Identifying the next phase of software development as always-on agentic artificial intelligence, Atlassian plc today announced a new set of upcoming Jira features to help engineering teams run AI agents at large scale while governing actions over long periods.
As enterprise engineering teams begin to adopt more agents, they’re not just scaling agents to do more work – they’re working them longer and across more parts of the software development lifecycle. According to Atlassian, letting agents work with less tedious supervision from start to finish comes with caveats because of trust, grounding, shared context, communication, institutional memory and validation.
To address this, the company is releasing updates that govern agentic activity, set standards for action, review AI agents in motion, and validate usage to ensure everything works.
According to Atlassian, agents fail because they don’t have a good view of the architecture of projects, decisions and standards. So, the starting line grounds them with better context, and the company calls this Code Context. It’s built with the company’s Teamwork Graph, which gives coding agents secure intelligence across complex, multi-repository codebases.
This is combined with Agent Space Settings and Agent Context Controls to govern where agents can operate, what they can see and what they can do. Allowing a team and management to securely control them the same way they control employee access.
The ideal of an AI agent is that it’s not a chatbot. It can run automatically, no more prompting it iteratively. This means that it can run for hours or days on its own, activating when work needs to be done and checking in.
Atlassian has introduced Agent loops in Jira, a system that scans backlogs for work and turns it into code merge requests inside Jira, a standards system that conforms code and a dedicated agent that reviews merge requests against standards to flag problems.
Automatic but not invisible
All of this doesn’t happen in the dark; validation happens along with transparency. Because there isn’t a perfect playbook or industry standard, but best practices are still being built, Atlassian offers accountability and visibility tools on the back end to track it.
Every time agents run, they generate an audit log with diagnostics that allow the system to display and measure AI impact across throughput, quality, adoption and cost. It lets teams understand spend across software as it ships. It also includes an AI agent usage dashboard that shows who is using the tools, how they’re being used, and outcomes at a team level.
Atlassian said the idea is to help teams move from using only foreground coding tools to working with always-on agents that pick up the slack by running in the background to automate engineering tedium. Currently, teams are experimenting with these tools ad hoc, but don’t have a good library to govern, connect or understand them.
