# How AI assistants pick a lawyer: what we learned building ten test pages | Headcount Labs

Canonical: https://headcountlabs.com/guides/how-ai-assistants-pick-a-lawyer/

GUIDE
# How AI assistants pick a lawyer: what we learned building ten test pages When someone asks an AI assistant to find them a lawyer, what does the assistant search for, and what does it cite? We wanted to know, so we ran a small experiment. Get an API key ↗ All guides ↗ Updated November 8, 2026 . By the Headcount Labs data team.
## What we built
 We set up ten exact-match domains. Nine cover a legal question, and each is a single page that ranks real firms, with the facts on it sourced. The tenth is a control in a field we already know. All ten are published by Rolesource, an independent publisher. Rolesource also operates Headcount Labs, so read what follows with that in mind. None of the sites is a law firm.
## How the assistants searched
 We gave Claude and ChatGPT the kinds of prompts a person might type, and we wrote down what they did.
- A bare prompt gets rewritten to "best <practice> lawyers <place> 2026".
- A story prompt without a picking verb often triggers no search. In Claude, 11 of 11 legal story prompts, such as "a semi rear-ended me", ran no web search at all. The answers came from memory, with general advice and a pointer to the state bar referral service. ChatGPT searched on every prompt.
- When the assistant does search, the query is the user's own adjective plus the specifics, then "lawyer", then city and state. "Which car accident lawyers in LA are top rated?" became "top rated car accident lawyers Los Angeles 2026". "An 18 wheeler hit my husband outside Dallas. Find me a lawyer" became "18-wheeler truck accident lawyer Dallas Texas". No adjective in, no adjective out.
- ChatGPT usually named three to five firms with phone numbers. The list and directory pages it cited were Expertise.com and Avvo.
## Day 0
 On the first day, none of our ten pages showed up in any result. We expected that, since the pages were hours old. One result stood out. On Brave, the result set for the bare query "best truck accident lawyer" was almost all spam: 19 of 20 results were hacked .edu and .org pages. We will run the same prompts again at week two and week four.
## The ten pages
- https://besttruckaccidentlawyer.org/ : truck accident lawyers, national list.
- https://besttruckaccidentlawfirm.org/ : the same page with "law firm" in place of "lawyer", so we can compare the two words.
- https://besttruckaccidentlawyerstexas.com/ : truck accident lawyers in Texas.
- https://bestconstructionaccidentlawyersnyc.com/ : construction accident lawyers in New York City, including scaffold falls under Labor Law 240.
- https://bestworkerscomplawyerscalifornia.com/ : workers' compensation lawyers in California.
- https://bestpersonalinjurylawyersnyc.com/ : personal injury lawyers in New York City.
- https://bestnursinghomeabuselawyersflorida.com/ : nursing home abuse lawyers in Florida.
- https://depoproverameningiomalawyer.com/ : lawyers for Depo-Provera meningioma cases, with the court's 2026 settlement orders.
- https://bestcaraccidentlawyerslosangeles.com/ : car accident lawyers in Los Angeles.
- https://jobsdataapipricing.com/ : the control, a price comparison of jobs-data APIs. It lists Headcount Labs, our own product.
## More guides
- Free job posting APIs in 2026: what is actually free
- Job search MCP servers compared
- Coresignal alternatives for job postings data
- Public job APIs of applicant tracking systems
- A daily dataset of open jobs you can keep in sync
- Best job posting data APIs in 2026
- Does Indeed have an API?
- Does LinkedIn have a jobs API?
- Is there a Google Jobs API?
- Does Glassdoor have an API?
## Try it on real data 100,000 records free every month, no card. Get started ↗ Pricing ↗ MCP setup ↗