As cloud venture monitoring software program monday.com’s engineering group scaled previous 500 builders, the crew started to really feel the pressure of its personal success. Product strains have been multiplying, microservices proliferating, and code was flowing quicker than human reviewers might sustain. The corporate wanted a method to evaluate hundreds of pull requests every month with out drowning builders in tedium — or letting high quality slip.
That’s when Man Regev, VP of R&D and head of the Development and monday Dev groups, began experimenting with a brand new AI device from Qodo, an Israeli startup centered on developer brokers. What started as a light-weight check quickly turned a essential a part of monday.com’s software program supply infrastructure, as a brand new case examine launched by each Qodo and monday.com right this moment reveals.
“Qodo doesn’t really feel like simply one other device—it’s like including a brand new developer to the crew who truly learns how we work," Regev informed VentureBeat in a current video name interview, including that it has "prevented over 800 points per thirty days from reaching manufacturing—a few of them might have triggered critical safety vulnerabilities."
In contrast to code technology instruments like GitHub Copilot or Cursor, Qodo isn’t attempting to write down new code. As a substitute, it focuses on reviewing it — utilizing what it calls context engineering to grasp not simply what modified in a pull request, however why, the way it aligns with enterprise logic, and whether or not it follows inner finest practices.
"You’ll be able to name Claude Code or Cursor and in 5 minutes get 1,000 strains of code," mentioned Itamar Friedman, co-founder and CEO of Qodo, in the identical video name interview as with Regev. "You have got 40 minutes, and you may't evaluate that. So that you want Qodo to really evaluate it.”
For monday.com, this functionality wasn’t simply useful — it was transformative.
Code Assessment, at Scale
At any given time, monday.com’s builders are delivery updates throughout a whole lot of repositories and providers. The engineering org works in tightly coordinated groups, every aligned with particular components of the product: advertising, CRM, dev instruments, inner platforms, and extra.
That’s the place Qodo got here in. The corporate’s platform makes use of AI not simply to test for apparent bugs or fashion violations, however to guage whether or not a pull request follows team-specific conventions, architectural pointers, and historic patterns.
It does this by studying from your personal codebase — coaching on earlier PRs, feedback, merges, and even Slack threads to grasp how your crew works.
"The feedback Qodo offers aren’t generic—they mirror our values, our libraries, even our requirements for issues like characteristic flags and privateness," Regev mentioned. "It’s context-aware in a approach conventional instruments aren’t."
What “Context Engineering” Really Means
Qodo calls its secret sauce context engineering — a system-level strategy to managing every part the mannequin sees when making a call.
This consists of the PR code diff, after all, but in addition prior discussions, documentation, related recordsdata from the repo, even check outcomes and configuration information.
The concept is that language fashions don’t actually “assume” — they predict the following token based mostly on the inputs they’re given. So the standard of their output relies upon nearly completely on the standard and construction of their inputs.
As Dana Effective, Qodo’s group supervisor, put it in a weblog publish: “You’re not simply writing prompts; you’re designing structured enter beneath a hard and fast token restrict. Each token is a design resolution.”
This isn’t simply principle. In monday.com’s case, it meant Qodo might catch not solely the apparent bugs, however the delicate ones that usually slip previous human reviewers — hardcoded variables, lacking fallbacks, or violations of cross-team structure conventions.
One instance stood out. In a current PR, Qodo flagged a line that inadvertently uncovered a staging setting variable — one thing no human reviewer caught. Had it been merged, it might need triggered issues in manufacturing.
"The hours we might spend on fixing this safety leak and the authorized situation that it might deliver could be far more than the hours that we scale back from a pull-request," mentioned Regev.
Integration into the Pipeline
In the present day, Qodo is deeply built-in into monday.com’s improvement workflow, analyzing pull requests and surfacing context-aware suggestions based mostly on prior crew code opinions.
“It doesn’t really feel like simply one other device… It looks like one other teammate that joined the system — one who learns how we work," Regev famous.
Builders obtain recommendations in the course of the evaluate course of and stay in charge of closing selections — a human-in-the-loop mannequin that was essential for adoption.
As a result of Qodo built-in immediately into GitHub by way of pull request actions and feedback, Monday.com’s infrastructure crew didn’t face a steep studying curve.
“It’s only a GitHub motion,” mentioned Regev. “It creates a PR with the checks. It’s not like a separate device we needed to study.”
“The aim is to really assist the developer study the code, take possession, give suggestions to one another, and study from that and set up the requirements," added Friedman.
The Outcomes: Time Saved, Bugs Prevented
Since rolling out Qodo extra broadly, monday.com has seen measurable enhancements throughout a number of groups.
Inside evaluation reveals that builders save roughly an hour per pull request on common. Multiply that throughout hundreds of PRs per thirty days, and the financial savings rapidly attain hundreds of developer hours yearly.
These aren’t simply beauty points — many relate to enterprise logic, safety, or runtime stability. And since Qodo’s recommendations mirror monday.com’s precise conventions, builders usually tend to act on them.
The system’s accuracy is rooted in its data-first design. Qodo trains on every firm’s non-public codebase and historic information, adapting to totally different crew kinds and practices. It doesn’t depend on one-size-fits-all guidelines or exterior datasets. Every thing is tailor-made.
From Inside Software to Product Imaginative and prescient
Regev’s crew was so impressed with Qodo’s influence that they’ve began planning deeper integrations between Qodo and Monday Dev, the developer-focused product line monday.com is constructing.
The imaginative and prescient is to create a workflow the place enterprise context — duties, tickets, buyer suggestions — flows immediately into the code evaluate layer. That approach, reviewers can assess not simply whether or not the code “works,” however whether or not it solves the precise drawback.
“Earlier than, we had linters, hazard guidelines, static evaluation… rule-based… you could configure all the foundations," Regev mentioned. "However it doesn’t know what you don’t know… Qodo… feels prefer it’s studying from our engineers.”
This aligns intently with Qodo’s personal roadmap. The corporate doesn’t simply evaluate code. It’s constructing a full platform of developer brokers — together with Qodo Gen for context-aware code technology, Qodo Merge for automated PR evaluation, and Qodo Cowl, a regression-testing agent that makes use of runtime validation to make sure check protection.
All of that is powered by Qodo’s personal infrastructure, together with its new open-source embedding mannequin, Qodo-Embed-1-1.5B, which outperformed choices from OpenAI and Salesforce on code retrieval benchmarks.
What’s Subsequent?
Qodo is now providing its platform beneath a freemium mannequin — free for people, discounted for startups by way of Google Cloud’s Perks program, and enterprise-grade for firms that want SSO, air-gapped deployment, or superior controls.
The corporate is already working with groups at NVIDIA, Intuit, and different Fortune 500 firms. And because of a current partnership with Google Cloud, Qodo’s fashions can be found immediately inside Vertex AI’s Mannequin Backyard, making it simpler to combine into enterprise pipelines.
"Context engines would be the large story of 2026," Friedman mentioned. "Each enterprise might want to construct their very own second mind if they need AI that truly understands and helps them."
As AI methods develop into extra embedded in software program improvement, instruments like Qodo are displaying how the precise context — delivered on the proper second — can remodel how groups construct, ship, and scale code throughout the enterprise.
Keep forward of the curve with NextBusiness 24. Discover extra tales, subscribe to our e-newsletter, and be part of our rising group at nextbusiness24.com
