Artificial Intelligence

  • Why Responsible AI in Medical Device Development Starts With Traceability

    Conversations around AI in medical device development have shifted from whether organizations should adopt AI to how they can use it responsibly.  Medical device manufacturers see enormous potential for AI to accelerate requirements development, improve documentation, identify inconsistencies, generate test cases, and reduce repetitive engineering work.   At the same time, quality and regulatory leaders are asking equally important questions:  These are all valid concerns. In fact, regulatory…

  • MVP Development Redefined: How Spec-Driven Development Helps Teams Go From Viable to Valuable 

    For years, MVP development was guided by the goal of shipping early, learning quickly, and reducing waste. Somewhere along the way, Minimum Viable Product became “What’s the least amount of work we can put in to ship something?”  This thinking optimizes for the team’s effort, not the customer’s result. Instead of validating product-market fit faster, organizations often end up in expensive cycles of rework: …

  • How OpenSpec Keeps AI Coding Agents From Losing Context

    Teams running Claude or a similar assistant across dozens of sessions hit a familiar wall. The artificial intelligence (AI) forgets decisions made two prompts earlier and reintroduces bugs it already fixed, and the reasoning behind an architecture choice disappears with it. OpenSpec keeps agents aligned by storing that intent in version-controlled proposals, delta specs, designs,…

  • AI Maturity Levels for Engineering Teams: Understanding the AI Adoption Maturity Model 

    AI coding assistants are now ubiquitous across software engineering teams, yet relatively few organizations have transformed how engineering itself operates. Teams write code faster while continuing to struggle with bottlenecks in requirements, specifications, testing, verification, compliance, and engineering governance.  That’s because becoming an AI-native engineering organization requires changes across the entire engineering lifecycle.  This article introduces the AI adoption maturity model, a practical framework for understanding…

  • What Is a Product Context Layer?

    We see engineering teams adopting artificial intelligence (AI) coding agents, who hit a wall they didn’t expect. Their agents handle single functions cleanly, but the moment work spans multiple files, output falls apart because the agents have no memory of the architecture they are building against. Isolated functions are manageable, while multi-file infrastructure work requires…

  • Best Practices for AI in Regulated Industries

    Artificial intelligence is transforming how engineering teams develop products, analyze requirements, and identify risks. But for organizations developing safety-critical or highly regulated products, the conversation is about doing so responsibly.  Many engineering leaders face the same challenge: How can we introduce AI into engineering workflows while maintaining control over the development process?  The answer isn’t simply choosing the right AI model. Successful…

  • How to Improve Developer Velocity Without Sacrificing Quality

    Artificial intelligence (AI) coding assistants can make individual coding tasks appear faster, while organizational delivery metrics lag. The speed may show up in commits and pull requests (PRs), while customer-visible delivery stays flat. Those gains get absorbed somewhere between the individual keyboard and the production release, lost to downstream bottlenecks. Vice Presidents (VPs) and Directors…

  • Closing the Gap From Agent to Reviewer Using AI Agent Toolkits and Jama Connect MCP™ 

    One of the challenges I often hear from our automotive customers is that a large portion of time disappears into tasks that are both very manual as well as very tedious.   An example of one of these tasks is scanning standards or regulatory documents, finding consistencies both between the standards and their internal requirements, then tracing them…

  • What Is Harness Engineering? A Software Engineering Guide

    Agent-first software workflows can begin with an empty git repository and a team of coding agents. By shipment, application logic, tests, continuous integration (CI) configuration, documentation, and internal tooling may all come from agents. The shift moves engineering work to a different layer. The job now is to design the specs, constraints, tools, and feedback…

  • Jama Connect® Features in Five: Jama Connect MCP™ for AI-Assisted Development and Traceability

    Requirements, code, and verification artifacts often live in different systems. Engineers switch between tools to understand requirements, implement functionality, and document traceability. By the time an audit arrives, teams may spend days or weeks proving that what they built matches what was specified. That gap shows up often in regulated engineering environments. Security requirements span…