In “The 80/20 Principle,” Ernie Svenson demystifies technology and introduces tools that improve your workday. This time, how a simple curated chatbot solves your law firm’s knowledge problem.
Table of contents
- Your Law Firm’s Knowledge Problem
- Every Law Firm’s Worst Knowledge Problem
- What a Curated Chatbot Is (and Why RAG Matters)
- How This Flips the Script for Small Firms
- How to Start Small: NotebookLM as Training Wheels
- The Bottom Line on Your Law Firm’s Knowledge Problem
- More From Ernie Svenson and the 80/20 Principle
Your Law Firm’s Knowledge Problem
Every law firm has a knowledge problem, even if nobody calls it that.
Precedent briefs sit in a folder on somebody’s laptop. The client intake FAQ lives in an old Word doc. Half of what your firm knows — how you handle a discovery dispute, what you tell a new client about billing, which judge hates late filings — lives in people’s heads or buried email threads.
Big firms have poured money into fixing this for two decades. SharePoint sites. Intranets. Dedicated KM teams. The results have been disappointing. Solos and small firms mostly gave up before they started.
That’s starting to change. And the change doesn’t require a KM team or a big budget.
Every Law Firm’s Worst Knowledge Problem
Think about what your firm knows:
- Client intake scripts and FAQs
- Template pleadings you’ve filed hundreds of times
- Training notes for new staff
- Onboarding docs for new clients
- Notes on local rules and judge preferences
- Prior research memos on recurring legal questions
All of it exists somewhere. Almost none of it is easy to find.
When a new paralegal starts, she asks the same 10 questions the last paralegal asked. When a client calls with a routine question, the associate pokes around in three folders before giving up and asking you.
This isn’t a document problem. It’s a retrieval problem.
What a Curated Chatbot Is (and Why RAG Matters)
A curated chatbot isn’t ChatGPT. It’s a chatbot that answers questions only from content you give it — your firm manual, FAQs, workflow notes, intake scripts, prior memos, whatever you feed it.
The mechanism behind a curated chatbot has a name: RAG. It stands for Retrieval-Augmented Generation. The idea is simple. When someone asks a question, the bot first retrieves the most relevant passages from your documents, then uses those passages to generate an answer. No open-internet guessing. The answer is grounded in your material, and a good RAG bot cites the source so you can see where the answer came from.
Think of it as an always-on assistant that has read every document in your firm and remembers all of it.
Here’s a working example.
I run a community called The Inner Circle, hosted on a platform called Circle. Circle recently added an AI chatbot trained only on our community’s content — courses, recordings, posts, PDFs, discussions—two years of material.
Members use it constantly. Here are real questions they’ve asked:
- “Tell me about Lawmatics.”
- “Give me tips on hiring and training new employees.”
- “Is there an archive of recordings from prior Zoom presentations?”
- “Can you show me a Clio workflow when a client contacts the office?”
- “Summarize Ross Fishman’s presentation on niche marketing.”
- “What’s the name of that service that clips web pages, Audible clips, and Kindle bookmarks?”
When the bot misses, I jump in and add my take. I’ve become the backup to the bot, not the other way around.
The side benefit is one I didn’t expect. Because members are asking the bot instead of silently giving up, I now get a window into what’s on their minds — what they’re working on, what they’re stuck on, what they care about. Low-friction for them. High signal for me. That alone is worth the cost of running it.
A small firm could get the same benefit internally.
Train a chatbot on your firm’s knowledge. Let your staff and associates ask it questions. Watch what they ask. Fill the gaps.
How This Flips the Script for Small Firms
For 20 years, real knowledge management has been a big-firm problem with a big-firm budget. The results were mostly bad, but at least big firms could afford to try.
Curated chatbots flip the economics. A solo with a folder full of documents and a free NotebookLM account can put together something surprisingly useful in a weekend.
The second-order effects matter too. New hires ramp up faster because the bot answers routine questions without interrupting anyone. The intake team gets instant answers to the same 12 questions clients ask every week. You stop being the bottleneck for questions you’ve already answered hundreds of times.
How to Start Small: NotebookLM as Training Wheels
Don’t buy enterprise software. Don’t hire a consultant. Start with NotebookLM, Google’s free RAG tool.
NotebookLM is nothing more than a RAG with a clean interface. You pull sources in — PDFs, Word docs, Google Docs, web pages, YouTube videos — and it answers questions using only those sources. No open-internet wandering. Every answer cites which source it came from.
That’s the whole thing, which is why it’s the right starting point. It forces you to think like a RAG builder: curate the sources, ask the questions, watch what breaks. That’s the muscle you’ll need for anything more ambitious later.
Your first project should be small:
- A pile of your firm’s content — manuals, FAQs, CLE materials, prior memos, intake scripts, anything text-based.
- A short list of real questions your team or clients ask every week.
- A weekend to iterate.
Drop the content in. Ask the questions. See what comes back. When an answer is wrong or thin, add a document that covers the gap.
One more note on what to put in. This isn’t the place for raw client data. Start with answers to common questions and anonymized problem-solving — firm procedures, intake scripts, redacted precedent memos, new-staff onboarding materials. That alone will cover most of what your team and clients keep asking. (Putting actual client data into a chatbot is a whole other conversation, and a whole other article.)
Ed. Note: Read Ernie’s article “NotebookLM for Lawyers: A Small Hammer for Big Document Problems” for more examples.
The Bottom Line on Your Law Firm’s Knowledge Problem
Your firm already has the knowledge. It’s been trapped in PDFs, email threads, and people’s heads for years, and the intranet you paid for hasn’t helped anyone find it.
A curated chatbot finally makes that knowledge useful — without a big-firm budget and without a KM department. Pick one document pile. Feed it to NotebookLM. See what happens.
More From Ernie Svenson and the 80/20 Principle
How Using AI Skills for Law Firm Workflows Can Turbocharge Your SOPs
Why I Switched From ChatGPT to Claude (And What Finally Pushed Me Over)
Loom for Lawyers: Why You Should Be Creating Shareable Videos
Top 8 Tech Tools for Solo and Small Firm Lawyers to End the Chaos
AI Tools for Lawyers: Why You Shouldn’t Stick to Just One
Our Fingers Can’t Keep Up With AI
Image © iStockPhoto.com.
Sign up for Attorney at Work’s daily practice tips newsletter here and subscribe to our podcast, Attorney at Work Today.
