity, and regulatory exposure. SWIRL acts as a governed retrieval layer between enterprise content and external AI models. It performs permission-aware search using existing credentials. It retrieves only relevant content. It sends only authorized material to the model. There is no bulk export of the firm’s documents, curated information, know-how, law libraries or information services. No uncontrolled indexing pipeline. No shadow content lake created in the name of innovation. This allows firms to experiment with generative AI while maintaining governance discipline. Adoption accelerates when compliance teams are comfortable. AI transformation begins with trust.

The Biggest AI Risk Isn’t Adoption. It’s *Duplication*!! Managing Partners are being told to “move fast on AI.” What no one is saying clearly enough is this: most AI architectures duplicate your firm’s most sensitive data. Vector databases. Shadow indexes. Secondary content stores. Every duplication is a governance event. Every governance event is liability. If privileged material is copied into parallel systems, you now have two discovery surfaces. Two retention questions. Two breach scenarios. SWIRL doesn’t duplicate your content. It searches in place. It respects native permissions. It avoids creating a second universe of sensitive information. Speed is exciting. Risk is expensive. Your AI strategy should not quietly multiply exposure.

Someone builds a project management tool with Claude Code over a weekend. Ships it. Tweets "just replaced Jira." The app works. One user, happy path, localhost. Then two people edit the same record simultaneously, and the data is silently corrupted. They don't know what an optimistic lock is. They never needed to before. The prototype is maybe 1% of what makes software actually work. The other 99% is what you find after real users show up: race conditions, failed transactions, sessions expiring at the wrong moment, a payment webhook that fires twice and charges someone double. AI didn't cover any of that. It built exactly what you asked for. And the confidence is the worst part. "Just need to adjust a few things before we go live." The few things you need to adjust are the product. That's like laying a foundation and telling people you basically built the house. Vibe coding works. For personal tools, throwaway scripts, and prototypes you'll never put in front of paying users, it's genuinely fast and good enough. I use it. But there's a hard ceiling, and it shows up the moment the stakes get real. Agentic engineering is a different discipline. You're not prompting for code. You're decomposing problems, designing system boundaries, writing specs precise enough that the agent doesn't go sideways. You review everything it builds, because it will make mistakes that only look wrong if you know what correct looks like. You guide it. You catch what it misses. If you don't know what a distributed transaction is, the agent won't save you. It'll generate something broken with complete confidence, and you won't know until production. The hard part of software was never writing the first 200 lines. It never was.

SWIRL @SWIRL_SEARCH is honored to be listed in the @KMWorld 100 Companies that Matter in KM for the third year in a row!! 🏅🙏 #AI #KM #Legal kmworld.com/Articles/Edito…

Throwdown Brown ALERT 🚨

SWIRL is honored to be named to the @KMWorld 100 Companies that Matter in Knowledge Management for the third year in a row!! 🙏 kmworld.com/Articles/Edito…

By the end of last year, over 50% of GenAI projects were abandoned after the proof-of-concept stage. The main reasons? ➡️ Poor data quality ➡️ Insufficient risk controls ➡️ Rising costs ➡️ Unclear business value Gartner analyzed hundreds of GenAI implementations and identified the top culprits behind project abandonment. Find out more: gtnr.it/4rEnco4 #GenAI #ArtificialIntelligence #ProjectManagement

Founders: the real lesson from the SVB collapse three years ago wasn’t “diversify your bank.” It was this: find out now -- in good times -- whether your investor will wire money with no strings when everything breaks. Most won’t. That answer will matter more than any term sheet. khoslaventures.com/posts/march-10…

Bam Adebayo attempted 43 free throws Tuesday. The last time the Boston Celtics TEAM shot so many free throws in a game was 10 years ago.

Most conversations about AI in the legal industry focus on models. Which one writes better. Which one summarizes faster. Which one drafts the cleanest memo. But that misses the real shift. The real change is not the model. It's the workflow. For decades, legal work has been built around information scarcity. Lawyers knew where things lived. Case law databases. Document management systems. Matter files. Email. Internal precedent libraries. Each system held part of the answer. No single system held all of it. Today, AI can write impressive text. But it still struggles with something far more important: finding the right information across all those systems. If the AI cannot see the key document in your own repository, its answer may sound confident but still be wrong. That is why retrieval is becoming the real battleground in legal AI. The firms that succeed will not be the ones running the most AI pilots. They will be the ones that allow AI to search, securely and in real time, across the systems where their knowledge already lives. When that happens, the role of the lawyer shifts. The AI gathers information from across the firm’s knowledge universe. The lawyer interprets, challenges, and decides. But there is another twist: every question lawyers ask these systems becomes data. Patterns emerge. What lawyers research. What clauses appear in deals. What risks keep coming up across matters. In other words, AI systems are not just answering questions. They are learning from them. Which raises an interesting thought for the legal profession. If AI is watching how lawyers search, research, and reason… who is paying attention to who??

Every law firm contains decades of accumulated expertise... briefs that shaped case law, contracts structured with precision, internal analyses that captured hard-earned insight. Yet much of that knowledge becomes buried over time. Partners retire. Associates leave. Practice groups evolve. File systems expand. The intellectual capital remains, but it becomes harder to retrieve in context. SWIRL restores access to that institutional memory. Through federated search and semantic re-ranking, it surfaces prior work not just by keyword match, but by meaning and intent. That means a junior associate preparing for a motion can discover prior winning arguments. A deal team can identify language used in similar negotiations years earlier. Strategic insight becomes reusable rather than lost. This is not archival convenience. Memory preserves competitive advantage.

The evolution of computers [1940-2100] 🤯

The legal industry is moving fast into the AI layer. Westlaw has AI. Lexis+ has AI. Each platform is evolving from a research database into an assistant that answers questions, synthesizes cases, and drafts language with confidence. That progress is real. But here is one thing we can be sure of: Lexis+ is not going to answer questions about Westlaw’s corpus, and Westlaw is not going to answer questions about Lexis’ corpus. They are separate ecosystems with separate content rights, ranking systems, and product strategies. Now assume something more ambitious. Assume both platforms can integrate with your document management system. Assume they can see your briefs, prior matters, and internal knowledge assets. Does that solve the structural problem? No. Because the issue is not access. It is judgment. Even if both systems can see the same internal content, they remain independent intelligence engines. Each has its own retrieval logic, ranking philosophy, and tuning decisions about what constitutes relevance and authority. Ask the same question in both systems and you may receive two polished, well-structured answers that emphasize different cases and reasoning paths. At that point, the lawyer becomes the reranker again ... only now comparing AI-generated answers instead of document lists. We are recreating the federated search problem at the reasoning layer. The next step is AI federation. Not replacing vendor AI, but orchestrating across it. A query is interpreted once, retrieval happens across systems, and results are evaluated in a shared context so that everything competes on the same relevance scale. Judgment happens above the silos instead of inside them. In a world with two dominant legal research platforms, each with powerful AI, you are going to need one AI to work with them all. We solved federated retrieval. The next challenge is federated reasoning. In legal practice, that won’t be a feature. It will be infrastructure.

Legal research should not start with a scavenger hunt. Today SWIRL added support for two major public legal archives: 🇬🇧 The National Archives Caselaw (UK) 🇺🇸 CourtListener (US) Now SWIRL can search and re-rank results across these sources alongside the rest of your enterprise knowledge, with optional AI insight generation using your choice of LLM. No new index. No copying the data. Just connect and search. For lawyers, researchers, and compliance teams, this means faster access to precedent across jurisdictions. The screenshot below shows SWIRL in action on these sources looking for "snail in a bottle negligence" ... ping me for a live demo anytime!!

Modern AI systems get most of the attention today. But one of the most important ideas behind modern search came from a paper written more than fifty years ago. Karen Spärck Jones introduced a simple but profound insight in 1972: the importance of a word depends on how rare it is across documents. She described it this way: “The specificity of a term can be quantified as an inverse function of the number of documents in which it occurs.” That idea became Inverse Document Frequency (IDF). In practice, it means something very intuitive... common words carry little meaning. Rare words carry much more. When a search system ranks documents, terms that appear everywhere should matter less than terms that appear only in a few places. IDF captures that principle mathematically. From that insight came TF-IDF, one of the foundational ranking methods in information retrieval. Later models such as BM25 refined the approach, but the core idea remains the same. Even today, many systems, from enterprise search platforms to modern retrieval pipelines that support AI applications, still rely on variations of this concept. The machinery under the hood. Karen Spärck Jones helped explain which information actually matters when we search. Her work shaped how computers retrieve knowledge from large collections of documents ... something that professionals in fields like law rely on every day. In an era focused on AI breakthroughs, it is worth remembering that some of the most durable ideas in computing come from elegant insights developed decades ago. Inverse Document Frequency is one of them. en.wikipedia.org/wiki/Karen_Sp%…

cant stop smiling