Something has shifted inside Pittsburgh's law offices. The stacks of scanned records that once kept paralegals occupied for days are now processed in minutes. Medical history timelines that demanded hours of careful review appear as polished drafts before a lawyer has finished their morning coffee. Client intake, which previously consumed the better part of an afternoon, now takes under a minute. The culprit behind this quiet revolution is a startup that has been quietly building its platform just steps from where it all began.
Squary AI, a legal tech company rooted in Pittsburgh's Carnegie Mellon University ecosystem, is using large language models to automate the most time-consuming administrative work facing mid-market law firms. The startup spun out of Cognistx, a Pittsburgh-based applied AI company that itself emerged from CMU in 2015, when cofounders Justin Waltrip, Sanjay Chopra, and Jagriti Pandey saw their legal clients pulling ahead of the rest of Cognistx's portfolio in both traction and impact. They created Squary as a focused venture to chase that opportunity.
The firm's software targets document-heavy practices, particularly personal injury and employment law, where attorneys routinely spend days reviewing case files, generating medical history chronologies, or drafting deposition questions. Squary's platform compresses those tasks into a fraction of the time, with outputs treated as attorney-reviewed drafts that include inline citations to source documents.
"We're not saying that it's here to replace anyone's job, but there are certain things, like someone spending 20 hours reviewing every single word of every single file, that aren't necessarily the best way to handle things."
Justin Waltrip, Cofounder, Squary AI
The practical consequences are rippling through how Pittsburgh firms structure their fees. When a task that once justified a full day's billing now takes minutes, the traditional model of charging by the hour starts to feel awkward for attorneys and clients alike. Curtis Wadsworth, a solo practitioner who runs Nerd Lawyer, has been adopting AI tools in legal work since 2017 and today bills clients through project-based fixed fees. He says the shift makes legal services genuinely more affordable. "It makes it cheaper for everybody and more efficient," Wadsworth said. His firm's intake process, once a three-hour endeavor, now runs in forty-five seconds.
Building Trust Into Every Output
The concern that surfaces in every conversation about AI in legal practice is hallucinations, and Waltrip addresses it directly. Squary invests heavily in preparing source data before any query runs, ensuring that scanned documents and messy PDFs are clean and legible before they reach the model. The team also carefully selects which large language models are best suited for each task type and engineers all prompts with legal specificity in mind. Every output includes citations pointing back to the original source material.
"We have full control over the end-to-end process," Waltrip said, "and so if something does go wrong, we actually have the ability to go in and change the behavior of the system right there." Wadsworth, who uses Squary and other AI tools in practice, notes that the more common challenge is not fabricated facts but faulty reasoning, where a model accurately cites a real case but misreads what that case means. Human attorney judgment remains essential. "It's like working with the senior associate that knows what they're doing enough but isn't quite there yet," Wadsworth said.
Squary's clients have so far included some recognizable Pittsburgh institutions through its parent company's network. Cognistx previously built customer-facing AI chatbots for the Pittsburgh International Airport and Duquesne Light, giving the founding team practical experience deploying AI in high-stakes, public-facing environments before narrowing to legal work. That institutional credibility has helped Squary build trust with firms that might otherwise be wary of handing sensitive case documents to a startup.
What This Means for Pittsburgh
Pittsburgh has spent the past several years establishing itself as a serious node in the national AI ecosystem, with major investments from Abridge, Gray Swan AI, Hellbender, and Gather AI. Squary's emergence adds a new dimension: a homegrown startup showing that the city's deep well of AI talent can produce practical commercial products in traditional industries far beyond healthcare and robotics. Legal services touch every business, every family, and every deal in the region. A Pittsburgh company quietly improving how legal work gets done is a win that compounds with every case that moves faster and every client who pays a fairer price.
The company is currently finalizing its seed round to build out sales and marketing. For a startup that traces its lineage directly to Carnegie Mellon and has already demonstrated real traction with paying clients, that funding conversation should be a productive one. Pittsburgh keeps building things worth watching.