Blitzy announces PR Review: helping teams understand and merge ai-generated code faster. Sep 28, 2026 New feature helps engineering teams alleviate code review bottlenecks CAMBRIDGE, Mass. September 28, 2026 - Blitzy, the autonomous software development platform for the enterprise, today announced PR Review. A breakthrough feature provides a detailed summary of PRs so teams can quickly understand what's changed in AI-generated pull requests (PRs), why, and merge faster. PR Review provides engineers with context behind code changes. Given the volume of work Blitzy executes, this helps them understand what Blitzy executed and merge faster with confidence, knowing the code follows enterprise standards and accounts for the global estate's dependencies. It answers three questions: what changes in the code, why those edits were made, and that the work is validated and ready to merge. "The AI revolution has shifted the bottleneck in software development from writing code to reviewing it," said Sid Pardeshi, Co-founder and CTO of Blitzy. "PR Review expedites code reviews by highlighting and explaining the key changes with supporting evidence. It gives engineers a clear view of what changed, why, and how the implementation was validated, so that humans can understand and trust the output." As agents generate code faster than humans can review it, and PRs stretch into hundreds of thousands of lines of code, traditional line-by-line review becomes increasingly impractical if not impossible. Blitzy shifts validation left. Before code is generated, engineers declare their intent, then review and approve the scope and approach Blitzy proposes in the Agent Action Plan. In unison with generation, Blitzy integrates QA into the process via automated validation through tests, benchmarks, builds, static analysis, and CI/CD signals. PR Review builds on that foundation by making the remaining human review faster and more focused. It enables teams to: * Review code confidently: The reasoning behind code changes is noted. Implementation decisions are visible, revealing decisions and trade-offs. * See how the work was validated: Blitzy validates the implementation against the technical specification and the codebase context represented in its knowledge graph, then surfaces the relevant testing and QA results alongside the changes. Reviewers see what changed and whether the implementation meets the intended requirements. * Avoid manual reconstruction: File-by-file or line-by-line review is possible if teams want to go deeper than the PR Review. PR Review is available today to all Blitzy customers and Blitzy Sandbox users. The recently launched Sandbox lets eligible organizations reverse-engineer up to 1 million lines of code, generate up to 25,000 lines of E2E-tested code, and surface security vulnerabilities at no cost. About Blitzy. Blitzy is the autonomous software development platform for the enterprise, built to accelerate software development at scale. Blitzy reverse-engineers software estates of 100M+ lines into a dynamic knowledge graph, giving agents system-wide context to plan, build, modernize, and validate software. By orchestrating thousands of agents and state-of-the-art models across each run, Blitzy autonomously executes months of development work, helping Global 2000 enterprises deliver software 5x faster while reducing risk across the development lifecycle.

Blitzy signs Cambridge's largest office deal of 2026, sealing a 52,000-SQFT expansion. Sep 24, 2026, 09:00 ET Blitzy quadruples its headcount at its global headquarters at One Kendall Square, solidifying the campus as a hub for AI innovation. CAMBRIDGE, Mass., Sept. 24, 2026 /PRNewswire/ - Blitzy, the autonomous software development company founded in Cambridge in 2023, has signed a 52,000-rentable-square-foot office lease at One Kendall Square, expanding and keeping its headquarters in its origin city. The transaction is the largest new office lease completed in Cambridge in 2026, according to JLL, which represented Blitzy in the deal. "We're choosing to keep building where we were founded and making an investment in the future of the AI community here," said Brian Elliot, CEO and Co-Founder of Blitzy. "We've transformed from two HBS students with a vision to more than 200 people on-the-ground in Cambridge pushing the frontier of AI and solving enterprises' largest software related problems. This lease gives us room to grow and represents an intentional bet on Cambridge." The lease covers two floors at Building 200 at One Kendall Square and runs five years, with Blitzy expected to take occupancy in Q2 of 2027 following a [39,000]-square-foot build-out. The building is owned by ARE-MA REGION NO. 59, LLC, which is an affiliate of Alexandria Real Estate Equities, Inc. Blitzy raised $200 million in May 2026 at a $1.4 billion valuation in a round led by Northzone and quadrupled its headcount in the first half of 2026. The new space will be built to support more than 300 employees. The company is hiring across engineering, go-to-market and operations. "We're bringing exceptional people together in Cambridge to push the boundaries of what's possible for our customers, "added Nick Denaro, Sr. Director, People & Talent, Blitzy. "As we enter our next phase of growth, we believe the talent to build a category-defining technology company is already here, and we're committed to building it in Cambridge." Blitzy's investment in the greater Boston area is an endorsement and a commitment that embodies the innovation, hard work, and first principles thinking of the city. "It's no mystery that the Cambridge office market has been particularly hard hit during the last 6 years, but the green shoots are there, with AI companies like Blitzy driving that early momentum and representing over 60% of the new leasing volume across the city year to date," said Bryan Sparkes, Senior Managing Director at JLL. Blitzy selected JLL and Bryan Sparkes to represent the company. About Blitzy: Blitzy is the autonomous software development platform for the enterprise, built to accelerate software development at scale. Blitzy reverse-engineers software estates of 100M+lines into a dynamic knowledge graph, giving agents system-wide context to plan, build, modernize, and validate software. By orchestrating thousands of agents and state-of-the-art models across each run, Blitzy autonomously executes months of development work, helping Global 2000 enterprises deliver software 5x faster while reducing risk across the development lifecycle. SOURCE Blitzy

Hyperscale remediation: secure your software estate autonomously. Blitzy reverse engineers hundreds of millions of lines of enterprise code, reasons across your entire codebase to uncover known and zero day vulnerabilities, determine which findings are reachable and exposed, and turn validated risks into remediation pull requests. Rapid improvement in frontier model capabilities arm attackers with an increasingly evolving arsenal of tools to exploit vulnerabilities before patches exist, while organizations can take an average 55 days to remediate known flaws according to Edgescan's Vulnerability Statistics Report. The problem isn't detection alone. It's knowing: * Reachable: Can your application's execution path reach the vulnerable code? * Exposed: Can an attacker access that path, such as through an internet-facing service? * Impact: What dependencies or functionality could the fix affect? Blitzy answers all three. Blitzy is introducing Proactive Insights. It does three things that no other tool does in unison: it finds vulnerabilities in proprietary code, it tells you with certainty rather than confidence intervals which of them your architecture actually exposes, and batch automates PRs to remediate them at scale. What Proactive Insights does. Proactive Insights is driven by Blitzy's unique capability of understanding enterprise codebases at scale. No matter how large the ecosystem, Blitzy can reverse engineer it down to the file and variable level in days. From there, you pick a branch from any connected repository. Blitzy reports two categories. Discovered by Blitzy. Blitzy analyzes your entire codebase with a proprietary blend of multi-model orchestration to uncover vulnerabilities absent from public CVE databases, advisories, and security signatures. When exploitable and unpatched, they represent zero-day risk, hidden in proprietary code that traditional tools have not examined in full-system context. Publicly known. Blitzy reconciles what you already run, like Snyk, Mend, Sonatype, and GitHub Advanced Security. This is not a replacement for your scanners. They are good at the classes they were built for. What they cannot tell you is which of their own findings your architecture exposes. For every finding, Blitzy goes beyond detection: it determines real exposure, evaluates whether the issue can be fixed safely, and generates the remediation. Prioritize by real exposure. Findings are deduplicated by instance rather than exploded per package, and filterable on severity and reachability. In one customer's transaction-processing system, Blitzy found a vulnerable function used by three services, two exposed to the internet. It also identified sites the fix would affect and included all in the remediation plan. Traditional scanners stop at the finding; Blitzy plans and executes the fix. Validate the fix before committing. Blitzy checks whether the fix is achievable without introducing a new vulnerability. If it is not, you are told before an engineer is committed. You can proceed with the manual steps identified, adjust scope and re-analyze, or abort. Turn findings into pull requests. Blitzy generates a project per finding with the prompt pre-populated, plans it, generates pre-tested code, and opens a pull request in your repository. You approve the plan. You review the PR. It re-runs on every codebase sync. Why this could only come from Blitzy. Blitzy was designed from inception to solve problems faced by enterprise software development teams. Before writing code, most large scale projects begin with an archeology expedition. Blitzy removes the need for this by reverse-engineering hundreds of millions of lines into a knowledge graph mapped to the exact line, tracing every node, and keeping it current as developers merge. Blitzy built that to accelerate enterprise grade software development. A graph that knows every call site in your estate turns out to be the only structure that can say which vulnerabilities are real, and what fixing them costs before you commit. That distinction matters because the alternative is volume. OX Security's 2026 Application Security Benchmark, drawn from 216 million findings across 250 organizations, reports: The average organization now faces 865,398 security alerts, up 52% from 569,354 a year earlier. After prioritization, the average organization is left with 795 critical findings. That is 0.092%. Nobody needs another list. Every tool in your stack reads a file or a manifest. None of them has a global, real-time understanding of your estate, so none can answer the only three questions worth answering: is it reachable, is it exposed, and what breaks if I fix it. Blitzy does not introduce vulnerabilities. According to Veracode's Spring 2026 GenAI Code Security Update, testing 80 coding tasks against successive model generations, it found that only 55% of generation tasks result in secure code. This means that in 45% of cases, the model introduces a known security flaw into the codebase. The longitudinal finding is the damning one: while syntax pass rates have climbed steadily from about 50% to 95% since 2023, security pass rates have remained essentially flat, hovering between 45% and 55% regardless of model generation or release date. Veracode's conclusion: Models have become excellent at writing code that compiles. They've failed at writing code that's safe. Blitzy is built so that it does not introduce vulnerabilities, as an architectural property rather than a policy. The majority of its compute goes to validation rather than generation. Security review runs inside the build against every artifact, at hard checkpoints where execution pauses so review agents inspect, classify, and mitigate before a pull request exists. Security shouldn't wait for someone to ask. Proactive Insights is now available in Blitzy, starting with security and expanding to more enterprise codebase insights soon.