Boston, Massachusetts: LinearB today launched LinearB Agentic Studio, a key part of its next-generation developer productivity platform designed to give enterprise engineering leaders and coding agents the context needed to make better software delivery decisions.
Historically, productivity platforms provided engineering leaders with metrics.
LinearB Agentic Studio takes the next step by turning everything happening across the software delivery lifecycle into context that people and AI agents can consume and act on.
With LinearB Agentic Studio, engineering leaders can ask questions in plain language and receive answers and next steps.
They can define the context surface with role-based access built in, while AI assistants help extend that context and build metrics, artifacts and dashboards.
Coding agents can also receive the same context, helping them better understand their tasks and environments and make smarter decisions.
Acting on that context is becoming increasingly important as AI adoption changes software development.
LinearB’s 2026 AI benchmarks, covering 2.7 million pull requests across more than 250 organizations, show that developers using AI most heavily nearly doubled their merged pull requests year over year.
However, the software factory is also facing new challenges. According to LinearB’s 2026 Software Engineering Benchmarks Report, AI-assisted pull requests were 2.6 times larger than unassisted pull requests at the 75th percentile.
Agent pull requests also 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 Agentic Studio Brings Context to Coding Agents
A key component of LinearB Agentic Studio is LinearB’s effort skill, which is now available in early access.
The skill is designed to match a coding agent’s effort to the task it needs to complete.
The effort skill gauges a change’s business relevance, complexity and risk by looking at the code quality in the relevant area, recent service incidents and ownership history.
Under the system, low-risk changes can use less effort and fewer tokens. Complex, risky or high-priority changes receive more effort and careful, tested edits.
LinearB said more skills are on the way, with a focus on accelerating downstream stages of the software factory, including review and merge.
Kraken Uses LinearB MCP Server to Identify Code Review Bottlenecks
Kraken used LinearB’s MCP server with AI to identify what was actually slowing down its code reviews. The analysis found that the problem was not large changes, but time zones and reviewer availability.
Kraken reduced review time at the 90th percentile by more than half over 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 LinearB Agentic Studio is available now to all LinearB customers, while agent skills are available through early access.
Why LinearB Agentic Studio Matters Now
Engineering leaders have more data than ever but less time to use it. Boards and CFOs are increasingly asking whether AI spending is delivering returns, while dashboards filled with numbers do not necessarily provide those answers.
At the same time, coding agents are writing more software and begin every task without knowing the history of the codebase.
The LinearB Agentic Studio is designed around turning the information collected by productivity platforms into action.
That includes providing answers for engineering leaders and context for coding agents that are taking on more software development work.
What LinearB Agentic Studio Does
LinearB collects data from across the software delivery lifecycle and makes it usable. The platform normalizes data from different Git and project management systems into one model, matches each engineer’s identity across tools and links every change from ticket to release.
It also adds AI attribution and industry benchmarks, allowing leaders to understand whether a particular number is good or bad.
The engineering context layer behind LinearB Agentic Studio delivers that knowledge to both people and agents.
Engineering leaders can ask questions in plain language about where delivery is stuck, how developers are performing and whether AI investments are paying off. Rather than simply reading a chart, leaders receive an answer and a next step.
They can also build their own metrics and pull the same context into AI tools such as Claude through MCP.
Coding agents receive the same context through MCP and agent skills. The first skill, currently in early access, matches an agent’s effort to the task.
It evaluates the complexity and risk of a change using the code’s rework rate, recent incidents and ownership history. Simple, low-risk changes can use less effort and fewer tokens, while complex or risky changes receive more effort and careful, tested edits.
LinearB said this approach is designed to raise quality where it matters most. The skill works with any coding agent, while engineering leaders can see how often agents were routed to low, medium and high effort.
The platform is also built for enterprise use, with role-based access and guardrails governing what agents can do.
LinearB Agentic Studio Journey and Milestones
LinearB initially focused on giving engineering leaders visibility into how their teams deliver software. Years of integration work across the software delivery lifecycle have given the company one of the largest datasets on how engineering teams work.
LinearB’s 2026 Software Engineering Benchmarks Report drew on more than 8.1 million pull requests from 4,800 engineering teams across 42 countries.
As AI coding tools expanded, LinearB added AI attribution and connected to more of the tools used by engineering teams.
In 2026, Gartner named LinearB a Leader in its first Magic Quadrant for Developer Productivity Insight Platforms, recognizing the company for both its ability to execute and completeness of vision.
LinearB said early customer response to its context layer has been strong. The AI assistant and MCP access have shown 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.”
LinearB Agentic Studio and the Changing AI Engineering Landscape
LinearB’s 2026 AI benchmarks, based on 2.7 million pull requests and 83,000 developers across 253 engineering organizations between February and May 2026, highlight the changing role of AI in software engineering.
The data shows that measuring AI adoption alone is not enough, with teams increasingly focused on acting on what they learn.
Heavy AI Users Are Pulling Ahead
The typical developer using AI on at least 75% of coding days merged 96% more pull requests per week than a year earlier.
By comparison, the typical developer using no AI merged 3.6% fewer pull requests.
AI Adoption Remains Below the Hype
Even at elite organizations, AI assists only 54% of pull requests.
Coding Agents Still Need Human Oversight
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%.
LinearB said the likely reason is ownership. When no developer owns an agent’s pull request, it often never merges.
AI Code Review Shows Strong Results
Pull requests with an AI review merge at the highest rate of any type and can lift yield by up to five percentage points.
AI Costs Are Rising at the Top End
Token spending 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 are already using LinearB to answer questions from their boards about AI spending and returns.
“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.
