The launch marks the most significant product development at the company since Trajectory Capital took a controlling investment<\/a> last September and installed David Solomon<\/a>, formerly general manager and global head of GLG Law and, before that, director of financial services at Axiom, as CEO.<\/p>\n In an interview ahead of today\u2019s launch, Solomon told me that Aperture grew directly out of feedback from the company\u2019s clients, who valued the depth of Legal Decoder\u2019s analysis but chafed at its Tableau-based delivery.<\/p>\n While financial analysis professionals were comfortable with Tableau, other legal professionals wanted a simpler way to be able to query the data.<\/p>\n \u201cI don\u2019t want to have to go and do like 20 dropdowns to try to get to this data,\u201d he said, characterizing what customers told him. \u201cIs there a way I can just ask a question?\u201d<\/p>\n Aperture does not replace the machine-learning engine at the core of Legal Decoder\u2019s platform. Rather, the LLM sits on top of that engine as an access layer, helping users query, summarize and act on the analysis, while the numbers themselves come from the underlying schema.<\/p>\n That architecture, Solomon says, solves a problem that has dogged conversational AI tools in analytics, which is that if you ask the same question twice, you will get two different answers.<\/p>\n With Aperture, \u201cyou might get a slightly different answer in terms of what the talking points should be, because LLMs notoriously will give you slightly different answers, but you\u2019re never going to get different numbers,\u201d Solomon said. \u201cThe numbers are always going to be the same.\u201d<\/p>\n The engine beneath Aperture was built over roughly a decade by the company\u2019s founders, Joseph Tiano<\/a>, a former Pillsbury partner and now the company\u2019s president, and Chris Miller<\/a>, now chief operating officer and chief technology officer. a technologist, longtime friends who met as undergraduates at Georgetown.<\/p>\n As Solomon tells it, the idea was born when Tiano was doing write-offs late one night at Pillsbury and concluded there had to be a better way.<\/p>\n The company they founded in 2014 built a library of more than 411,000 legal concepts and action words which Legal Decoder uses to disaggregate line-item narratives in legal invoices.<\/p>\n Rather than rely on UTBMS codes \u2014 which Solomon called \u201cnotoriously very unreliable\u201d \u2014 the system disregards the timekeeper\u2019s own categorization, recategorizes each line item based on its narrative, and then classifies the work four layers deeper than the UTBMS code level.<\/p>\n The platform applies 45 proprietary analytics flags to identify issues such as block billing, skill-set mismatches, multi-staffed meetings, excessive time, and vague entries.<\/p>\n One notable feature of Aperture relates to data security. Before any customer data interacts with the LLM, Legal Decoder\u2019s engine strips identifying markers \u2014 law firm names, timekeeper names, matter names, client names, and proper nouns within narratives \u2014 and replaces them with secure tokens. The LLM sees \u201cprepare for [token] deposition,\u201d not \u201cprepare for John Smith deposition.\u201d<\/p>\n The company also resets tokens at the session level, so the same underlying value is never represented the same way across tokenization runs.<\/p>\n \u201cMost token systems map values the same way every time, which means that mapping itself becomes something to protect,\u201d Tiano said in the company\u2019s announcement. \u201cWe reset tokens at the session level, so the underlying data is never represented the same way twice.\u201d<\/p>\n In our interview, Solomon contrasted that approach with what he sees as the prevailing practice in legal tech, where vendors rely on enterprise agreements with LLM providers to protect data rather than structural controls.<\/p>\n \u201cA lot of our clients said we don\u2019t like using some of the tools on the market because it just feels like they\u2019re a wrapper around an LLM,\u201d he said. \u201cSo can you figure out a way that we can get AI-grade responses without exposing our data?\u201d<\/p>\n The results are also designed to be auditable. Any finding \u2014 say, that 8% of line items were block billed \u2014 can be exported to CSV down to the underlying line items, so a skeptical user can check the work against the actual invoices.<\/p>\n Legal Decoder\u2019s press materials say that its analytics engine \u201chas been validated in federal court proceedings.\u201d<\/p>\n What it means by that is that it has been approved for use by fee examiners in major bankruptcies, including PG&E, Toys \u201cR\u201d Us, Spirit Airlines and Purdue Pharma. In those engagements, fee examiners disclose in publicly filed court documents that Legal Decoder\u2019s tool is the methodology underlying their fee-application analysis.<\/p>\n \u201cFederal bankruptcy courts and their trustees and their appointed fee examiners have not only accepted our methodology, they are relying on our methodology,\u201d Solomon said.<\/p>\n The company has gained recognition in other ways, as well. It won the Association of Corporate Counsel Value Champion award<\/a> in 2025 for its partnership with UnitedLex to help UBS consolidate legal operations following its acquisition of Credit Suisse, conducing an in-depth review of its highest-cost matters, identifying inefficiencies, and realigning staffing models.<\/p>\nAI Layered on Machine Learning<\/h3>\n
![\"\"](\"https:\/\/i0.wp.com\/www.lawnext.com\/wp-content\/uploads\/2026\/07\/SAMPLE-Aperture-by-LD-Summary-1024x541.png?resize=1024%2C541&ssl=1\" "\\"\\"")
<\/a><\/p>\nTokenization Before the LLM<\/h3>\n
![\"\"](\"https:\/\/i0.wp.com\/www.lawnext.com\/wp-content\/uploads\/2026\/07\/SAMPLE-Aperture-by-LD-Data-Viz-and-Follow-Up-Queries-1024x482.png?resize=1024%2C482&ssl=1\" "\\"\\"")
<\/a><\/p>\nCourt-Validated Analytics<\/h3>\n