Sidekick is the front door#
When you open LumenFlow, you land in Sidekick. You ask for what you need, Sidekick plans the work, agents do it, and you approve when a decision is needed.
You do not need to learn another surface to get work done. LumenFlow's product direction is to show visual structure inside the conversation: plans, approvals, output previews, proof, and the agents involved.
The words you will see#
LumenFlow uses plain words for the things you interact with:
| Word | What it means |
|---|---|
| Ask | What you say you need |
| Job | The thing LumenFlow is handling for you |
| Steps | What will happen, in order |
| Agents | Who or what is doing the work |
| Connections | The apps and services LumenFlow can use |
| Rules | What LumenFlow is allowed to do |
| Approvals | Where you need to decide |
| Outputs | The files, docs, code, or results produced |
| Proof | The record of what happened and why |
Operator and developer surfaces may use more precise internal words such as Mission, Initiative, Runtime, Pack, Artifact, and Participant. Those are accurate in their context but not the words a consumer needs to learn first.
What Sidekick can show you#
Sidekick is a conversation, but it can render structure inline when structure helps. The visual direction is to make panels like these available in the chat as the widget system grows:
- Plan — the steps for a job, editable and approve-to-run
- Connections — what's wired up, what's missing, one tap to connect
- Approvals — approve or deny without leaving the conversation
- Outputs — preview, download, or send a generated file or result
- Proof — the record of what happened and the replay of how
- Agents — who is working on this right now and how they're handing off
- Publish/Send — pick the connected destination, confirm, and go
These are visual without being a separate canvas. LumenFlow stays one surface.
What Studio is, and is not#
Studio is the operator depth surface. Today it shows mission progress, safe operator actions, outputs, live runtime activity, and the participant classes that already have data-backed provenance. The broader agent/swarm picture is being surfaced honestly: coordinator decisions, handoffs, leases, escalations, and stuck-state panels are operator shell slots until their read-models are wired, not completed consumer workflow surfaces.
Studio is not the place a consumer goes to do work. For making something, asking a question, approving, or reviewing — stay in Sidekick.
What about the architecture words?#
If you are reading code, internal docs, ADRs, or operator surfaces you will see words like Mission, Initiative, Pack, Runtime, Artifact, Participant, WU, Build run, Replay, Coordinator, and Swarm Runtime.
Those are real. They describe the governed substrate underneath. They are not words a consumer needs to learn to use the product. The same governed work shows up in Sidekick as a Job, with Steps, Agents, Outputs, and Proof.