created rovo agent for perform the weekly analysis and generate report

Question

I have created rovo agent for perform the weekly analysis and generate report of identifying top 5 problem request we received on weekly basis in which escalation required, below prompt i used: Analyzes support tickets from the last 15 days, identifies the Top 5 problem types, assesses Engineering escalation need, and generates an executive summary. You are a Support Operations Analyst. Your job is to analyze recently created support tickets and produce a clear weekly trend report for Support and Engineering leadership. Scope Analyze only tickets created in the last 15 days. Use these fields only: Summary, Status, Issue Type, Priority, Labels, Components, Created Date, Resolution. Do NOT use the Description field unless absolutely necessary (to minimize context usage). Analysis Requirements Group similar tickets into meaningful problem types/trends based primarily on the Summary field. Identify the Top 5 problem types by ticket volume. For each of the Top 5 problem types provide: Problem type name Total number of tickets Number of currently Open tickets List of relevant Jira ticket keys 2–3 representative ticket summaries Priority breakdown (if meaningful) Engineering Escalation Assessment (for each of the Top 5): Recommend Yes / No / Monitor Base the recommendation on: frequency, recurrence of the same technical problem, customer/business impact, production impact, and blocker/critical symptoms mentioned in the summary. Do NOT rely solely on the Jira Priority field — priority data can be inaccurate. Explicitly highlight any potentially under-triaged blockers or high-impact issues. Output Format (strictly follow this structure) Weekly Support Trend Analysis Reporting Period: [Start Date] – [End Date] Generated on: [Today’s date] Top 5 Problem Types (Summary Table) Number Problem Type Tickets Open Escalate to Engineering? 1 [Problem Type Name] X Y Yes / No / Monitor 2 [Problem Type Name] X Y Yes / No / Monitor 3 [Problem Type Name] X Y Yes / No / Monitor 4 [Problem Type Name] X Y Yes / No / Monitor 5 [Problem Type Name] X Y Yes / No / Monitor Detailed Breakdown

* [Problem Type Name] Total Tickets: X Open Tickets: Y Ticket Keys: KEY-123, KEY-124, KEY-125... Representative Summaries: "..." "..." "..." Priority Breakdown: High: A | Medium: B | Low: C Engineering Escalation: Yes / No / Monitor Rationale: [brief explanation] (Repeat the same detailed structure for problem types 2–5) Key Observations & Trends Bullet points of important patterns Recommendations for Engineering Numbered list of actionable recommendations Potentially Under-Triaged High-Impact Issues List any tickets that appear to be blockers or high-impact but have lower priority Source Data JQL used: project = "YOUR-PROJECT-KEY" AND created >= -15d ORDER BY created DESC S" And then i created automation that publish confluence page based upon agent analysis, now I want automation can also edit top 5 issues field problem type identify as problem. let me know how to fix automation

Josh · Answer

Hi Gurinder, building on Jovânio's JSON suggestion, here's the part that usually trips people up: Automation can't nest a branch inside a branch. So "for each problem type → for each key" won't work as one loop. Flatten it:

* Ask the agent to return only JSON in a fixed shape, with the problem type restricted to the exact option names of your "Problem type" field (select lists reject anything that doesn't match exactly):
{"p1":{"type":"Login failures","keys":"SUP-123,SUP-124"},"p2":{...},...,"p5":{...}}
* Right after Use Rovo agent, add Create variable actions: p1type = {{agentResponse.asObject.p1.type}}, p1keys = {{agentResponse.asObject.p1.keys}}, and so on for p2 to p5. Variables stay available inside later branches, which is why you capture them first.
* Add a Log action printing all ten variables and run the rule once. If the keys look right in the audit log, the rest is simple.
* Add five Branch rule / related work items → JQL blocks: key in ({{p1keys}}), then Edit work item → Problem type = {{p1type}}. Repeat for p2 to p5.
* Put an If: {{p1keys}} is not empty condition in front of each branch. An empty key in () is a JQL error and will fail the whole rule.

Your Confluence publish step can stay as it is and use the human-readable part of the response.

One thing to watch: the model will name and group the "problem types" a bit differently each week, which makes week-over-week trends hard to compare. If stable recurring categories are what leadership really wants, Root Cause is built for exactly that on service desk tickets. It groups related issues into root-cause themes and gives you an analytics view of what keeps coming back.

Disclosure: I work at Aneto Software, which makes this app.

Jovânio Junior · Answer

Hi, welcome to the Atlassian Community!

Yes, you can do this, but I’d change the agent output slightly.

When a Rovo agent is called from Automation, it doesn’t directly edit Jira issues using its own tools. It returns a response, and then the following automation actions need to use that response.

For your case, I’d ask the agent to return the Top 5 results as raw JSON, for example:

{
"topProblems": [
{
"problemType": "Login failures",
"issueKeys": ["SUP-123", "SUP-124", "SUP-130"]
}
]
}

Then in Automation you can parse it with:

Atlassian specifically recommends .asObject when you need to extract values from structured JSON returned by a Rovo agent.

The flow would be roughly:

Scheduled trigger → Use Rovo Agent → Branch through returned issue keys → Edit issue → set “Problem Type” field

I’d also add a Log action first to confirm that the JSON is being parsed correctly before editing the tickets.

So the key change is: don’t ask Rovo only for a human-readable report. Ask it to return a structured JSON result as well, so the automation can reuse the Top 5 issue keys and problem type values.

Hope this helps!