back_office_ops · saas · workflow
How Atlassian's Rovo Chat evolved into a hierarchical multi-agent orchestration framework
Rovo Chat's original single-agent framework was static and failed to generalize as queries became more complex, with a single orchestrator easily getting confused when managing tools across many domains.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · User submits query to Rovo Chat
Users submit queries to Rovo Chat to retrieve information from the enterprise knowledge base or perform actions.
Tools used
Rovo ChatLLMsRAGJiraJQL
Outcome
The hybrid multi-agent orchestrator achieved a +3.49% quality improvement and reduced P50 first-token latency by 29.5% and P90 latency by 19.97% compared to the single-agent RAG baseline.
What failed first
A multi-agent DAG orchestration approach proved brittle when subagents failed or did not supply the information needed by downstream tasks, because a complete orchestration plan could not be reliably generated from the user query alone in a single shot.
Results
Volume+3.49%
Source
https://www.atlassian.com/blog/atlassian-engineering/how-rovo-embraces-multi-agent-orchestration
Grounding & classification
Source type: technical build writeup
34 fields verified against source quotes.
agentic workflowenterprise searchknowledge searchmulti agent workflowragknowledge basesupport ticketfailure mode describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedsoftwareaccuracy improvementresponse time reductiontechnical build writeupback office opsticket triageagentic task executionextract classify routerag answering