LinearB launches Agentic Studio to help engineering leaders and AI coding agents build better software faster. November 2, 2026 LinearB, a Leader in the 2026 Gartner Magic Quadrant for Developer Productivity Insight Platforms, today launched the agentic studio, a key part of the next generation of the developer productivity platforms. Historically, productivity platforms gave engineering leaders metrics. LinearB now turns everything happening across software delivery into context that people and agents can consume and act on. Engineering leaders ask questions in plain language and get answers and next steps. They define the context surface with role-based access built in, and AI assistants help extend that context and build metrics, artifacts and dashboards. Coding agents receive that context, so they understand their task and environment better and make smarter decisions. Acting on that context matters more than ever. LinearB's 2026 AI benchmarks, covering 2.7 million pull requests across more than 250 organizations, show that developers who use AI most heavily nearly doubled their merged pull requests year over year. Yet the software factory faces new problems. In LinearB's 2026 Software Engineering Benchmarks Report, AI-assisted pull requests were 2.6 times larger than unassisted ones at the 75th percentile, and agent pull requests waited more than five times longer for review. "Context is the new king," said Ori Keren, CEO and co-founder of LinearB. "We realized we hold a knowledge graph that nobody else has of everything happening across the software delivery lifecycle, and that's exactly what agents and teams need to deliver high quality software, faster. So we rebuilt LinearB around it." LinearB's effort skill, now in early access, matches a coding agent's effort to the task. It gauges a change's business relevance, complexity and risk using the code quality in the area, recent service incidents and ownership history. Low risk changes use less effort and fewer tokens. Complex, risky or high priority changes get more effort and careful, tested edits. More skills are on the way, focused on accelerating downstream stages of the software factory, such as review and merge. Kraken used LinearB's MCP server with AI to find what was really slowing its code reviews. The answer wasn't large changes. It was time zones and reviewer availability. Kraken cut review time at the 90th percentile by more than half in four months. "That's the structural shift," said Nik Sudan, engineering operations lead at Kraken. "It moves leaders from anecdote-driven to evidence-driven." The Agentic Studio is available now to all LinearB customers. Agent skills are available in early access. Why it matters now Engineering leaders have more data than ever and less time to use it. Boards and CFOs now ask whether AI spend is paying off, and a dashboard full of numbers doesn't answer that. At the same time, coding agents write more of the code, and they start every task knowing nothing about the codebase's history. Productivity platforms have always been good at measuring. The next step is turning what they measure into action. That means answers for the people running engineering, and context for the agents doing more of the work. What LinearB does LinearB collects data from across the software delivery lifecycle and makes it usable. It normalizes data from different Git and project management systems into one model, matches each engineer's identities across tools, and links every change from ticket to release. It adds AI attribution and industry benchmarks, so leaders can tell whether a number is good or bad. The engineering context layer delivers that knowledge to people and to agents. Engineering leaders ask questions in plain language, like where delivery is stuck, how their developers are doing and whether AI is paying off. Instead of reading a chart, they get an answer and a next step. They can build their own metrics and pull the same context into AI tools like Claude through MCP. Coding agents get the same context through MCP and agent skills. The first skill, now in early access, matches an agent's effort to the task. It checks how complex and risky a change is, using the code's rework rate, recent incidents and ownership history. Simple, low risk changes use less effort and fewer tokens. Complex or risky changes get more effort and careful, tested edits, which raises quality where it matters most. The skill works with any coding agent, and leaders can see how often agents were routed to low, medium and high effort. The platform is built for the enterprise, with role based access and guardrails on what agents can do. Journey and milestones LinearB started by giving engineering leaders visibility into how their teams deliver software. Years of integration work across the software delivery lifecycle gave it one of the largest datasets on how engineering teams work. Its 2026 Software Engineering Benchmarks Report drew on more than 8.1 million pull requests from 4,800 engineering teams in 42 countries. As AI coding tools spread, LinearB added AI attribution and connected to more of the tools teams use. In 2026, Gartner named LinearB a Leader in its first Magic Quadrant for Developer Productivity Insight Platforms, for both its ability to execute and its completeness of vision. Early customer response to the context layer is strong. The AI assistant and MCP access show the highest user retention of any features LinearB has released. "These are exciting times to rethink our role in the software ecosystem," said Ori Keren. "Everyone else is focused on writing code. We realized we hold a knowledge graph of everything happening across the software delivery lifecycle, and that's exactly what developers and agents need. So we rebuilt LinearB around it. We don't build the software factory. We instrument it, so leaders know what to do next and agents make smarter decisions on every change." "For years, engineering leaders told us the same thing. Metrics are useful, but they don't tell you what to do," added Dan Lines, co-founder and COO of LinearB. "A dashboard says your cycle time is two days. So what? Now a leader can ask what to improve in their engineering organization and get a clear answer. And when that same context goes to coding agents, the platform isn't just reporting anymore. It's acting." Market trends LinearB's 2026 AI benchmarks, built from 2.7 million pull requests and 83,000 developers across 253 engineering organizations between February and May 2026, show why measuring AI isn't enough on its own. The teams pulling ahead are the ones acting on what they learn. * Heavy AI users are pulling away. The typical developer who uses AI on at least 75% of coding days merged 96% more pull requests per week than a year earlier. The typical developer using no AI merged 3.6% fewer. * Adoption is shallower than the hype suggests. Even at elite organizations, AI assists only 54% of pull requests. * Agents still need people. At the 90th percentile, autonomous agents open 4.7% of pull requests. At elite organizations, 79% of agent pull requests merge within 30 days, compared with 92% of human only pull requests. At fair organizations, agent yield drops to 37%. The likely reason is ownership. When no developer owns an agent's pull request, it often never merges. * AI code review is the fastest win. Pull requests with an AI review merge at the highest rate of any type and lift yield by up to five percentage points. * AI costs are climbing fast at the top. Token spend at the 90th percentile reached $35.20 per developer per coding day, up nearly 75% in three months, while the median barely moved. Engineering leaders already use LinearB to answer the questions their boards are asking about AI. "I use LinearB data and charts directly in my board decks, because my board is specifically asking questions about our use of AI and what our ROI is," said Ken Ringdahl, CTO of Emburse. Forward-looking vision The effort skill is the first in a library of agent skills. Each one turns LinearB's context into an action an agent or a leader can take. Next, LinearB will focus on helping teams merge and govern AI generated code safely, and on cutting what engineering organizations spend on AI. The goal is the one productivity platforms have always promised, helping teams deliver better software faster. LinearB now does it by giving people answers and giving agents the context to act. About LinearB LinearB is the developer productivity platform built on a foundational engineering context layer. It turns data from the tools teams already use into context for agents, developers and engineering leaders. Teams use it to find bottlenecks, prove what AI delivers and guide agents toward safer, cost-aware changes. Learn more at https://linearb.io/

LinearB launches Agentic Studio to give coding agents engineering context - unite.ai. LinearB has launched Agentic Studio to turn software-delivery data into context that engineering leaders and coding agents can use to make decisions. Announced November 2, the platform combines natural-language analysis with an engineering context layer spanning the tools teams use to plan, write, review and release software. The launch reflects a growing problem in AI-assisted development: producing more code does not automatically help an organization deliver useful software faster. Reviews can become congested, changes can grow harder to assess, and agents can begin a task without knowing which services are fragile or why a particular fix matters. Agentic Studio is available to all LinearB customers, according to the announcement. Agent skills, including an initial capability for matching an agent's effort to a task, are in early access. Turning delivery data into engineering context. LinearB collects information across software delivery and normalizes it into a common model. The company says it reconciles engineers' identities across Git and project-management systems, connects changes from ticket to release, and adds AI attribution and benchmarks to help leaders interpret the results. The important step is connecting those records. A pull request can look straightforward in isolation while affecting a service with recent incidents, frequent rework or complicated ownership. Linking the change to that history gives a reviewer or coding agent information that a repository snapshot alone may not provide. In the new studio, leaders can ask questions in plain language, obtain suggested next steps and use AI assistance to create metrics, dashboards and other artifacts. LinearB says organizations can define the context available to users with role-based access built into the platform. That direction aligns with the company's context-engineering guidance, which emphasizes selecting relevant information rather than filling an agent's context window indiscriminately. Its framework considers the code, the intent behind a change, connections across systems and the boundaries of what an agent may access. An early-access skill for matching effort to risk. The first agent skill is designed to decide how much effort a coding task warrants. LinearB says it considers business relevance, complexity and risk, using signals such as rework rates, recent service incidents and ownership history. A low-risk change can receive a lighter treatment with fewer tokens, while a more consequential change can receive more deliberate analysis and testing. Engineering leaders can see how frequently tasks are routed to low, medium or high effort. The company says the skill works with any coding agent, although the announcement does not provide comparative results across specific agents or quantify realized token savings. The engineering idea is useful even before a cost claim is established. A uniform reasoning budget treats a minor maintenance change and a sensitive production fix alike. Task-specific context could help allocate more attention where mistakes are expensive, while reducing unnecessary work on simpler changes. MCP connects the data to existing AI workflows. LinearB also exposes engineering information through the Model Context Protocol, or MCP. Its MCP product page describes natural-language access to delivery metrics, custom reporting and bottleneck analysis, alongside recommendations such as review automation and routing. This gives teams a way to investigate engineering data from an AI client instead of manually moving between dashboards. MCP provides the connection to tools and information; the context layer supplies the delivery-specific relationships that make a question about a repository or team meaningful. There is a distinction to resolve as the new platform rolls out. While the launch describes role-based access and enterprise guardrails, LinearB's public MCP FAQ still lists permissions-scoped MCP access as a roadmap item. The new studio's access-control statement should therefore not be read as confirmation that every existing MCP client already inherits every LinearB permission. Why more AI output can expose downstream bottlenecks. LinearB's announcement cites 2026 AI benchmarks drawn from 2.7 million pull requests and 83,000 developers across 253 organizations. Developers using AI on at least 75% of coding days merged 96% more pull requests per week than a year earlier, according to the company. Those figures describe observed activity, rather than proving that AI alone caused the change. More merged pull requests also does not establish that customers received twice as much value. The release separately cites findings that AI-assisted changes were larger and agent-created pull requests waited substantially longer for review, illustrating how faster code generation can shift work onto the rest of the delivery process. A customer example makes that distinction concrete. LinearB says Kraken used its MCP server with AI to investigate review delays and found that time zones and reviewer availability mattered more than large changes. Kraken reportedly reduced review time at the 90th percentile by more than half over four months. The company's published discussion with Kraken provides further context on using repository data and delivery metrics to uncover bottlenecks. From measuring AI adoption to improving delivery. LinearB plans additional agent skills for downstream work such as review, merge and governance. Those are future directions, distinct from the studio's current availability and the effort skill's early-access status. The broader proposition is that coding agents need an understanding of the organization around the code: what matters, who owns it, where earlier changes failed and which constraints apply. Agentic Studio brings that proposition into the developer-productivity platform, with its value ultimately measured by the quality and flow of delivered changes rather than the amount of code generated.