Ivo works where you work

Ivo has recently launched one of our most highly requested features. Users can now bulk upload documents with Ivo Assistant in both PDF and Docx formats. Using Assistant, you can quickly and easily compare and contrast documents or extract key data. 

Using Assistant, if you have several versions of an agreement and want to know the differences between them, you can now upload all versions and ask Assistant to generate a table of its findings, all within your existing workflow. 

This feature is also useful for fact extraction. You can query a large batch of documents by asking something like, “What do each of the documents I uploaded say about termination rights or the effective date?” or “Please extract the key facts and generate a table of the results.” 

Here are more ideas of prompts you can use in Assistant with the bulk upload feature: 

• Draft a customized reverse engineering provision for this agreement based on the uploaded documents.
• Revise the notice period required to terminate this Agreement to align with the notice provision in the uploaded agreements.
• Compare the uploaded documents and summarize the governing laws provisions.
• What are our obligations in the event of a data breach under the uploaded agreements?
• Redline the confidential information definition in this agreement against the uploaded template.

Want to see how this feature can transform your workflows? Schedule a demo! 

Metropolis, the largest parking operator in the US, has adopted Ivo’s AI-powered Contract Review platform to streamline and speed up the contract review process. Metropolis will be using Ivo to ensure consistency and accuracy in its contract review workflows. 

Metropolis is famous for using technology to solve real-world logistics problems. Companies in these industries know that speed is a competitive advantage, yet legal teams are often mired in laborious contract review processes. Accuracy and consistency is also a concern for teams with multiple lawyers, so having a single source of truth for standards and procedures will be invaluable for the legal team.

Accuracy and consistency are non-negotiables when it comes to contract review. But lawyers everywhere are challenged by dense, lengthy contracts that must be reviewed by multiple parties. Ivo makes analyzing, comparing, and reviewing contracts trivially easy, shortening processes that normally can take years into just a few weeks. 

“We’re pleased that logistics leaders like Metropolis are using Ivo to speed up contract review,” said Min-Kyu Jung, CEO and co-founder of Ivo. “It’s fantastic to see how Metropolis is using Ivo to help its legal team achieve strategic impact for the business.” 

Across the logistic sector, legal teams are reimagining their workflows with Ivo’s AI-powered contract review platform. With custom playbooks that deliver surgical redlines and consistent insights, Ivo helps legal teams achieve surgical accuracy and consistency, saving up to 75% of the time spent on manual contract review.

Find out how Ivo is helping companies in every industry re-imagine the contract review process.

Ivo’s latest product release is Research — a concise, report-style legal tool that uses authoritative sources and trusted inline citations for all of your legal research needs. 

Research uses a dataset that has been created with high-quality primary and secondary legal sources. Ivo’s Research feature conducts all research exclusively within this dataset, ensuring precise and reliable outputs, rather than relying on generic web sources which could produce inaccurate results. 

In the US, those sources include EDGAR / SEC Filings, U.S. Code and Congress.gov, eCFR and the Federal Register, as well as reputable indexes for court case retrieval. For questions involving EU matters, we use materials from official EU portals (Companies House, Parliament, Court of Justice). 

To further ensure reliability, we have ensured that each claim in a Research report is cited inline at the sentence level. Additionally, we avoid indirect citations. If a case quotes a statute, we cite the statute directly; if a case cites another case, we find and cite the original. Quotes are also cited against the source and pinpoint to specific sections. Finally, for broad propositions, Research will generate multiple authorities and reasoning excerpts — not a single, superficial citation.

Research is also able to understand context about your company through the Company Profile feature. For example, if Ivo knows that your company is located in California, without specifying the jurisdiction in your prompt, Research will look to California-specific statutes, regulations, and case law. For mixed federal-state or multi‑state questions, Research organizes your report into clearly labeled jurisdictional sections.

The new Research feature uses a number of cooperating agents to double‑check work: a retrieval agent (finds and deduplicates sources), an authority/ranking agent (promotes primary law), a cite‑checker (verifies text and pinpoints citations), a conflict reviewer (flags contradictory authorities), and a gap detector (signals when evidence is thin rather than speculating). 

The results from Research come as a comprehensive legal memo. You’ll find Issue, Brief Answer, and Analysis with inline, sentence‑level citations next to each assertion. Authorities are clickable back to the source. You can also download the memo as a separate Word document.

Schedule a demo to see how Research would work in your workflow. 

My favorite part about attending events with Ivo is hearing legal professionals talk about what they’re interested in and challenged by with new technology.

I attended SOLID Atlanta and got a chance to have in-depth conversations with both in-house counsel and lawyers from firms around the country... We talked about how legal professionals’ role has become less   about the universe of knowledge that they need to have access to, but more about their ability to provide judgment and a wise legal perspective. And despite having comfort with AI tools, they (and myself as a member of this community) still believes strongly that having a human element in the AI process is critical for organizations to be successful in 2025 and beyond. They also noted that senior leadership is no longer skeptical of innovation, but hesitation breeds from knowing which tools are worth investing in and which are not. I heard how the current legal SaaS business model is at odds with how legal teams buy. Often CFOs have a budget for just one tool for Legal — e.g. a CLM — but current tech is sold in modules - this is somewhat new for in-house teams to need resources for multiple tools. 

The two biggest concerns that were shared last week that I feel I personally can impact are   the need to ensure end-user adoption and integration in the existing workflow. This is where AI companies can do better to provide support and implementation that leads to successful and repeatable outcomes.  In-house counsel in particular need assurances that the AI products that they are buying will be adopted by the end users, or they will not hesitate to walk away from the purchase. 

My takeaways from SOLID Atlanta were that attorneys are well aware that AI was changing their role and moving them from knowledge gatekeepers to strategic advisors. And they were open to that shift as long as they could bring their judgment and trusted colleagues  along on the journey. 

Take a look at how companies in numerous industries have reimagined their legal workflows with Ivo. 

Software projects are notorious for blowing past their projected timelines. Despite numerous techniques to try to mitigate this, delays and cost overruns are the norm, and have been forever. This is illustrated by such phenomena as the Ninety-Ninety Rule:

The first 90 percent of the code accounts for the first 90 percent of the development time. The remaining 10 percent of the code accounts for the other 90 percent of the development time.

Most software projects follow a long-tailed lifecycle. In the beginning, progress is fast as the basic functionality is built out. Whether you're building a peer-to-peer networking library, an AI contract review product or a self-driving car, you can probably quickly knock out something demo-ready. You might even convince people to buy it! But there will be bugs - holes in your logic, or edge cases you haven't considered. Your demo software will be filled with bugs, and your typical user will complain that your software is "crap."

The process of going from demo software to mature software is the process of hammering down the long tail of bugs. How long will you have to hammer for? It depends on the domain.

A wise man once said:

grug understand all programmer platonists at some level wish music of spheres perfection in code. but danger is here, world is ugly and gronky many times and so also must code be

The insight we can draw from Grug's words is that, the closer your problem is to the "ugly and gronky" real world, the longer and fatter the tail will be.

Self-driving cars are very close to the real world, so their tail is long. The DARPA Grand Challenge was in 2004, and after twenty years of hammering down the tail, Waymo still only operates in five cities. Peer-to-peer networking libraries only have to deal with other computers, so their tail is relatively minuscule - Bitcoin is still running on the same chain debuted by Satoshi Nakamoto in 2009.

Ivo's domain sits in the middle. We’re not driving cars, but after decades of evolution, Microsoft Word barely qualifies as "software" anymore - rather it's some semi-organic digital lifeform that no human fully understands. Contracts, while they bear deceptive resemblance to trees and other familiar datastructures, are unapologetically and often deliberately flawed human constructions. And LLMs...don't get me started on LLMs.

The result of this is it's easy to build demo-ready contracting software, but the road to non-crap contracting software involves hammering down a very long tail.

Hammering down the tail

In 2014, I interned on a self-driving car team. The engineers had a team-wide mandate to increase our "Miles-Per-Intervention" (MPI) to 1 million. My memory is fuzzy, but when I joined, I think our MPI was around 0.7. Every week, we would have an org-wide meeting where we went through every single incident where a human driver had had to intervene.

All sorts of stuff came up in the meeting. There was one t-junction in Mountain View where the double-yellow lines extended out pretty far, and rather than risk clipping the painted lines as it cut the corner, the car would just stall forever. There was another intersection where the setting sun would reflect off the red traffic light, making it look active even when the light was green. Also, one time, they took the car to Arizona and it thought all the cactuses were people.

All the interventions were filed as bugs and assigned to the appropriate teams, who would diligently fix them. Fixing some of these bugs was hard. Entire modules had to be written, others thrown away, others endlessly tweaked. By the time my internship ended, the combined efforts of all these dozens of brilliant hard-working people had pushed our MPI to slightly above 1.

The main reason why there aren't that many self-driving car companies is because most software teams don't have the patience or diligence to take on a multi-decade bugfixing marathon. It's much more satisfying to work far away from the real world and chase music of spheres perfection. At Ivo, we're grateful that our domain isn't as long-tail as a self-driving car. Still, in a domain where it's easy to build a demo-ready solution, our willingness to spend months and years hammering down the tail is our biggest competitive advantage.

Our threshold for what qualifies as a "bug" is very low. Basically, any time our software does something worse than a human, it's a bug - even if it hasn't done anything technically "incorrect".

After the redlines have been applied and the changes have been accepted, all of these diffs result in the exact same text in the document. They all do the same thing, so in a sense, they're all "correct." But the leftmost diff is unnatural. It's noisy and hard to understand. Moving from the leftmost screenshot to the middle screenshot took us around a year and a half of iteration on a "diff coalescing algorithm," which we hammered down bug report after bug report. Our diff.js file is now over a thousand lines, and diff.test.js is even longer.

The middle screenshot still has a problem though - the words "if Metadata becomes aware of a" are redundantly removed and reinserted. This is a particularly tricky case because the string "if Metadata becomes aware of a" constitutes the suffix of the deletion and the prefix of the insertion, so even though the redundancy is obvious to a human, it's hard for a computer to efficiently detect. This bug was assigned to our newest full-time engineer, and he was able to figure out a clever way to modify the KMP algorithm to detect the redundancy in linear time and coalesce it into the final result on the right.

The reason that Ivo has the best redlining on the market has nothing to do with AI, and everything to do with an extraordinarily talented engineering team who is willing to spend years diligently hammering down the long tail.

Do you want to build something great too? Join us! 

The Ivo team joined thousands of legal professionals in Philadelphia recently for the Association of Corporate Counsel Annual Meeting. The team met dozens of lawyers and legal ops professionals in every industry and working for companies of every size, and a prominent theme that emerged is that small, lean legal teams are overwhelmed with high volumes of work and are hoping that AI can help.

In numerous conversations that the team had with legal professionals, we heard the same stories over and over again:

• Teams have C-suite mandates to “start using AI,” but are overwhelmed by the sheer number of options, all of whom promise very similar benefits, and don’t know how to determine what good looks like or even how to distinguish one vendor from another. “It’s a tough time to be a buyer right now,” one person observed, noting that there are so many contract review vendors in particular that all sound the same.
• Wasting time is a major pain point for in-house legal teams. Legal professionals spend hours, or sometimes even days, reviewing and redlining contracts, and are eager to find a way to reduce this workload. In addition, if legal teams wanted to find any insights in the content, it would take them hours. We heard one story about a GC who tried to analyze their contracts by hand in their CLM. “There went five hours,” she said.
• Trying to access data that lives in a CLM is a laborious and tedious process. Many people were interested in solutions that would make that workflow easier.

For us, there were three key takeaways:

• Overwhelmed teams are anxious to use AI to ease their workload. While they may already have a mandate from their company leadership to use AI, they’re already interested in the technology. They just need to know how to select a vendor.
• Legal teams are anxious to prove their importance to the business and the ROI of their time and effort. Contract intelligence might be the way to do that, but getting the insights out of contracts is such a laborious process.
• CLMs no longer work for what lawyers need to do with their contracts. They’re fine for storage, but as soon as legal professionals need to do anything with their contracts, their limitations in search and information retrieval become very clear.

We hear the message loud and clear: The market for legal tech has matured at an incredible rate in the last few months. Teams want to use AI to clear out their workloads, and want to understand what technology is available and guidance on how to select tools.

Take a look at this webinar to get more advice on how in-house counsel should use AI tools.

F5, a technology leader specializing in app delivery and cybersecurity, has partnered with Ivo to streamline and simplify its contract review workflows. Ivo’s ease of use, integration into the team’s existing workflows, and the breadth of features were cited as reasons why F5 chose to partner with Ivo.

Many technology companies struggle with managing complex contract review workflows  while ensuring consistency and accuracy. In addition, legal teams must work with complex contract amendments which often include large volumes of new terms. 

Ivo’s ability to analyze and ensure consistency across multiple documents as well as the ease of use and integration into existing workflows leads to greater efficiency and ease in managing contracts. Plus, Ivo’s approach of training its AI models with custom-built playbooks, created by lawyers, leads to not only standardizing processes across companies, but allows for a personalized approach to contract review. 

“We’re thrilled that a company like F5 has chosen to partner with Ivo to streamline and standardize their contract review workflows,” said Min-Kyu Jung, the CEO and co-founder of Ivo. “For technology leaders, speed is a competitive edge. The efficiency gains that F5 will experience as a result of re-imagining their contract workflows will help their legal team spend their time on more strategic outcomes for the business.” 

F5’s partnership with Ivo highlights that there’s no need to make a choice between efficiency and accuracy. Rethinking the tedium of manual contract review means that legal teams can spend their time on strategic work that will contribute to the business’ bottom line.

See a demo to find out how Ivo could be part of your workflow. 

Ivo Assistant is an exciting and powerful feature in our product because it allows you to ask plain-language  questions about your contracts just like you would ask a colleague. Assistant is an agentic legal partner that allows you to review, redline, and get instant answers from your contracts and trusted sources using ordinary language prompts. When combined with Repository, you can get immediate insights, discover risks, and track patterns across all of your agreements. 

Our customers love Assistant because it’s such a powerful tool that’s also easy to use. But, like any AI tool, if you prompt it well, it will give you better answers than if you prompt it poorly. 

Here are the top 10 secrets to great prompts for Ivo Assistant:

1. Define your goal.  Before typing your prompt, ask: What am I trying to achieve?
- Good: Summarize this 10-page contract into five key takeaways for executives.
- Not-as-good: Summarize this.

2. Provide context and constraints. AI works best with background, audience, and boundaries.
- Good: Draft an email memo for my sales team. Be sure to include details about the deal size, contract term, and any other context that would be relevant to a sales organization.
- Not-as-good: Draft an email for my sales team.

3. Specify tone, style, or role. Assign a persona to shape the response:
- Good: Act as a product trainer. Explain how the new repository feature works in simple steps.

4. Break down complex requests into simple ones. Split complex requests into steps for clarity.
- Good: 1) Generate subject lines → 2) Draft email → 3) Refine.

5. Iterate and refine. First drafts are rarely final. Don’t be afraid to follow up.
- Examples: “Make it concise.” “Add 3 data points.”

6. Use examples and templates. Show what good looks like. Examples act as guardrails and improve accuracy.

7. Experiment with prompt styles. Try direct instructions, open-ended questions, or comparative framing.

8. Watch out for pitfalls. You want to make sure that your prompts aren’t too vague, because you’ll get generic answers. Avoid prompts that are too long, because the tool may miss details. And if your prompts are unclear, the answers may be off-target.

9. Consider some helpful prompt frameworks:
- Role + Task + Context + Format + Tone
- C.R.I.S.P.: Context, Role, Instructions, Specifications, Purpose

10. Remember the Golden Rule. Treat AI like a smart junior lawyer, not a mind reader. Give it clear instructions, check its work, and refine.

As a cheat sheet, here are the top five things to think about when creating great prompts:

• Be specific
• Add context (who/what/why)
• Define format (bullets, table, paragraph)
• Assign role or tone
• Iterate

Take a look to see more of what Assistant can do for you.

The Aldo Group, a leading multinational retailer specializing in shoes and accessories, has chosen Ivo to accelerate and streamline its review contract. The in-house legal team was excited to select Ivo to ensure consistency and speed across all of its contract review workflows. 

Retailers deal with dozens of contracts, if not more, on a daily basis. And for a retailer that operates across multiple countries like the Aldo Group, a universal approach to documents is very important. Ivo’s implementation of custom playbooks with our customers’ own standard terms means that customers can ensure consistent application of their own positions every time. And of course, having the standard positions already implemented in Ivo means the tool can detect and flag deviations from those positions for a lawyer to review quickly and easily. 

We are proud to work with The Aldo Group as they re-imagine their contract workflow for speed and consistency across their global team, said Min-Kyu Jung, the co-founder and CEO of Ivo. 

Ivo’s contract review platform allows legal teams to review contracts up to 75% faster while maintaining their unique standards and positions. Ivo reads and interprets complex contracts exactly as a lawyer would, providing surgical redlines directly in legal teams’ existing workflows. 

A growing number of retailers are implementing Ivo to make their contract workflows simpler and more consistent. Ivo delivers accurate, precise redlines in a fraction of the time it takes to manually review contracts, helping legal teams work smarter, not harder. 

Learn more about how Ivo could help your company transform contract review here.