Create Sprint retrospective agent

[Anuj Batta]

Can someone please help me in creating Sprint retrospective agent , Create capacity and velocity predictability agent .

please make it in such a way that i enter team label and it creates 

Please provide me agent instructions

[Rodrigo De Sebastian Martin]

Hi @Anuj Batta 

My name is Rodrigo, I am a Product Manager in the Jira Team. I really like your comment and I am wondering if you would like to have a call to share more details about this new Agent that you have built.

We have recently launched a new Jira Delivery Agent that helps to identify risks, dependencies and stalled work. https://support.atlassian.com/rovo/docs/work-with-jira-delivery-agent/

If you could test it and share feedback with me, I will be very happy to hear about how our Agent can help you and how can be compatible with yours.

This is my calendar link: https://calendar.app.google/ZiQjQymT7vV9afkm9

Thank you,

Rodrigo

[Sami Shaik]

Hello @Anuj Batta , the article @Arkadiusz Wroblewski linked gives you good scaffolding, so let me add the part you actually asked for: instructions you can paste and adapt, for both agents.

Agent 1: Sprint Retrospective Prep. In Rovo Studio, create an agent and give it instructions along this shape:

You prepare sprint retrospectives. When asked, work on the most recently closed sprint for the board or project named in the request. Produce, in this order:

(1) completed vs carried-over work items, with counts.

(2) bugs opened, closed, and reopened during the sprint.

(3) blockers: which items were blocked, for how long, and the stated reason.

(4) cycle-time outliers: items that took notably longer than the sprint's average, with links

(5) wins worth naming: epics closed, milestones reached

(6) exactly five discussion questions for the team, each tied to something in the data above, never generic. Format as short sections with the item links inline. Do not invent data: if something cannot be found, say so explicitly.

Add your board's project and your retro space in Confluence as knowledge, keep the Jira skills enabled, and test it in the agent preview against your last real sprint before the team ever sees it. That last instruction line matters more than any other: agents that are told to admit gaps are dramatically more trustworthy in a retro.

If you want it fully automatic: pair it with an automation rule on the sprint-completed trigger, using the agent action, so the summary posts itself while the sprint is fresh.

Agent 2: capacity and predictability, with a team label as input. Here is where I will save you a frustrating week: do not ask the agent to compute velocity. Language models are excellent narrators and unreliable accountants; asking one to sum story points across six sprints of raw work items produces confident, occasionally wrong numbers, which is fatal for exactly this use case. The shape that works in practice:

1) Let something deterministic do the counting. A scheduled automation (or a dashboard you already trust) maintains the per-sprint numbers per team: committed points, completed points, carried over, per team label. A simple Confluence page the automation updates each sprint close is enough.

2) Let the agent narrate. Instructions along this shape:

You analyse delivery predictability. The request will include a team label: use it to select that team's rows from your knowledge source. Compare committed vs completed across the last five sprints, describe the trend in plain language, name the say-do ratio direction without inventing precision, flag sprints where scope grew after start, and end with two risks and one question the team should discuss. If the label is missing, ask for it before answering. If data for a sprint is absent, say so rather than estimating.

Point its knowledge at the automation-maintained page, and the agent becomes genuinely reliable, because every number it speaks was counted by a rule, not guessed by a model. The division of labour is the whole trick: deterministic tools count, the agent explains.

Both templates are starting shapes: expect two or three preview-and-adjust rounds against your real data before the output feels like your team. And one honest caveat that applies to both: these agents surface data hygiene instantly, so if sprints close loosely or blockers go unlabelled, the first thing the agent will teach you is that. Useful, but worth warning the team.

[Howard Berkman]

A little late on this one, but hopefully it can still help some people!  I'm a Scrum Master, and I'd split it into two agents rather than one, because they carry very different risks.

The retro agent is the safe one. Scope it hard to the current sprint only, and give it a fixed output shape. Something like: summarize completed / carried-over / in-progress counts; flag bug trends; list blockers with their dependencies; call out wins; then generate 3–5 discussion questions from what it found. For the team label, tell the agent to ask for it up front and use it in the underlying JQL filter — that gets you the reusability you're after without building one agent per team.

The velocity/predictability agent is where I'd slow down. Forecasting is exactly where these tools are most confidently wrong. There's a good write-up elsewhere in this community from a team whose agent invented entirely fictional releases, with full names and timelines, whenever the data didn't contain what it was asked about. For anything predictive: require it to list the actual work items behind every number so you can spot-check, and treat the output as a draft for the humans in the room, not an answer. A retro summary that's slightly off wastes five minutes. A capacity forecast that's confidently wrong plans your next sprint into a wall.

Run both against a sprint you already know the truth about before trusting either. Happy to share the instruction blocks I use if useful.

[Arkadiusz Wroblewski]

Hello @Anuj Batta 

Somebody already covered that Topic with small Article quite some time Ago

https://community.atlassian.com/forums/Atlassian-AI-Rovo-articles/Building-a-Rovo-Agent-to-Supercharge-Agile-Retrospectives/ba-p/3100759 

Begin with that as it can be good entry point for you.

Best,

Arek🤠

[Khrystyna_Dzhus_SaaSJet_]

Hi @Anuj Batta

If resolving everything from a team label becomes difficult with a custom Rovo setup, there is also a ready-made option you could try.

Time in Status by SaaSJet includes a Sprint Report Insights Rovo agent that automatically generates a retrospective based on sprint data — completion rate, velocity, scope changes, workload, work item distribution, key observations, and recommendations.

The main difference from your use case is that it works from a selected board and sprint, rather than from a team label.

So it may not replace the exact flow you described, but it could be useful if you’re looking for an already-built retrospective agent instead of creating the whole analysis from scratch.

Disclosure: I’m part of the SaaSJet team.