Reading, UK

USE CASE

Creating a custom Rovo Agent to Enhance Root Cause Analysis

Case study at a glance

The Challenge

A high volume of items requiring Root Cause Analysis

Team overwhelmed by the scale of incident data
Many items missed due to bandwidth constraints
Data split across Jira and Airtable, increasing risk of human error
Senior analysts required to double-check RCA accuracy
Slow, inconsistent, and heavily manual processes

The Solution

A custom Rovo Agent to automate the initial RCA process

Agent collects Jira + Airtable data and suggests a likely root cause theme
Performs linguistic, thematic, and logical pattern matching to identify the root cause
Provides rationale behind every recommendation for transparency
Human analysts approve or refine the suggestion via JSM forms
Built entirely in Rovo Studio using natural language prompts

The Benefit

Stronger accuracy in early-stage RCA

Significant reduction in manual data handling
Frees analysts to focus on complex investigations
Better insight from large, previously under-utilised datasets
Increased RCA completion rates
Higher data quality and fewer missed items

The full story: In depth

Background

In our work with an international speciality insurance firm, we’re continually exploring how we can automate internal processes for its business teams. Our client has embraced Rovo across its Atlassian toolset – particularly in Jira Service Management (JSM).

We have created a range of custom Rovo Agents to unlock greater time efficiencies, tighter quality control, and happier users for our client.

In this case study, we’re focusing on a custom Atlassian Rovo Agent to enhance Root Cause Analysis (RCA)

The Challenge

Our client’s Data Analysis team was handling a vast number of items, analysing the root cause to understand why an incident happened, and how to prevent reoccurrence.

With so many items constantly coming in, the team simply didn’t have the bandwidth to analyse each of them, nor to embed a streamlined process. As a result, team members could only focus on one or two subsets of items – meaning a high volume simple had to be omitted.

All root causes were documented in a densely populated Airtable, with items tracked in Jira. This also led to some challenges, including human error, due the vast datasets and having to comb through so much information. Senior team members therefore often had to check RCAs for accuracy – which took time and often resulted in additional fixing and reworking.

The Solution

We automated this entire RCA process for our client. As part of this work, we created a custom Rovo Agent to gather context, analyse data, and suggest the likely cause of a data issue – all before our client’s human team members even began investigating.

We also connected the datasets in Airtable and Jira using EDA (External Data Application), for greater cohesion and accuracy. Now, whenever a new entry is added to Airtable, an automated trigger fetches the relevant Airtable data/column and syncs it with Jira. This is vital for the Rovo Agent to have all the information it needs to conduct RCA.

How does the custom Rovo Agent work?

The Rovo Agent collects work item data from Jira, and pulls relevant data from Airtable (we used automation rules to achieve this, calling Airtable APIs to pull in the data we needed). The Agent then suggests the most likely root cause ‘theme’ (this could be anything from human error to configuration issue). With over 4,000 entries in Airtable alone, identifying one singular theme to focus on is an essential first step.

The Rovo Agent then runs through all related causes associated with that suggested theme. Each theme has anywhere from 1-10 associated root causes, and the Agent conducts linguistic, thematic, and logical pattern matching to suggest the most relevant root cause. We ensured that the Agent would provide a rationale as to how it made this root cause recommendation, so human users could understand how it came to a decision and, crucially, add comments if it was the wrong call, to help the Agent draw from for an improved result next time.

Finally, we added in an approval step. Our client requested this, to ensure that a human Root Cause Analyst could review the Agent’s suggestion. We built this using Jira Service Management forms.

The Benefits

Our client has been very happy with the accuracy of the custom Rovo Agent so far, and the automated process as a whole.

‘I expected far fewer accurate responses… Rovo has exceeded my expectations.’ – Operational Excellence Consultant, Global Insurance Firm

During a dedicated testing period, the custom Rovo Agent could correctly identify the root cause theme 70% of the time.

As a long-term project, our client also expects the custom Rovo Agent to guide the team towards improved data quality and accuracy – alongside freeing up human time to focus on the most complex RCA cases.

Our accreditations

Atlassian Cloud Migration Specialised Badge

Atlassian Service Management Specialised badge

SOLUTIONS

Rovo AI Accelerator

Turn to AC to guide you through your full Rovo and AI adoption process. From discovery and design to training and rollout, you’ll unlock new levels of AI-powered efficiency and smarter decision-making. Whether you’re looking to embed sustainable internal AI processes, or create your own library of powerful custom Rovo agents, we can help you realise value from Atlassian Rovo AI capabilities faster, more effectively and securely.

Find out more about our Rovo AI Accelerator

Ready to explore what Rovo Agents could do for your team?

If you’d like advice on your own RCA workflows or want to discuss building a custom Rovo Agent, our experts are here to help.