\n
![](\"https:\/\/images.ctfassets.net\/jdtwqhzvc2n1\/6ITdq6fWHUqQToLpa2LMjE\/9071464cc3dabd3e163518c89f5eb3b2\/cfr0z3n_aerial_view_extended_view_of_hundreds_of_software_devel_dac48c75-82c8-48b8-9ca4-ff785e9ba5f3.png?w=300&q=30\")
<\/p>\n
\n<\/p>\n
As cloud project tracking software monday.com\u2019s engineering organization scaled past 500 developers, the team began to feel the strain of its own success. Product lines were multiplying, microservices proliferating, and code was flowing faster than human reviewers could keep up. The company needed a way to review thousands of pull requests each month without drowning developers in tedium \u2014 or letting quality slip.<\/p>\n
That\u2019s when Guy Regev, VP of R&D and head of the Growth and monday Dev teams, started experimenting with a new AI tool from Qodo, an Israeli startup focused on developer agents. What began as a lightweight test soon became a critical part of monday.com\u2019s software delivery infrastructure, as a new case study released by both Qodo and monday.com today reveals. <\/p>\n
\u201cQodo doesn\u2019t feel like just another tool\u2014it\u2019s like adding a new developer to the team who actually learns how we work," Regev told VentureBeat in a recent video call interview, adding that it has "prevented over 800 issues per month from reaching production\u2014some of them could have caused serious security vulnerabilities."<\/p>\n
Unlike code generation tools like GitHub Copilot or Cursor, Qodo isn\u2019t trying to write new code. Instead, it specializes in reviewing it \u2014 using what it calls context engineering<\/b> to understand not just what changed in a pull request, but why, how it aligns with business logic, and whether it follows internal best practices. <\/p>\n
"You can call Claude Code or Cursor and in five minutes get 1,000 lines of code," said Itamar Friedman, co-founder and CEO of Qodo, in the same video call interview as with Regev. "You have 40 minutes, and you can't review that. So you need Qodo to actually review it.\u201d<\/p>\n
For monday.com, this capability wasn\u2019t just helpful \u2014 it was transformative.<\/p>\n
At any given time, monday.com\u2019s developers are shipping updates across hundreds of repositories and services. The engineering org works in tightly coordinated teams, each aligned with specific parts of the product: marketing, CRM, dev tools, internal platforms, and more.<\/p>\n
That\u2019s where Qodo came in. The company\u2019s platform uses AI not just to check for obvious bugs or style violations, but to evaluate whether a pull request follows team-specific conventions, architectural guidelines, and historical patterns. <\/p>\n
It does this by learning from your own codebase \u2014 training on previous PRs, comments, merges, and even Slack threads to understand how your team works.<\/p>\n
"The comments Qodo gives aren\u2019t generic\u2014they reflect our values, our libraries, even our standards for things like feature flags and privacy," Regev said. "It\u2019s context-aware in a way traditional tools aren\u2019t."<\/p>\n
Qodo calls its secret sauce context engineering<\/b> \u2014 a system-level approach to managing everything the model sees when making a decision.<\/p>\n
This includes the PR code diff, of course, but also prior discussions, documentation, relevant files from the repo, even test results and configuration data.<\/p>\n
The idea is that language models don\u2019t really \u201cthink\u201d \u2014 they predict the next token based on the inputs they\u2019re given. So the quality of their output depends almost entirely on the quality and structure of their inputs.<\/p>\n
As Dana Fine, Qodo\u2019s community manager, put it in a blog post: \u201cYou\u2019re not just writing prompts; you\u2019re designing structured input under a fixed token limit. Every token is a design decision.\u201d<\/p>\n
This isn\u2019t just theory. In monday.com\u2019s case, it meant Qodo could catch not only the obvious bugs, but the subtle ones that typically slip past human reviewers \u2014 hardcoded variables, missing fallbacks, or violations of cross-team architecture conventions.<\/p>\n
One example stood out. In a recent PR, Qodo flagged a line that inadvertently exposed a staging environment variable \u2014 something no human reviewer caught. Had it been merged, it might have caused problems in production. <\/p>\n
"The hours we would spend on fixing this security leak and the legal issue that it would bring would be much more than the hours that we reduce from a pull-request," said Regev.<\/p>\n
Today, Qodo is deeply integrated into monday.com\u2019s development workflow, analyzing pull requests and surfacing context-aware recommendations based on prior team code reviews. <\/p>\n
\u201cIt doesn\u2019t feel like just another tool… It feels like another teammate that joined the system \u2014 one who learns how we work," Regev noted. <\/p>\n
Developers receive suggestions during the review process and remain in control of final decisions \u2014 a human-in-the-loop model that was critical for adoption.<\/p>\n
Because Qodo integrated directly into GitHub via pull request actions and comments, Monday.com\u2019s infrastructure team didn\u2019t face a steep learning curve.<\/p>\n
\u201cIt\u2019s just a GitHub action,\u201d said Regev. \u201cIt creates a PR with the tests. It\u2019s not like a separate tool we had to learn.\u201d<\/p>\n
\u201cThe purpose is to actually help the developer learn the code, take ownership, give feedback to each other, and learn from that and establish the standards," added Friedman.<\/p>\n
Since rolling out Qodo more broadly, monday.com has seen measurable improvements across multiple teams.<\/p>\n
Internal analysis shows that developers save roughly an hour per pull request on average. Multiply that across thousands of PRs per month, and the savings quickly reach thousands of developer hours annually.<\/p>\n
These aren\u2019t just cosmetic issues \u2014 many relate to business logic, security, or runtime stability. And because Qodo\u2019s suggestions reflect monday.com\u2019s actual conventions, developers are more likely to act on them.<\/p>\n
The system\u2019s accuracy is rooted in its data-first design. Qodo trains on each company\u2019s private codebase and historical data, adapting to different team styles and practices. It doesn\u2019t rely on one-size-fits-all rules or external datasets. Everything is tailored.<\/p>\n
Regev\u2019s team was so impressed with Qodo\u2019s impact that they\u2019ve started planning deeper integrations between Qodo and Monday Dev, the developer-focused product line monday.com is building.<\/p>\n
The vision is to create a workflow where business context \u2014 tasks, tickets, customer feedback \u2014 flows directly into the code review layer. That way, reviewers can assess not just whether the code \u201cworks,\u201d but whether it solves the right problem.<\/p>\n
\u201cBefore, we had linters, danger rules, static analysis… rule-based… you need to configure all the rules," Regev said. "But it doesn\u2019t know what you don\u2019t know… Qodo… feels like it\u2019s learning from our engineers.\u201d<\/p>\n
This aligns closely with Qodo\u2019s own roadmap. The company doesn\u2019t just review code. It\u2019s building a full platform of developer agents \u2014 including Qodo Gen for context-aware code generation, Qodo Merge for automated PR analysis, and Qodo Cover, a regression-testing agent that uses runtime validation to ensure test coverage.<\/p>\n
All of this is powered by Qodo\u2019s own infrastructure, including its new open-source embedding model, Qodo-Embed-1-1.5B, which outperformed offerings from OpenAI and Salesforce on code retrieval benchmarks.<\/p>\n
Qodo is now offering its platform under a freemium model \u2014 free for individuals, discounted for startups through Google Cloud\u2019s Perks program, and enterprise-grade for companies that need SSO, air-gapped deployment, or advanced controls.<\/p>\n
The company is already working with teams at NVIDIA, Intuit, and other Fortune 500 companies. And thanks to a recent partnership with Google Cloud, Qodo\u2019s models are available directly inside Vertex AI\u2019s Model Garden, making it easier to integrate into enterprise pipelines.<\/p>\n
"Context engines will be the big story of 2026," Friedman said. "Every enterprise will need to build their own second brain if they want AI that actually understands and helps them."<\/p>\n
As AI systems become more embedded in software development, tools like Qodo are showing how the right context \u2014 delivered at the right moment \u2014 can transform how teams build, ship, and scale code across the enterprise.<\/p>\n