Blog
How AI agents fit into software delivery, and what it takes to govern their access to Jira, GitHub, Confluence, data and mail.
AI agent audit trail: what to log under the EU AI Act
What an audit trail for AI agents should record, why the AI vendor's own log is not independent evidence, and how the EU AI Act and GDPR frame it.
AI agents and Databricks: access control for tables and columns
How to give AI agents read access to Databricks without exposing personal data: structured queries, table and column allowlists, value masking.
AI documentation in Confluence and the Azure DevOps wiki
How AI agents can keep Confluence and Azure DevOps wiki pages current, and which controls stop them from editing spaces and pages they should not touch.
AI code review: permissions on GitHub and Azure DevOps
Which permissions an AI code review agent needs on GitHub and Azure DevOps, why approve and merge are separate risks, and how to scope repos and branches.
AI agent for Jira sprint planning: access without risk
How an AI agent can groom the Jira backlog and prepare sprints, which permissions it really needs, and how to limit it to one project and board.
What is an MCP gateway, and when does a team need one?
An MCP gateway sits between AI agents and tools like Jira. What it checks on every call, how it differs from direct MCP servers, and when to use one.
AI agents in the software development lifecycle: where they help and where control is needed
Where AI agents help in planning, documentation, code review, data and communication, and which controls each stage of the software lifecycle needs.
See it on your own stack.
A short walkthrough on your tools, your rules, your audit log. Nothing leaves your network.