PROJECT MANAGEMENT

Capacity what-if assistant for sprint planning

A chat agent that, when asked about adding work to someone, reads live Asana load plus sprint capacity and answers whether the assignment fits or overcommits.

CategoryProject Management
Enginepaperclip
Difficultyadvanced
Triggerchat
Steps5
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerChat: proposed assignment question
  • ActionFetch assignee load from active Asana projectsAsanaAsana
  • LogicProject utilization with proposed work added
  • ActionReason over fit and find teammates with headroomOpenAI
  • OutputReply with fit verdict and alternatives

What it does

This is a conversational planning assistant. Ask it "can I give Priya the onboarding epic this sprint?" and it pulls her current committed hours across boards, adds the proposed work, and tells you whether it fits her capacity, by how much it would over- or under-commit her, and who has room instead.

When to use it

Use it live during standups or planning sessions when a manager wants an instant capacity check before making a call, without opening a report or doing the math manually.

How it works

  1. 1A chat message starts the conversation with a proposed assignment.
  2. 2The agent fetches the named assignee's open tasks and estimated hours from active Asana projects.
  3. 3It loads sprint capacity and computes current and projected utilization.
  4. 4It reasons over the result: does the new work fit, and if not, which teammates have free hours.
  5. 5The agent replies in chat with a fit verdict, the projected overage, and ranked alternative assignees.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect AsanaTasks, projects, milestones — everywhere.
  2. 2
    Connect OpenAIModels, embeddings, files.
  3. 3
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  4. 4
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  5. 5
    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.