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 had been multiplying, microservices proliferating, and code was flowing sooner than human reviewers may sustain. The corporate wanted a technique to assessment 1000’s 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 Progress and monday Dev groups, began experimenting with a brand new AI software from Qodo, an Israeli startup centered on developer brokers. What started as a light-weight take a look at quickly turned a essential a part of monday.com’s software program supply infrastructure, as a brand new case research launched by each Qodo and monday.com immediately reveals.
“Qodo doesn’t really feel like simply one other software—it’s like including a brand new developer to the crew who truly learns how we work," Regev informed VentureBeat in a latest video name interview, including that it has "prevented over 800 points per 30 days from reaching manufacturing—a few of them may have brought on severe safety vulnerabilities."
Not like code era instruments like GitHub Copilot or Cursor, Qodo isn’t attempting to jot down new code. As a substitute, it makes a speciality of reviewing it — utilizing what it calls context engineering to know not simply what modified in a pull request, however why, the way it aligns with enterprise logic, and whether or not it follows inner greatest practices.
"You may name Claude Code or Cursor and in 5 minutes get 1,000 strains of code," stated Itamar Friedman, co-founder and CEO of Qodo, in the identical video name interview as with Regev. "You will have 40 minutes, and you’ll't assessment that. So that you want Qodo to truly assessment it.”
For monday.com, this functionality wasn’t simply useful — it was transformative.
Code Overview, at Scale
At any given time, monday.com’s builders are transport updates throughout a whole bunch of repositories and companies. The engineering org works in tightly coordinated groups, every aligned with particular elements of the product: advertising and marketing, 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 verify for apparent bugs or type violations, however to judge whether or not a pull request follows team-specific conventions, architectural tips, and historic patterns.
It does this by studying from your individual codebase — coaching on earlier PRs, feedback, merges, and even Slack threads to know how your crew works.
"The feedback Qodo offers aren’t generic—they mirror our values, our libraries, even our requirements for issues like function flags and privateness," Regev stated. "It’s context-aware in a manner conventional instruments aren’t."
What “Context Engineering” Really Means
Qodo calls its secret sauce context engineering — a system-level strategy to managing every thing the mannequin sees when making a choice.
This consists of the PR code diff, after all, but additionally prior discussions, documentation, related information from the repo, even take a look at outcomes and configuration knowledge.
The concept is that language fashions don’t actually “assume” — they predict the following token primarily based on the inputs they’re given. So the standard of their output relies upon virtually totally on the standard and construction of their inputs.
As Dana Nice, Qodo’s group supervisor, put it in a weblog put up: “You’re not simply writing prompts; you’re designing structured enter below a hard and fast token restrict. Each token is a design choice.”
This isn’t simply concept. In monday.com’s case, it meant Qodo may catch not solely the plain bugs, however the refined ones that usually slip previous human reviewers — hardcoded variables, lacking fallbacks, or violations of cross-team structure conventions.
One instance stood out. In a latest PR, Qodo flagged a line that inadvertently uncovered a staging surroundings variable — one thing no human reviewer caught. Had it been merged, it may need brought on issues in manufacturing.
"The hours we might spend on fixing this safety leak and the authorized concern that it could carry could be far more than the hours that we scale back from a pull-request," stated Regev.
Integration into the Pipeline
Right this moment, Qodo is deeply built-in into monday.com’s improvement workflow, analyzing pull requests and surfacing context-aware suggestions primarily based on prior crew code evaluations.
“It doesn’t really feel like simply one other software… It seems like one other teammate that joined the system — one who learns how we work," Regev famous.
Builders obtain recommendations through the assessment course of and stay in command of last selections — a human-in-the-loop mannequin that was essential for adoption.
As a result of Qodo built-in instantly 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,” stated Regev. “It creates a PR with the assessments. It’s not like a separate software we needed to be taught.”
“The aim is to truly assist the developer be taught the code, take possession, give suggestions to one another, and be taught 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.
Inner evaluation reveals that builders save roughly an hour per pull request on common. Multiply that throughout 1000’s of PRs per 30 days, and the financial savings rapidly attain 1000’s 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 personal codebase and historic knowledge, adapting to completely different crew types and practices. It doesn’t depend on one-size-fits-all guidelines or exterior datasets. The whole lot is tailor-made.
From Inner Device 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 instantly into the code assessment layer. That manner, reviewers can assess not simply whether or not the code “works,” however whether or not it solves the suitable drawback.
“Earlier than, we had linters, hazard guidelines, static evaluation… rule-based… you have to configure all the principles," Regev stated. "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 assessment code. It’s constructing a full platform of developer brokers — together with Qodo Gen for context-aware code era, Qodo Merge for automated PR evaluation, and Qodo Cowl, a regression-testing agent that makes use of runtime validation to make sure take a look at 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 below a freemium mannequin — free for people, discounted for startups by means 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 due to a latest partnership with Google Cloud, Qodo’s fashions can be found instantly inside Vertex AI’s Mannequin Backyard, making it simpler to combine into enterprise pipelines.
"Context engines would be the huge story of 2026," Friedman stated. "Each enterprise might want to construct their very own second mind if they need AI that truly understands and helps them."
As AI techniques grow to be extra embedded in software program improvement, instruments like Qodo are exhibiting how the suitable context — delivered on the proper second — can rework how groups construct, ship, and scale code throughout the enterprise.
