Agent permissions
Configure and manage Worker Agent permissions at pipeline level and through RBAC.
Configure and manage Worker Agent permissions at pipeline level and through RBAC.
Use Harness AI PR agents to review pull requests, fix failing builds, and raise test coverage from your pipelines.
Configure the Anthropic Model Connector to run Harness Worker Agents on Claude models through direct Anthropic or AWS Bedrock endpoints.
Use Harness AI chat history and Memory to search past conversations and build on previous context.
Write effective prompts for Harness AI to generate pipelines, services, environments, and other resources.
Explore common use cases for Harness AI Chat across DevOps, security, cost management, reliability, and knowledge assistance.
Use Harness AI Memories to personalize AI responses with context captured from your chats.
Use Harness AI Rules to tailor AI output to enterprise standards before Harness resources are created or changed.
Use the Harness MCP Server to query IaCM workspaces, resources, and module registry from AI-powered tools via three exposed API endpoints.
Use Harness Skills, prompt templates that teach AI coding assistants how to generate pipeline YAML, manage resources, debug failures, and analyze costs on the Harness platform.
Add third-party MCP connectors to Harness AI chat to give the assistant tools from external services such as GitHub, GitLab, and Jira.
Configure the OpenAI Model Connector to run Harness Worker Agents on GPT models with configurable reasoning effort.
Browse the Harness Skills catalog, grouped by workflow mode, to find the right skill for creating, running, governing, or analyzing Harness resources.
Chain Harness Skills into end-to-end workflows, and review skill file anatomy, MCP tools, and the harness-skills repository structure.