Skip to content
Law FirmAI AssistantDocument OCRPrioritization

An immigration and personal injury firm, 6 attorneys and 12 paralegals

An in-house AI assistant for an 18-person law firm: $100K to $130K a month without hiring

An immigration and personal injury firm was stuck at $100K a month because growth meant hiring, and every question in the office went to the same overloaded paralegals. I found the real bottleneck, scoped an assistant that had read every file, and measured the result: 50 hours a week back and 30% more revenue in six months.

+$30K

more revenue every month within six months, same 18 people

50 hrs

a week back across the firm

0

new hires needed to take the extra cases

My role
Discovery and problem definition, scope and prioritization, success metrics
Timeline
Six months from launch to the $130K month
Team
Me (product, client lead) and Andres Diaz (engineering)

TL;DR

Six attorneys, twelve paralegals, years of scanned documents nobody could search, and every “where is this?” or “how do we handle this?” landing on the same few people. The firm was capped at about $100K a month because more cases meant more hires. We built an in-house AI assistant loaded with every document and procedure the firm had, with OCR so scanned files became searchable. The firm got back about 50 hours a week, took on more cases with the same team, and went from $100K to over $130K a month within six months.

Context and users

  • Paralegals were the real users. They fielded questions all day and worked late to do their own jobs afterward.
  • Attorneys needed documents and procedural answers fast and didn’t care where they came from.
  • The partners wanted growth without another round of hiring, training, and desk space.

The problem, and how we found it

The partners asked for “AI to help with documents.” The assessment showed the document problem was really two problems stacked on each other:

  1. Scans aren’t searchable. A scanned page is a picture. Years of case files existed only as pictures, so finding anything meant a person who remembered where it was.
  2. Procedures lived in people’s heads. How the firm handles a given filing was tribal knowledge. New staff learned by interrupting experienced staff.

Both problems had the same symptom, everyone asking the paralegals, and the same cost: overtime, mistakes, and a hard cap on caseload.

Hypothesis

If every document and every procedure lived in one assistant that anyone at the firm could ask, and scanned files were made searchable, the paralegals would stop being the firm’s search engine, the hours would come back, and the firm could take more cases without hiring.

Scope, specs, and prioritization

The order was deliberate: make the archive searchable first, because nothing else worked until the scans were readable; then the procedure answers; then drafting.

Shipped, in orderDeferred
1. OCR the scanned archive so every page is searchableClient-facing intake chatbot
2. “Where is this?” and “how do we handle this?” answers from the firm’s own filesAutomated filing or e-signature
3. First drafts of letters and forms for an attorney to reviewAnything that sends output to a client without attorney review

Specs that shaped the build:

  • Answers cite their source. Every answer points at the document it came from, so a paralegal can check it in one click. This was the accuracy safeguard and the trust builder.
  • Attorney review on drafts. The assistant drafts; a lawyer signs. Non-negotiable in a law firm.
  • Lives inside the firm’s systems. No new place to log in.

Key decisions and tradeoffs

  • OCR first, even though it was the least visible work. Nobody gets excited about text extraction, but shipping the assistant before the archive was searchable would have produced an assistant that couldn’t find half the firm’s files.
  • Citations over conversational polish. A slightly clunkier answer with a link to the source beat a smooth answer nobody could verify.
  • Drafting last. Drafting was the feature the partners were most excited about, and the one with the most risk. Sequencing it third meant the firm trusted the assistant’s search and answers before it trusted its writing.

What shipped

Andres built the assistant and the OCR pipeline over the firm’s document archive and procedure library, inside the firm’s own systems. I ran the discovery, wrote the scope and the sequencing, defined the success metrics with the partners, and ran the weekly check-ins through launch.

Metrics and outcomes

BeforeAfter (within 6 months)
Monthly revenue~$100K$130K+
Hours back per week0~50 (more than one full-time person)
New hires neededGrowth required hiring0
Paralegal overtimeRoutineDropped
Time to find a documentAsk a person, waitSeconds, with the source cited

The 50 hours was the mechanism; the $30K a month was the outcome. The partners used the freed capacity to take more cases rather than to cut staff, which was the plan from the assessment.

What I’d do differently

  • Measure interruptions, not just hours. “Questions asked of paralegals per day” would have been a sharper before/after than the hours estimate.
  • Bring the paralegals into scoping earlier. The partners scoped; the paralegals used. Two of the best procedure questions came from them after launch and could have been in v1.
  • Define “done” for the OCR pass up front. Old scans vary wildly in quality. A clear accuracy bar would have saved a round of rework.

My role vs. the team

I owned discovery, the two-problems framing, scope and sequencing, the metrics, and the partner relationship. Andres owned the OCR pipeline, the assistant, and the integration. The firm’s senior paralegal was the de facto product owner on their side, and the reason adoption was fast.

Want to talk through this one?

I'm happy to walk through the decisions, what I'd change, and what the numbers don't show. Everglade Systems was acquired in August 2026; I'm now looking for my next product role.