Harness Launches AI DevSecOps Agents to Streamline Software Delivery
Harness.io introduces new AI-powered DevSecOps agents to address bottlenecks in software delivery pipelines, with features set to roll out next week.
BOSTON — Harness.io showcased its new AI-powered DevSecOps platform at the Unscripted Boston event, highlighting live demos and previewing features slated for release starting September 23. The platform, which became generally available on August 26, leverages a knowledge graph built on user pipeline data, workflow orchestration, and task-specific AI agents for DevOps, SRE, security, and testing.
Key Features and Adoption
- Agentic Workflows: Harness breaks tasks into single-step components, assigning specialized agents to each. Evaluation agents ensure response quality.
- Production Use: 100 of Harness’s 1,000 enterprise customers already use its DevOps agent for pipeline building, per CEO Jyoti Bansal.
- Upcoming Releases: New agentic workflows for release orchestration, developer portals, and FinOps, plus upgrades like AI Autofix for code remediation.
Harness CEO Jyoti Bansal at Unscripted Boston (Credit: Beth Pariseau/Informa TechTarget)
Addressing the AI Coding Bottleneck
Bansal cited a 2024 DORA report showing AI coding tools worsen delivery stability (-7.2%) and throughput (-1.5%) despite increased code output. "The delivery process is the choke point," he said. Harness CTO Nick Durkin demonstrated how the platform accelerates tasks like YAML pipeline building and failure troubleshooting.
Competitive Landscape
- GitLab and JFrog offer similar AI agents, but Harness stands out with its opinionated, policy-driven approach, per IDC analyst Jim Mercer.
- Enterprise Feedback: An anonymous financial services engineer praised Harness’s centralized data layer but noted risks in "doing everything right."
Customer Perspectives
- Takeda’s Chris Williams sees CI/CD as an enforcement point for responsible AI.
- Synchrony’s Tori Currier highlighted AI’s potential to modernize legacy systems like .NET-to-mainframe migrations.
Related News
AWS extends Bedrock AgentCore Gateway to unify MCP servers for AI agents
AWS announces expanded Amazon Bedrock AgentCore Gateway support for MCP servers, enabling centralized management of AI agent tools across organizations.
CEOs Must Prioritize AI Investment Amid Rapid Change
Forward-thinking CEOs are focusing on AI investment, agile operations, and strategic growth to navigate disruption and lead competitively.
About the Author
Michael Rodriguez
AI Technology Journalist
Veteran technology journalist with 12 years of focus on AI industry reporting. Former AI section editor at TechCrunch, now freelance writer contributing in-depth AI industry analysis to renowned media outlets like Wired and The Verge. Has keen insights into AI startups and emerging technology trends.