Tabnine has launched the Tabnine Agentic Platform for AI-assisted software development using coding agents. The platform enables enterprise software development teams to ship faster while maintaining control of their code and context, the company said.
Introduced Nov. 5, Tabnine Agentic gives developers an autonomous coding partner who not only suggests and completes code, but also completes workflows, all in line with an organization’s standards and security policies, Tabnine said. Tabnine’s “org-native” agent, powered by the Tabnine Enterprise Context Engine, understands a user’s repositories, tools, and policies and uses these artifacts to plan, execute, and validate multi-step development tasks, Tabnine said. Agent tasks include refactoring, debugging, and documentation. This engine includes coding standards, source and log files, and a ticketing system. According to Tabnine, the Tabnine agent runs the complete coding workflow and provides security and context.
Tabnine agents can use external systems and tools to adapt to new codebases and policies without retraining or redeployment. The engine combines vector, graph, and agent search techniques to interpret relationships between codebases, tickets, and tools, enabling Tabnine’s organization-native agents to reason through multi-step workflows, the company said. Enterprise-grade benefits include:
