LinearB launches Agentic Studio to link coding agents with engineering context

Agentic Studio is available to all LinearB customers immediately, with an initial agent skill in early access. This skill matches an agent’s effort to a task’s risk by analyzing business relevance, complexity, and signals like rework rates or recent incidents. LinearB claims the feature helps allocate resources more efficiently, though no comparative results or token savings are quantified. The platform also supports role-based access and lets leaders ask questions in plain language to generate suggested next steps or AI-driven dashboards. LinearB’s Model Context Protocol (MCP) further connects engineering data to existing AI workflows, enabling teams to investigate bottlenecks without manually switching between tools.

The announcement cites 2026 benchmarks from 2.7 million pull requests and 83,000 developers across 253 organizations. Teams using AI on at least 75% of coding days merged 96% more pull requests per week than a year prior. However, LinearB notes that larger AI-assisted changes and agent-created pull requests often face longer review times, highlighting downstream bottlenecks. Kraken reportedly cut review times at the 90th percentile by over half after using MCP to analyze delays, attributing the issue to time zones and reviewer availability rather than change size.