The future of software development, according to Linear CEO Karri Saarinen, is increasingly automated. The company, known for its cloud-based issue tracking and project management tools, has launched an AI agent and plans to add AI-powered coding assistance, a move Saarinen boldly declares renders traditional “issue tracking” obsolete.
The Linear Agent, currently in beta, integrates directly into the company’s online, mobile, and desktop applications, as well as popular communication platforms like Slack, Microsoft Teams, and Zendesk. Users interact with the agent through a chat interface, with examples including the ability to automatically create and assign issues based on existing conversations, according to a recent blog post. This represents a significant shift in how development teams manage tasks and workflows.
Beyond simple task creation, the agent offers “skills” and “automations” – features available on Linear’s Business ($16 per user/month) and Enterprise plans. Skills allow users to save frequently used workflows for future application, even as automations trigger actions automatically when new issues are created. These features aim to streamline repetitive processes, freeing up developers to focus on more complex problem-solving.
The long-term vision extends to code itself. Future iterations of the Linear Agent will include the ability to write and debug code, answer questions about existing codebases, and even present code “diffs” – highlighting the changes made to a block of code. Saarinen stated in a post outlining his vision for the future of the platform that “issue tracking is dead,” arguing that AI agents “make software development a lot simpler” by handling much of the procedural work. He claims coding agents are already in use by 75 percent of Linear’s enterprise customers, and that the volume of work completed by these agents has increased fivefold in the last three months.
This isn’t simply about adding AI features to an existing system; Saarinen envisions a fundamental change in how developers interact with their tools. A diagram accompanying his post illustrates Linear evolving into a platform primarily for capturing context, with agents handling the bulk of the engineering tasks. Despite this shift, he clarifies that “issues will remain as the core items in Linear,” suggesting a hybrid approach rather than a complete abandonment of traditional issue tracking.
A Shift in Project Management Philosophy
The announcement has sparked discussion within the developer community. Early feedback, shared in Linear’s Slack channel, has been largely positive, with users expressing enthusiasm for the new capabilities. However, some have requested support for the Model Context Protocol (MCP), a standard for sharing context between AI agents. A Linear employee responded, confirming that MCP support is currently under development.
This move by Linear isn’t happening in a vacuum. 37signals, the company behind Basecamp, is likewise repositioning its project management tool to embrace an “agent-first, agent-native” approach. Basecamp’s plans include access for any AI agent via a command-line interface, aiming to transform the platform into an “agent-driven assistant.” Both companies are vying to develop into central hubs in a future where AI agents play a more prominent role in software development.
Security Concerns Remain a Key Consideration
While the potential benefits of agentic AI are significant, security remains a critical concern. Currently, Linear’s documentation states that the agent “operates within your existing permissions,” but details regarding specific security measures are limited. Generative AI systems are known to be vulnerable to “prompt injection” attacks and other errors, and these risks could escalate as the agent’s capabilities expand, particularly when it gains the ability to write and modify code and interact with external systems like those utilizing MCP.
The potential for malicious actors to exploit vulnerabilities in AI agents is a growing area of concern for cybersecurity professionals. As these tools become more integrated into critical workflows, ensuring their security will be paramount.
Pricing and the Future of Agentic Workflows
During the beta period, pricing for Linear remains unchanged. However, the company anticipates transitioning automations and coding features to a usage-based pricing model “beyond a certain threshold.” This suggests that heavy users of these AI-powered features may face increased costs.
The broader implications of this shift towards agentic workflows are still unfolding. If AI continues to automate more aspects of the coding process, companies like Linear may face competition from tools specifically designed for agent management. The race is on to define the future of software development, and the outcome remains uncertain.
The evolution of tools like Linear and Basecamp highlights a fundamental question: will project management software become less about managing tasks and more about managing the agents that perform them? The answer will likely shape the landscape of software development for years to come.
Linear plans to continue refining the agent’s capabilities and addressing user feedback. The next major update is expected to focus on improving the agent’s coding assistance features and expanding support for different programming languages. Users can stay informed about these developments by following the company’s blog and participating in the Linear community forum.
If you are experiencing a mental health crisis, please reach out for help. You can contact the 988 Suicide & Crisis Lifeline by calling or texting 988 in the US and Canada, or by dialing 111 in the UK. These services are available 24/7, free, and confidential.
What do you think about the rise of AI agents in software development? Share your thoughts in the comments below.
