PROJECT MANAGEMENT

Weekly Sprint Velocity Roll-up from GitHub to Confluence

At sprint end, tallies merged pull requests and closed issues from GitHub, computes throughput stats, and publishes a velocity report page in Confluence for stakeholders.

CategoryProject Management
Enginesim
Difficultyintermediate
Triggerschedule
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerFriday sprint-close schedule
  • ActionFetch merged PRs and closed issuesGitHubGitHub
  • LogicAggregate throughput and cycle-time stats
  • ActionWrite velocity narrativeOpenAI
  • OutputPublish report page to ConfluenceConfluenceConfluence

What it does

Generates the weekly engineering velocity report automatically. At the close of each sprint it gathers merged PRs and closed issues from your GitHub repos, computes throughput and cycle-time figures, has an LLM write the narrative summary, and publishes a clean Confluence page so leadership gets a consistent record without an engineer assembling slides.

When to use it

Use it when you report sprint outcomes to non-engineering stakeholders in Confluence and want the numbers and narrative produced consistently each week. Good for eng managers who currently hand-build status pages.

How it works

  1. 1A schedule fires every Friday afternoon at sprint close.
  2. 2The flow queries GitHub for PRs merged and issues closed during the sprint window across the configured repos.
  3. 3A logic step aggregates the raw events into counts, per-author throughput, and average time-to-merge.
  4. 4An LLM step turns the metrics into a readable velocity narrative with highlights and risks.
  5. 5The report publishes as a new Confluence page under the team's sprint space, ready to share.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect GitHubRepos, issues, pull requests, actions.
  2. 2
    Connect OpenAIModels, embeddings, files.
  3. 3
    Connect ConfluenceSpaces, pages, blueprints.
  4. 4
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  5. 5
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  6. 6
    Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.

Run this workflow in your colony.

14-day trial. No DevOps. No Sales call. Provisioned in under a minute.