PROJECT MANAGEMENT

Mid-Sprint At-Risk Digest to Email and Discord

Mid-sprint, scans Linear for issues that are behind schedule or have stalled, ranks them by risk, and sends a prioritized at-risk digest to the team via email and Discord.

CategoryProject Management
Enginesim
Difficultyintermediate
Triggerschedule
Steps6
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerSprint-midpoint schedule
  • ActionFetch open active-sprint issues from LinearLinearLinear
  • LogicScore each issue by delivery risk
  • ActionWrite ranked at-risk digestOpenAI
  • OutputEmail digest to teamGmailGmail
  • OutputPost digest to Discord channelDiscordDiscord

What it does

Gives a mid-sprint reality check on what won't land. Halfway through the sprint it pulls Linear issues that are still open with little recent movement, past their target date, or carrying too many points for the days remaining, ranks them by delivery risk, and broadcasts a prioritized digest so the team can rescope before it's too late.

When to use it

Use it when sprints routinely slip and you want an early warning instead of a Friday surprise. Good for leads who want a ranked 'these are in trouble' list without combing the board themselves.

How it works

  1. 1A schedule fires on the sprint midpoint, typically Wednesday morning.
  2. 2The flow pulls open Linear issues for the active sprint with last-update time, estimate, and target date.
  3. 3A logic step scores each issue's risk from staleness, remaining estimate, and days left.
  4. 4An LLM step writes a ranked at-risk digest with a short reason per issue and suggested action.
  5. 5The digest goes out by email to the team and is posted to the sprint Discord channel.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect LinearIssues, projects, cycles, triage.
  2. 2
    Connect OpenAIModels, embeddings, files.
  3. 3
    Connect GmailRead, draft, send, label.
  4. 4
    Connect DiscordCommunity channels + voice + bots.
  5. 5
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  6. 6
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  7. 7
    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.