Introduction  

At Thomson Reuters, we are redefining what it means to deliver professional-grade AI for the legal industry. More than 2,000 law firms, corporations, nonprofits, and government agencies worldwide rely on CoCounsel, our GenAI assistant, which transforms how legal professionals work by automating complex document review, contract analysis, drafting, and other time-intensive tasks with unprecedented speed and accuracy. That trust is earned through a comprehensive evaluation methodology that encompasses dataset rotation, automated testing, expert assessment, continuous monitoring, and strategic partnerships. This post focuses on one critical component of our broader testing framework: how our teams combine attorney expertise with large-scale automated testing through Scorecard, a proprietary evaluation platform originally developed by the engineers behind Waymo’s self-driving car testing infrastructure. While Scorecard represents just one pillar of our multi-layered approach, it exemplifies our commitment to proactive system optimization and continuous improvement.  

Testing and Benchmarking with Scorecard 

Our teams of attorney subject matter experts (SMEs), machine learning experts, and engineers rely on a robust array of testing tools and methodologies, including human legal expertise, specialized testing software, expert prompt engineering, and continuous monitoring of test results. Rather than waiting for performance issues to emerge, we proactively identify and address potential challenges through systematic testing and optimization. When issues arise that may affect CoCounsel’s performance, these teams are equipped to mobilize a collaborative, rapid response effort, locating and remedying performance issues before they affect our customers.  

A key tool is Scorecard, a specialized application that quantitatively evaluates CoCounsel responses against ideal responses created by our attorney SMEs. Scorecard is the evaluation infrastructure for AI agents in legaltech, fintech, and compliance, and enables us to supplement our manual testing with large-scale, automated testing against our internal benchmarks. Built by the team behind Waymo’s self-driving evaluation infrastructure, Scorecard runs millions of agent simulations to help teams evaluate, optimize, and ship reliable AI agents faster. 

Performance issues typically arise from two distinct factors:
(1) the quality of user inputs, such as user prompts or queries, and documents; and,
(2) system limitations.

We address the first factor by providing customers with high-quality training, support, and tools—including CoCounsel-created prompts, guided expert workflows, and agentic systems. In contrast, addressing the second factor requires recalibrating the system itself. 

Each CoCounsel skill is a precisely engineered legal tool, tailored on the backend to perform a specific legal task. Because we calibrate each skill to reliably extract information by leveraging the unique strengths of its underlying AI model, migrating a skill from one model to another often introduces performance issues that require recalibration. Such migrations may occur, for example, when a third party releases a new AI model with enhanced capabilities. To safeguard our customers, we conduct all migration and recalibration work within testing and staging environments before deploying any changes. 

Case Study: AI Model Migration of Review Documents Skill 

Large-Scale Testing Using Realistic Scenarios & Manual and Automated Review 

Jessica, an attorney SME on the CoCounsel AI Reliability Team—also known as the Trust Team—oversees the evaluation of CoCounsel’s Review Documents skill. In just minutes, the Review Documents skill can closely review and analyze large troves of legal information that would ordinarily require an attorney to spend hours or even days of manual review.  

Jessica proactively monitors the upcoming migration of the Review Documents skill to a new AI model. This migration promises significant improvements in CoCounsel’s speed and accuracy. Working in a CoCounsel testing environment, Jessica manually reviews and evaluates the skill’s responses on the new model using a carefully curated “testset” of sample “testcases” that reflect real-world legal practice scenarios. Jessica checks CoCounsel’s response to each testcase user query against an ideal or “gold-standard” response that she has personally crafted using knowledge and expertise gained from years of experience as a real-world attorney.  

Because each testset can contain several hundred testcases or more, reviewing each result would ordinarily be prohibitively time-consuming. However, Scorecard enables Jessica to supplement and scale the impact of her manual review by providing an extra layer of automated review.  

Scorecard works by evaluating each response produced by CoCounsel and the AI model against the corresponding ideal response, then assigning the testcase a passing or failing numerical score using several criteria, such as the model’s ability to recall information, its precision, and its accuracy.  

Reviewing the Scorecard results enables Jessica to compare the full testset’s scores on both models for the Review Documents skill. This means she can evaluate CoCounsel’s performance at scale much more efficiently.

Fig 1: Attorney SME manual review workflow.

Fig 2: Scorecard automated review workflow.

Reviewing the Scorecard data, Jessica quickly observes that on the new model, Scorecard consistently assigns failing scores to a specific testcase, assigning it a 1 out of 5 on all metrics. She identifies underperformance in other testcases, too; however, the other testcases still yield higher scores than the problem testcase. Recognizing the stakes are high, Jessica immediately begins troubleshooting the performance issue.

Troubleshooting

Jessica and her team of SMEs begin to troubleshoot by homing in on the problem testcase that Scorecard identified.

The testcase user query asks:

What medications is the patient currently taking? Please be specific with prescription names and dosages.

Analyzing CoCounsel’s outputs for the testcase, Jessica determines that on the new model, the Review Documents skill is failing to identify all medications for the patient consistently, causing a clear discrepancy with the ideal response. The new model occasionally includes all the relevant medications, but such inconsistent behavior does not meet the required standard.

[Click image to expand] Fig. 3: Scorecard screenshots of the AI model’s failing answer. As can be seen in the expanded “model response” window above, the model was including medications that were no longer currently active and was failing to identify the only two current, active medications (Aspirin 81MG EC TAB and Aspirin 325MG EC TAB).

By digging deeper and examining the problem testcase response as well as some of the other, underperforming testcase responses, Jessica pinpoints the core issue as being the AI model’s ability to provide a sufficiently comprehensive level of detail. Since the model sometimes does output a complete response, Jessica observes, as a secondary concern, that the AI model struggles to produce consistent results.

Iterative Resolution & Continuous Improvement

Having identified the core issues, Jessica brings the issue to the CoCounsel engineering team for resolution. She describes the parameters of an ideal response and how the new model’s response fails to meet target metrics. This gives the engineers concrete goals, which they can use to modify the backend AI prompts. After each prompt change, Jessica evaluates a portion of the test set which is continuously updated, complemented by independent attorney reviews. Jessica and the engineering team continuously execute multiple rounds of prompt changes and use Scorecard to evaluate the results until the issue has completely resolved, and the new model is performing as expected. Scorecard now assigns the problem testcase a 4 out of 5 on all metrics, a good score—it reflects that the model has produced a valid response that captures all relevant substantive data points contained in the ideal response but may differ in more subtle ways, such as writing style or level of additional detail. Resolving this core issue ensures the secondary issue of inconsistent performance has been resolved as well. Jessica further conducts manual reviews of CoCounsel’s performance on the problem testcase.

These adjustments have cascading positive effects. When the problem testcase begins passing 99-100% of the time, the other testcases that had experienced the same issues (albeit less frequently) begin passing 100% of the time.

[Click image to expand] Fig 4: Scorecard screenshots of the AI model’s passing answer. This was achieved after multiple rounds of testing and prompting changes, which confirmed the engineers were able to pinpoint and fix the issue. As shown in the expanded “model response” window above, the issue was ultimately fixed, and the model began answering this testcase correctly (as well as a few other testcases that had been failing, albeit less frequently, due to the same issue).

Once the model consistently returns results that meet TR’s expectations and are suitable for legal work, Jessica feels secure in the knowledge that the Review Documents skill meets necessary standards and can be released to customers.

Even after the skill is released on the new model, Jessica continues to run various Scorecard tests, multiple times daily to ensure consistency.

Fig 5: Continuous improvement process between attorney SME and engineers.

Observations

CoCounsel’s proactive and continuous iterative improvement process is painstaking but necessary. The problem testcase identified by Jessica using Scorecard provided a useful benchmark for improvement, because it failed more consistently than other testcases. Using a “least common denominator” testcase provided a measuring stick against which we could measure other testcases.

Using Scorecard allowed Jessica to extrapolate improvements from the single problem testcase to all other testcases, dramatically increasing the efficiency and speed with which she could iterate and improve CoCounsel’s performance across the board.

Conclusion

Innovation in AI is never “one and done.” Models evolve, new risks emerge, and customer needs grow more complex. While this post has focused on Scorecard as one essential component of our testing infrastructure, it represents just one element of our comprehensive evaluation methodology. Our broader approach integrates dataset rotation, automated testing at scale, expert assessment from legal professionals like Jessica, continuous monitoring of live performance, and strategic partnerships with leading AI providers.

This multi-layered framework is what sets CoCounsel’s approach apart. By combining deep legal expertise with world-class technology infrastructure, we’re not only raising the standard for AI in professional fields, we’re defining it. Through proactive system optimization and evaluation approaches, CoCounsel continues to deliver the transformative professional-grade legal AI capabilities that tens of thousands of legal professionals depend on.

—-

About the Authors

Tyler Alexander is the Director of AI Reliability at Thomson Reuters, where he leads a team of attorneys to ensure CoCounsel delivers trustworthy, professional-grade performance. He specializes in large-scale testing and benchmarking of AI systems for legal professionals.

Heather Nodler is a Lead CoCounsel AI Reliability Manager at Thomson Reuters. With years of experience practicing law, they now apply their expertise to evaluating, calibrating, and continuously improving CoCounsel’s legal AI skills. Heather works closely with product and engineering teams to ensure that every CoCounsel feature meets the high standards required for real-world legal practice.

Redesigned drafting capabilities unify CoCounsel tools, content, expertise, and workflows

Informed by customer feedback, we’ve reimagined the legal drafting experience – making it more intuitive, intelligent, and seamlessly integrated. The drafting capabilities in CoCounsel fuse users’ institutional knowledge with trusted Thomson Reuters content and AI-powered technology to expedite the legal drafting process. The redesigned homepage puts everything users need right at their fingertips – CoCounsel Chat, skills, and powerful litigation and document analysis tools – all in one clean, intuitive space. Eliminating the need to jump between tabs or hunt for resources, it’s now an even smoother, faster experience that lets users stay focused, work smarter, and get more done with less friction.

Live Draft brings the ability to summarize and modify a document using natural language in Word. Live Draft also delivers contextual awareness of the document and understanding of the content and structure, so every suggestion and edit is tailored to the content. This helps to further reduce time spent producing a final draft, by delivering more accurate, relevant suggested changes.

Append Authorities enables users to combine all cited documents into a single file suitable for court use, reducing the risk of errors and increasing efficiency. Every cited document is linked for verification purposes, and a hyperlinked table of contents is included.

Region settings customizes CoCounsel tools for global legal professionals

The new region settings capability enables users to select their geographic preference from U.S., UK, Australia or Canada. Based on the selected region, region settings will automatically adjust tools and prompts in the CoCounsel Library making the work product more relevant. Users can now automatically tailor their documents using specific regional requirements, including for the UK and Australia, British English spelling variations, legal terminology, grammar, and content formats. Similarly, this will be coming soon for Canadian English. Additionally, CoCounsel Library is now available in the UK, Canada and Australia.

HighQ integrates CoCounsel AI for intuitive, conversational client data access

With CoCounsel’s Search a Database skill embedded within HighQ, this customer-driven development allows clients the ability to pose queries regarding their data and receive summarized, highly relevant answers. Sourced from pre-approved content within their site, clients can quickly review summaries, generate reports, and make informed decisions without waiting for manual responses.

Legal Tracker adds AI-powered capabilities

Legal Tracker’s new AI features help users manage legal spend more efficiently. The AI-powered PDF-to-LEDES converter and invoice review speed up invoice evaluation and ensure accurate billing. An AI assistant also streamlines reporting and reduces manual data handling.

These transformative features reinforce our commitment to empowering legal professionals with the tools and solutions they need to excel. Explore these new features or request a demo to see firsthand how they elevate work to new heights.

To stay abreast of newly added features, monthly releases, and more, please sign up for the CoCounsel Community.

Nearly half (47%) of law firm respondents from the Future of Professionals Report say their firms are already experiencing at least one type of benefit from AI adoption and 80% expect AI to fundamentally alter the course of their business over the next five years. Chief among those is time savings. On average, law firm professionals expect to free up 190 hours per year by using AI. At current average hourly rates, that works out to approximately $18,000 in savings per professional, per year – or a total of $20 billion for the U.S. legal industry.

Perception vs. Reality

For all the enthusiasm that exists for AI’s potential, however, there is a large gap emerging between law firms’ AI aspirations and their real-world AI strategies. Even though the majority of law firms expect AI to drive transformational change in the future and nearly half are experiencing some benefits now, far fewer (29%) expect to see high or transformational levels of change this year. When pressed further on what their firms are doing today to leverage AI, nearly one-third (32%) of law firm respondents say they feel their firms are moving too slowly on AI adoption, and just 22% say their firms have a visible AI strategy in place.

This gap between future ideals and current realities is a phenomenon McKinsey recently dubbed “the GenAI paradox,” which occurs when businesses race to invest in AI pilot projects and buy new solutions, but struggle when it comes to implementing them and integrating them into everyday workflows. Versions of this struggle are playing out in virtually every industry right now as professionals come to grips with the fact that true transformation is not as simple as plugging in an off-the-shelf AI tool. It requires a clear strategy, a carefully planned roadmap, targeted integration of professional-grade AI solutions, and a commitment at all levels for the long haul. A firm cannot afford to sit on the sidelines any longer – it is imperative to have an AI strategy.

Key Steps to True AI Transformation

Over the course of our partnerships helping some of the world’s largest law firms not only access new AI capabilities, but implement firm-wide AI strategies, we’ve found four levers that all firms need to engage to ensure the success of their AI initiatives.

• AI Tools Without an AI Strategy will Never Reach Their Potential: Among the 22% of law firms that currently have a visible AI strategy in place, 71% are already experiencing a clear return on investment from AI. By contrast, for those firms that do not have a clear AI strategy in place, just 18% are experiencing a return on investment. That means law firms with a visible AI strategy are almost four times more likely to experience benefits compared to firms without any significant plans for AI adoption.
• AI Leadership Comes from the Top: Law firms helmed by leaders who lead by example when introducing change, firms that have added new governance roles, and those that are actively investing in AI are consistently seeing more benefits than those that don’t. For AI to truly add value, it needs to be implemented firm-wide, and that kind of sweeping change can only come with leadership support, clear goals and objectives, and widespread adoption.
• Operations is Where the Hard Work Happens: Firm-wide AI integration is impossible without first understanding the need to change and reimagining workflows. To extract maximum value, AI-powered tools must be built directly into existing systems and processes. That requires making transformative changes to underlying business models, including how firms price, staff, and deliver legal work, and how they adapt related workflows and processes, while adding new roles and skills to support their operations.
• End-User Adoption: The best AI technology and most well-thought-out strategy in the world will not mean anything if no one uses it. When users within law firms understand AI and feel empowerment, ownership, and accountability for its use, their law firms see results not only in terms of higher levels of AI adoption but in the additional benefits and ROI that they gain as well. Firms need to make sure they are educating staff, making tools readily available, and allowing time for a learning curve to take root.

While the detailed strategies and specific paths to AI implementation will vary from firm to firm, there are a handful of universal truths that apply to all. Foremost is the commitment to address the AI revolution for what it really is – a monumental transformation in the way legal work is conducted on par with the introduction of the personal computer, the internet, and the smartphone. It is not enough just to buy the latest greatest widget. Firms that want to extract real value from AI need to think hard about how it will affect everything they do and start addressing those changes now to unlock the full potential of the technology to transform their firm.

But what followed was less about innovation and more about disruption. Longstanding models like GPT-4o were pulled without warning. Familiar workflows broke. Performance felt inconsistent. Some users even said the model felt distant and robotic. Within days, OpenAI had rolled back several changes and re-enabled access to older models.

It wasn’t a failure of any one model or company but rather a failure of expectations. And it’s a reminder of a broader truth in the AI industry: even the most advanced systems can introduce friction if change outpaces the ability to adapt to it. As models evolve, so must the frameworks around them, especially in professional environments, where progress only matters if it delivers measurable, reliable benefits for the humans it’s meant to empower.

At Thomson Reuters, we work with lawyers, tax advisors, and compliance professionals whose work leaves no room for guesswork. For them, consistency is not a preference—it’s a fundamental requirement for them to uphold their professional duty to their clients. That’s why we don’t chase upgrades for their own sake. And we certainly don’t ask our customers to pick which model they want to use. That’s our job. Our customers expect us to deliver a result they can trust, not a menu of models to experiment with. They want confidence, not complexity.

When we evaluate a new LLM, we do it through the lens of real-world use:

• • Can it reason over long documents with accuracy?
  • Can it explain its conclusions with transparent citations?
  • Will it behave consistently inside multi-agent workflows?
  • Does it integrate with how professionals already work?

If the answer is no, we don’t ship it…until we’re confident that we’ve mitigated those concerns appropriately.

One example: earlier this year, our team benchmarked several leading LLMs for long-context performance. The task was to extract and apply insights from large, multi-thousand-word legal documents, a common need in law and compliance. We found significant variance. Some models struggled to maintain context or reference earlier sections accurately. Others returned plausible-sounding answers that fell apart under scrutiny. Rather than push forward with the best-performing model, we paused. We refined how our agents chunk and reason over large documents. We optimized prompts and guardrails. And we only moved forward when the system delivered answers that we’d be willing to stand behind in a courtroom.

This kind of work doesn’t show up in a product demo. But it’s what builds trust.

We also design our products to abstract that complexity away. In CoCounsel Legal and Deep Research, we use multi-agent systems to coordinate model selection, content access, and validation behind the scenes, so the user sees a transparent, explainable result, not a swirling mix of models and prompts.

Recent model rollouts offer an important reminder: in enterprise AI, newer isn’t always better. Progress should be measured not just by technical benchmarks, but by the clarity, consistency, and confidence it delivers to real users. The systems that will define the next chapter aren’t just the most advanced, they’re the ones that work reliably, integrate seamlessly, and build trust from day one.

The reality is, there will be more disruption. We are all moving fast because the potential of AI is enormous and the demand for it is real. But speed does not have to come at the expense of the hard-earned trust of our customers. The more we treat disruption not as a cost of innovation, but as a signal to improve our processes—model governance, human oversight, testing frameworks—the better we will get at delivering AI that is not just powerful, but trustworthy. Over time, the industry will learn. We will see fewer rollbacks, clearer standards, and smarter integration. But that will only happen if we choose to build that way, with intention, transparency, and the end user in mind.

That’s the future we’re building toward. Not hype-proof. Trust-proof.

Behind the scenes, we’re evolving our engineering culture, accelerating development cycles, and embedding AI into the way we work, because to deliver professional-grade technology externally, we must operate like a modern tech company internally.

Here’s what that transformation looks like in practice.

From Technical Debt to Engineering Velocity: Our Work with AWS

Every technology company navigates the balance between maintaining legacy systems and building for what’s next. For us, our .NET applications were a major bottleneck, slowing down innovation and tying up engineering time in maintenance instead of forward progress.

To tackle this, we partnered with AWS and joined the private preview of AWS Transform, an agentic AI-powered code modernization tool. The impact was immediate. What once took months of painstaking manual updates became a two-week sprint. Using agentic AI, we cut technical debt dramatically and lowered cloud operating costs by 30%.

But the bigger shift was cultural. Our engineers now spend less time managing legacy code and more time creating value. That’s what transformation looks like.

“This isn’t just a modernization story—it’s a mindset shift,” said Matt Wood, VP of AI Products at AWS. “Thomson Reuters showed what’s possible when you combine large-scale enterprise systems with next-generation AI tools. They didn’t just migrate—they accelerated how they build, think, and deliver.”

Cloud at Scale: Partnering with Microsoft to Future-Proof Our Core Infrastructure

Innovation can’t thrive without a strong foundation. That’s why we undertook one of the most ambitious cloud migrations in our history: moving over 500 terabytes of data and 18,000 databases to Microsoft Azure SQL Managed Instance. This shift supported over 70,000 users across 7,000 firms and dramatically improved performance, scalability, and reliability. Working side by side with Microsoft’s engineering teams, we used automation, phased rollouts, and custom tooling to modernize without disruption. We eliminated legacy bottlenecks, streamlined backup and restore processes, and reduced infrastructure complexity across the board.

“Microsoft was invaluable, working closely with us to optimize load and troubleshoot at every stage,” said Bart Matzek, Senior Director of Technology, Solutions Engineering at Thomson Reuters. “This deep collaboration empowered us to build new technical capabilities and resilience. Our team emerged stronger—better equipped to deliver reliable, high-performance solutions to our customers.”

“We’re proud to support Thomson Reuters in this journey,” said Arpan Shah, General Manager of Azure Infrastructure at Microsoft. “Their scale, complexity, and ambition make them a model for how modern enterprises can evolve their platforms to unlock agility, reliability, and innovation through the cloud.”

This wasn’t just about lifting and shifting infrastructure. It laid the foundation for everything we’re building next: agentic AI systems, real-time decisioning, and seamless integration across domains.

AI Agents in Action: Driving Internal Insights with Snowflake

We’re not just building agentic AI for customers. We’re embedding it into how we operate.

One powerful example is our AI Data Analyst Agent, built in partnership with the Snowflake AI Data Cloud. This system interprets natural language queries, performs operations, and surfaces real-time insights to non-technical teams across support, finance, and operations.

“Before this agent, analyzing support cases was a manual, monthly process,” said Rittika Jindal, Principal Engineer at Thomson Reuters. “Now it happens daily, automatically, and gives time back to teams to focus on the customer experience.”

We’ve built this using Snowflake’s unified platform and deployed it with governance, scalability, and reliability top of mind. Powered by LLMs like Anthropic’s Claude via Snowflake Cortex AI and observable with tools like TruLens and AgentBench, this system is secure by design. Our data never leaves Snowflake.

This is AI that works, not just in theory, but at scale and with trust.

The Bigger Picture: Operating Like a Technology Company

These aren’t isolated initiatives. They’re signals of a broader shift. Across Thomson Reuters, we’re applying the same mindset we bring to customer-facing products: agile, AI-powered, and engineering-led.

We’re modernizing our tech stack. We’re hiring and empowering top-tier engineering talent. And we’re building AI into everything from code migration to platform orchestration.

This is what becoming a technology company looks like, from the inside out.

Because for us, it’s not just about what we sell. It’s about how we think, how we build, and how we move. 

The most important skill new lawyers will need to thrive isn’t encyclopedic knowledge of case law, razor-sharp logic, or the ability to tolerate long hours – it’s adaptability. But what does that actually mean for a first-year associate starting their first job at a law firm? It means approaching the role as a continuous learner rather than someone who has “arrived” with their JD in hand.

Building An Adaptability Toolkit

Developing adaptability isn’t about becoming a generalist who can do everything – it’s about becoming someone who can quickly learn what each situation requires. Start by cultivating core habits and building your adaptability toolkit by:

Embracing technology: View legal technology as a collaborator, not a threat. The associates who thrive will be those who become fluent in leveraging the latest tools to produce higher-quality work more efficiently. According to a recent study, 28% of law firms are already using generative AI (GenAI) in their practices and 93% say GenAI will be a central part of their organization’s workflow within the next five years. So next time your firm introduces new research platforms or AI tools, volunteer to part of the beta test rather than waiting for mandatory training. This positions you as someone who embraces innovation rather than fears it.

Seek feedback on efficiency, not just accuracy: An adaptable associate might ask: “I completed this document review in eight hours – what would help me provide the same quality analysis in six hours next time?” This mindset shifts from time-based to value-based thinking, positioning new lawyers for success in an evolving market – and AI can help make this a reality by completing select tasks that take valuable time.

Participating in new experiences early in your career: Volunteer for cross-practice projects, client secondments, or firm innovation initiatives. The broader your exposure to different ways of practicing law, the more adaptable you’ll be when change inevitably happens. For example, if you’re a corporate associate, volunteer to help the litigation team with a discovery project – you’ll learn how the contracts you draft might be evaluated in disputes.

For first year associates to prove their value in this new world, it will require more than just hard work. You should put your energy toward higher-value tasks that put an emphasis on soft skills like adaptability, creativity, leadership, curiosity, and tech fluency. The work is no longer just about the volume of output produced; it is about leveraging all available resources – including technology – to achieve successful outcomes.

Lead Change, Don’t Just Follow It

To that end, adaptability remains the thing that will quickly separate the future leaders from the rest of the pack of first-year associates entering the legal workforce. While versatility as a skillset is not as easy to quantify as billable hours, it is a far more accurate measure of how well new attorneys are able to recognize new opportunities, embrace creative problem-solving, and adopt new approaches focused on achieving the best end result. This is the factor that will help law firms navigate the next decade of transformation – and the individuals prioritizing adaptability early in their careers will set themselves up as key drivers of the firm’s overall success.

Clients are demanding more value, transparency, and efficiency. Legal technology – from AI-assisted research tools to automated contract analysis – is redefining how law firms deliver services.

Today’s most effective legal professionals are those willing to rethink entrenched practices, test new technologies, and collaborate in ways that break down traditional silos. Adaptability in this context means not just keeping up with change but leading it. Start building your adaptability toolkit today, and you’ll be positioned to lead tomorrow’s legal innovations rather than scramble to catch up with them.

Throughout history, widespread corporate technology adoption has always come from the places that could make the best business cases for investment. The first computers were used in banking and finance. The internet hit its stride in the marketing and sales departments. And now, AI-led transformation is coming from the world of professional services, where legal, tax, accounting, compliance, global trade, human resources and other enabling functions are pioneering some of the most exciting use cases for technology.  

Transforming Complex Corporate Workflows 

As a case in point, consider the recent launches of Thomson Reuters CoCounsel Legal, CoCounsel Tax, and AI-enhanced Legal Tracker, which are setting the stage for enterprise AI transformation. Unlike point solutions and other standalone AI tools that help to automate specific tasks, these new platforms are the first of their kind to create fully integrated enterprise AI platforms that break down legacy silos and connect disparate data to deliver more collaborative, strategic insights. 

The newest of these solutions, CoCounsel Legal, is the industry’s first agentic AI platform that makes it possible to integrate AI seamlessly across legal research, document analysis, and drafting tasks. That’s such a game-changer because it removes one of the biggest barriers to widespread AI adoption: fragmented, clunky workflows.

The fact is, corporate legal teams are busier than ever, and many are struggling to keep pace with the crush of demand being placed on their teams. The same can be said for corporate tax, compliance, global trade, human resources, and other enabling functions that are being tasked with doing more with less every day. They simply don’t have time to toggle in-and-out of different tools, conducting research on one platform, drafting on another, and then cross-referencing everything to make sure they trust the results. They need tools they can trust, and they need those disparate workflows to be connected in a single place. 

Embedded, Connected, and Intelligent 

To date, seamless connectivity has been the missing link keeping many corporate AI initiatives stuck in first gear. Consider recent research from S&P Global, which found that corporate AI project failure rates have risen to 42%, this year, with nearly half (46%) of those projects being abandoned between proof of concept and broad adoption. What that shows us is AI needs to do more than just produce results in isolation—it only really drives value when it is connected, or embedded, into the larger workflow. 

This phenomenon also helps to explain why corporate enabling functions like legal, tax, and others are emerging as the ideal proving ground for a truly enterprise approach to AI adoption. The very nature of this data-intensive, knowledge-driven type of work is rooted in consuming large amounts of structured and unstructured information, spotting anomalies and connections, and interpreting and reporting results—all of which are areas where AI can deliver enormous benefits.  

By combining those analytic and data processing strengths with authoritative case law and tax policy information that’s been curated and vetted by attorneys and CPAs—and connecting it all in a seamless workflow that supports multiple different functions—Thomson Reuters is creating the template for what successful enterprise AI integration looks like. Perhaps more importantly, though, we’re making it possible for our clients to address some of their biggest pain points. In addition to CoCounsel Legal, our recently launched CoCounsel Tax is giving corporate tax teams expert-level analysis, comprehensive research, and end-to-end workflow automation, and our AI-enhanced Legal Tracker is helping legal, compliance, and finance teams automate routine tasks, streamline invoice review, and provide instant, data-driven insights to optimize legal spend and operations.  

Transforming the Enterprise from the Inside-Out 

Together, these solutions are helping to transform corporate workflows from the inside out. By focusing our resources on some of the most complex, process-driven functions of the modern corporation, and delivering solutions that solve real problems, we’re creating the playbook for successful enterprise AI adoption.  

Not everyone would have expected legal, tax, or other corporate enabling functions to be the standard bearers for AI-driven innovation, but few parts of the modern business ecosystem are in greater need of an AI-assisted boost, and few are in better position to truly transform their day-to-day operations with embedded, connected, and intelligent solutions. For our part at Thomson Reuters, we look forward to continuing to push the envelope and give these teams the resources they need to chart the course for the future of professional work.

Learn more about Legal Guided Workflows here:

For the past few years, legal AI has been all about prompting. Ask a question, get an answer; refine your prompt, get a better response. It’s been helpful, but it still required you to drive every interaction, manage every step, and verify every output. That’s changing in a big way. 

CoCounsel Legal represents something entirely different: it unifies legal research, workflow automation, intelligent document management, and AI-powered legal assistance into one seamless solution. This is the most advanced AI offering to date from Thomson Reuters, and it is designed to help legal professionals move from merely prompting and into true AI transformation.  

The Foundation for Professional-Grade Agentic AI 

True agentic AI in legal practice requires three essential components: advanced reasoning models, comprehensive legal content and tools, and expertise from thousands of domain experts. Thomson Reuters has meticulously developed and enhanced these capabilities over decades, a key differentiator that other providers simply cannot imitate. 

Part of CoCounsel Legal, Deep Research, grounded in Westlaw content, demonstrates what becomes possible when these elements come together. This isn’t AI that mimics legal thinking; it reasons through complex legal problems with the depth and rigor that legal professionals require. 

Customer Value Through Reasoning and Transparency 

Deep Research in CoCounsel Legal stands out by providing value through transparency. Legal professionals need more than just answers; they need to understand the reasoning behind those answers. This transparency is essential for professional accountability. By understanding how AI reaches its conclusions, you can trust its work and build upon it with confidence. 

“Thomson Reuters latest integration of advanced AI models into its core platforms marks an encouraging step forward in legal technology,” said Colleen Nihill, Chief AI & KM Officer at Morgan Lewis. “Deep Research stands out for its ability to reason through legal questions rather than simply return search results. When faced with a complex issue, it can generate a research plan, explain its logic, and deliver a structured report. This level of transparency is essential to maintaining the oversight and trust lawyers need to confidently adopt AI in practice.”  

From Task Completion to Strategic Delegation 

The guided workflows in CoCounsel Legal take this concept even further. Rather than handling individual tasks, these multi-step agentic workflows tackle entire legal processes – from drafting complaints to reviewing deposition transcripts. Each workflow integrates legal content, applies structured reasoning, and ensures human oversight by design. 

As our Chief Product Officer David Wong said:

“This is where AI starts to feel less like a tool and more like a teammate. Guided workflows are how professionals start delegating – not just prompting – and that’s a huge leap forward … “ 

This transformational shift from prompting to delegating isn’t just about efficiency, either; it’s about enabling legal professionals to focus on what they do best: strategic thinking, counseling, and complex problem-solving. With AI handling foundational research and routine workflows, lawyers can dedicate more time to high-value work. 

The Future of Legal AI 

Agentic AI is redefining the relationship between legal professionals and technology. We’re moving from AI as an adjunct to AI as an indispensable part of the legal process, driving real outcomes in litigation, transactional work, and regulatory analysis. CoCounsel Legal isn’t just an advancement; it’s a fundamental shift in how legal work gets done. 

The future of legal practice isn’t about humans versus AI – it’s about humans empowered by AI they can delegate to and trust. With CoCounsel Legal, that future is here today. 

But legal research is a multi-step process, where researchers iteratively review what’s been found and intelligently alter course based on new information. And they don’t just search. They use a wide variety of research tools to find relevant information in ways that can be far more efficient and effective when combined with search. With agentic AI, we can emulate the best practices of great researchers using the full research toolset Westlaw has to offer, tools like Key Numbers, KeyCite, Precision Research classifications, and statutes annotations.

Today we’re introducing Deep Research: an AI-native legal research system that doesn’t just summarize search results. It plans, reviews, and strategizes like a great researcher would, and it uses the full set of research tools Westlaw has to offer. Not only does Deep Research emulate the best practices of savvy researchers, but its AI agents use research tools in parallel, making research exponentially faster. What used to take hours now takes minutes and what used to be manual is now orchestrated by AI agents designed specifically for the legal domain.

What Makes Deep Research Different

While others layer generic AI on top of legal content, we’ve built something fundamentally more advanced: AI agents trained, equipped, and trusted to use Westlaw’s exclusive research toolset with the curated and up-to-date content of Westlaw and Practical Law to move through complex legal research workflows with unprecedented speed and precision.

These AI agents are:

• Instructed by the experienced attorneys from Westlaw and Practical law how to approach legal research like an expert
• Equipped with Westlaw’s exclusive research toolset, including Key Numbers, KeyCite, Precision Research classifications, statute annotations, and more
• Fueled by Westlaw and Practical Law’s up-to-date curated legal content
• Guided by orchestration logic grounded in decades of domain-specific workflow expertise

We’ve spent more than a year pushing AI frontier models to their limits in legal research workflows. We’ve tested where they succeed and fail. We’ve studied how they reason and what it takes to make them behave like thoughtful legal researchers. We’ve designed for long-document comprehension, multistep reasoning, and structured tool usage, all while working with domain-specific legal content and workflows.

And we didn’t do it alone. We reviewed and tested the designs, plans, and capabilities of Deep Research with over 1,200 customers to make sure we built it right. This isn’t just a simple connection to the off-the-shelf deep research capabilities of major LLM providers. It is a product transformation rooted in real testing, real constraints, and real customer experiences and expectations. This level of AI agent autonomy, reasoning, and transparency will define future workflows, and we’re excited to bring it to our customers for legal research.

To see it in action, watch the demo:

Seamless Integration with CoCounsel

Deep Research is featured prominently on the homepage of our new version of Westlaw, Westlaw Advantage, and it’s also fully embedded into the CoCounsel experience, so our customers can access it through the cutting-edge guided workflows in CoCounsel Legal.

Built for What’s Next

Deep Research will be available in Westlaw Advantage and CoCounsel Legal next week! I’m so excited for our customers to use it, and I’m beyond grateful for the enormously talented teams of experts at Thomson Reuters who have worked tirelessly to bring Deep Research to our customers. It’s a huge leap forward and yet, still, just the beginning. We see so much potential for developing this technology even further into legal workflows and thrilled about the breakthroughs to come. Stay tuned!

Thomson Reuters is proud to join the Coalition for Secure AI (CoSAI)—a cross-industry initiative dedicated to advancing security standards for AI systems. Together with organizations including Google, Microsoft, IBM, NVIDIA, Dell Technologies, and PayPal, we’ve contributed to a newly released white paper: Establish Risks and Controls for the AI Supply Chain (v1.0) 

This work outlines a powerful truth: AI systems are not like traditional software.
Their attack surfaces include poisoned training data, tampered model weights, insecure plugin ecosystems, and compromised inference infrastructure. 

Our Thomson Reuters Contributors 

We’d like to recognize several of our security and AI leaders at Thomson Reuters who helped shape this industry-wide framework: 

• Yassine Ilmi – Director, Product Security 
• Arbër Salihi – Lead Product Security Engineer 
• Lorenzo Verstraeten – Manager, Responsible AI Technology 
• Danilo Tommasina – Distinguished Engineer, Labs 
• Ramdev Wudali – Distinguished Engineer, Core AI & Data Platforms 

Their expertise reflects our commitment to secure-by-design practices and our belief that AI innovation must go hand in hand with transparency, accountability, and governance. 

Read the blog and full paper here. 

This work was developed by the Coalition for Secure AI (CoSAI), with contributions from security, engineering, and research teams across leading organizations.