Platform operations across every organization β analytics, users, structure, and support. Distinct from the user app, which is about a single customer's delivery.
π¬ Assistant β all
Chat about this project and I turn what we discuss into scored, estimated stories in its backlog β then we refine and align them together. Share an idea, paste documentation, or upload a doc for context below. I can also act: pull feedback, sync the dashboard, find/answer/prioritize work.
Paste documentation, a transcript, requirements, or a list of items β or upload a text document. The AI extracts scored, estimated stories into this project's backlog (skips anything already built).
π Share an idea
Describe what you'd like or what's not working. I'll ask a couple of quick questions, then log it in Azure as a scored, time-estimated story β recorded for review. No technical detail needed.
π€ Agent
Claude Code working on this project β see if it's active, and guide it with replies.
How your agent works & how to steer it
What it does
Given only your token, a coding agent pulls Ready stories through our API, builds them, moves each Active β Resolved (auto-timed), and posts questions and notable decisions back on the story. It all streams into the live activity feed on Setup.
How you steer it
Standing guidelines (build cadence, conventions, deploy/test) β Setup βΈ AI ledger β fed to the agent via config.json.
Answer its questions β Stories (the Pending queue) or Needs you.
Nudge a live session β reply in its terminal below (e.g. βpushβ, βcontinue to the next Ready storyβ).
β add it to the repo so the agent knows how to build, verify & run it.
Session history
Users
Invite people into your account by email and share an org β or just specific projects β with them. A project invite adds them to that org with access to those projects only.
Loadingβ¦
Organizations
An org holds the master credentials (Azure DevOps PAT + OpenAI key) its projects share.
Add an organization
You only need an Azure DevOps PAT (Work Items: read/write) to start β the AI runs on our platform LLM out of the box. Add your own OpenAI/Anthropic key any time to use your preferred model and lift the free monthly limit. Storage is only needed for feedback sources.
π Dashboard
Delivery over time β hours, throughput, estimates vs actuals.
Loadingβ¦
Delivery overview
β
β¦ Needs your input
Work through the open questions across your projects β answer, assign, or skip.
Checkingβ¦
New project
π Stories
Every story in this project. The Pending queue is what needs your review β set a priority (P1βP4) on each card, or open one to answer its questions and move it to Ready.
Loadingβ¦
Run the loop β no project selected
Each action runs against the selected project with its org's keys, and shows live output below.
output appears hereβ¦
π€ My profile
Your personal settings β separate from an org's shared keys. These identify you when the tool acts on your behalf.
Connections & keys
Plug in a key to unlock each connection. You only need Azure DevOps and OpenAI to start β add the rest whenever you want what they unlock.
Answer
β Add an item to
Drop in an idea, notes, or a document β we turn it into scored, estimated stories in this project's backlog. No connected source needed.
Text documents (.txt, .md, .csv, .json, .log) are read here and added above. For richer/binary docs or ongoing intake, connect a feedback source (Teams, email, store).
β Add a story to
Straight onto the board β no AI. Use this when you already know the work.