Kira Built-in Provision Models
Kira’s built-in machine learning models cover due diligence, M&A deal points, general commercial, corporate organization, real estate, ISDA schedules, commitment letters and non-disclosure agreements, with more being added on a regular basis. These models help you get started on review projects quickly without having to invest any time in training your own.
Built-in Provision Groups
Our team of experts—who practiced at large firms such as Skadden, Weil, Fried Frank, and Reed Smith, and graduated from law schools such as Harvard, McGill, and NYU—is continually working to add more models. Our currently released provision groups can help with the following areas.
- Due Diligence: Includes provisions such as change of control, assignment, exclusivity, license grants and indemnity to help you get through contract review faster and more accurately.
- M&A Deal Points (Private Target): Includes provisions from share purchase agreements, asset purchase agreements and merger agreements, to help you build clause banks or deal points studies, or maintain a database with details about the deals you’ve worked on.
- General Commercial: Includes provisions such as most favored nation, liquidated damages, termination, automatic renewal, export control and anti-money laundering compliance to help you manage contractual obligations.
- Corporate Organization: Includes common provisions from shareholders’ agreements such as board/manager selection, veto/approval rights, rights of first offer/refusal, drag-along rights and tag-along rights to help you find precedent language, conduct due diligence or obtain market intelligence information.
- Real Estate: Includes commercial lease provisions such as rent, notice, sublet conditions, description of premises, common area maintenance, parking, signage and utilities to help you with lease abstraction or due diligence projects.
- ISDA Schedules: Includes provisions such as netting of payments, credit event merger, termination currency and multibranch clause to help with due diligence or regulatory compliance.
- Commitment Letters: Includes provisions from loan commitment letters, including interest rate, maturity, amortization, credit facility sizes, covenants and conditions to help you determine market trends, maintain a database of deals or search for precedent language.
- Non-Disclosure Agreements: Includes provisions from non-disclosure agreements including the definition of “Confidential Information” and exceptions, injunctive relief and standard of care to help you determine confidentiality rights and obligations in the context of due diligence or any departures from your organization’s accepted and standard NDA terms.
Kira is the world’s most powerful and accurate machine learning contract analysis system, thanks to a unique combination of superior algorithms, developed by our in-house R&D team, and professionally trained provision models.
Just how accurate is Kira? Our standards require that virtually every built-in provision achieves at least 90% “recall.” This means that our software will find 90% or more of the instances of the provision. Our “precision” (a measure of false positives) differs provision by provision but is consistently manageable.
How good is 90% recall? Multiple studies in the field of information retrieval have found that the theoretical maximum of human review without technology assistance is around 65% recall, and with typical technology assistance in eDiscovery context, maxes out around 75-80%. See, e.g., Maura R. Grossman & Gordon V. Cormack, Technology-Assisted Review in E-Discovery Can Be More Effective and More Efficient Than Exhaustive Manual Review, XVII RICH. J.L. & TECH. 11 (2011) at 23-24.
In other words, 90% recall is probably a whole lot better than the typical junior associate at a law firm. And with Kira, 90% can be your team’s starting point, allowing you to focus your time on the remaining 10%.
All Artificial Intelligences are not Equal
Kira is built on advanced state-of-the-art machine learning technology and delivers accurate results even on new and unknown agreements. Alternative technologies include “rules-based” A.I.s, and comparison-based approaches (some of which leverage a very different form of “machine learning”), both of which have been around for several decades. These legacy approaches require a human to predict the variability of the documents and write guidelines that help the machine identify particular clauses. They can work reasonably well if you are reviewing highly similar documents or for simple provisions (e.g., provisions like governing law). However, these older technologies have proven incapable of delivering consistent results over a highly varied set of documents, and seldom come anywhere close to the precision and recall standards set by Kira’s machine learning algorithms.