# Lumis: Case Study | Gr8r Studio

> Lumis: an AI workspace where every page has an assistant beside it. How we designed an AI automation product that drafts, summarises and runs workflows for a team, and keeps a person in charge of every result.

Source: https://gr8rstudio.com/work/lumis

# Lumis: an AI workspace where every page has an assistant beside it.

How we designed an AI automation product that drafts, summarises and runs workflows for a team, and keeps a person in charge of every result.

Built by Gr8r for its own portfolio. Not client work.

Client

Lumis

Project

AI automation web app

Platforms

Web app, desktop-first

Deliverable

Desktop screens + design spec in Figma

- [Product Design](https://gr8rstudio.com/services/product-design)

[Discuss your product](https://gr8rstudio.com/contact)

The problem

## AI help is scattered across tabs.

A product team writes briefs, reviews PRDs, summarises feedback and prepares decks every week. The AI that helps lives in separate chats and tools, so its work is hard to find, hard to check and easy to lose. We designed Lumis around one idea: the assistant sits inside the workspace, next to the work, and everything it does is labelled and reviewable.

- 1
### AI work gets lost
Drafts and summaries end up in chat histories, away from the documents and tasks they belong to.
“What did AI do for us today?”
- 2
### Output is hard to trust
A generated brief arrives without a source, a model or a confidence level, so someone rereads everything.
“Can I use this as it is?”
- 3
### Repeat jobs are done by hand
The same brief-from-meeting-notes job runs every week, and every time someone starts it from scratch.
“Can this run on its own?”

Where the day starts: what AI did, how well, and the one thing that needs attention next.

Every conversation is a named thread with tags, people and quick actions to continue it.

Information architecture

## Work first, team and setup after.

The sidebar follows how a team uses the product: the AI workspace, the people and their board, then configuration, with active threads pinned below.

Lumis

1. Workspace

  - Command Centre
  - AI Threads
  - Documents
  - Insights
  - AI Agents
  - AI Automation
2. Team

  - Team Members
  - Workspace Board
3. Configure

  - Integrations
  - Settings

The workflow

## From raw notes to a reviewed result.

1. 1
Ask
Start a thread, or let an automation pick up a new document.
2. 2
Draft
An agent drafts, summarises or finds gaps, with its model shown.
3. 3
Review
Apply, retry or edit the result. Low confidence goes to a person.
4. 4
Track
Activity, accuracy and time saved roll up to the Command Centre.

The product

## An assistant that shows what it did.

Six close-ups of how the interface keeps AI work visible, checkable and under the team's control.

1. Command Centre
### The day's AI work, on one screen.
Four KPIs show queries, time saved, documents drafted and accuracy. Every item in the activity feed says what AI did to it, and the Lumis panel adds a page summary, key insights and suggested next steps.

  1. 1Accuracy and time saved, not just volume
  2. 2Every item labelled: drafted, summarised, reviewed
  3. 3One insight with edit, dismiss or open
  4. 4The AI panel on every page
2. AI Threads
### Conversations that stay with the work.
Each thread has a title, date, tags and the people involved. Answers come back as structured points with copy, share and regenerate, and quick actions continue, expand or condense the thread.

  1. 1Threads labelled by what AI did
  2. 2Tags and people on every thread
  3. 3Answers as clear, scannable points
  4. 4Summarise, continue, expand, condense
3. Documents
### AI editing inside the document.
An AI-drafted document shows its word count, model and last edit. Lumis AI Assist sits beside it with six actions, and every result waits for Apply, Retry or Copy before it touches the text.

  1. 1AI-drafted, and marked as such
  2. 2Words, model and last edit
  3. 3Summarise, rewrite, find gaps, translate
  4. 4Nothing changes until you apply it
4. AI Agents
### Agents with a report card.
Every agent shows its model, accuracy, number of runs and last run. Scores for accuracy, quality, speed and trust sit beside a live chart of request volume and response time.

  1. 1Active and inactive agents, with model and accuracy
  2. 2Accuracy, runs and last run up front
  3. 3Accuracy, quality, speed and trust
  4. 4Volume and response time, live
5. Configuration
### Set up an agent without code.
The system prompt, model, maximum tokens and fallback behaviour are plain fields. Test Agent runs it before Save Configuration puts it to work.

  1. 1The prompt, readable and editable
  2. 2Pick the model per agent
  3. 3A fallback when something fails
  4. 4Test before you save
6. AI Automation
### Workflows with a safety net.
A canvas links a trigger, an AI action and a condition. Results above 85% confidence go straight to Docs; the rest are queued for a person to review. An execution log records every run.

  1. 1Running and paused automations
  2. 2Low confidence goes to a person
  3. 3Configure each step in place
  4. 4Every run logged with its confidence

Interaction

## Three answers, then a useful first screen.

Onboarding asks for a role, a use case and a goal, then shows the first insight before the workspace opens.

1. Profile Establish your professional context Pick a role and a primary use case, and add a goal in your own words, or skip.
2. Personalise Personalizing Lumis A short checklist shows the work in progress: profile saved, training on your role, first insight, workspace.
3. First insight Your first insight A card generated for you, with its confidence, recent AI activity, the most urgent item and recommended next steps.

Style guide

## Typography & colours.

Instrument Serif for headings and titles, Geist for body, labels and buttons. A warm near-white base, three text greys and dark buttons keep the focus on the work, with the gold Lumis mark as the only accent.

Primary text

HEX #0E0E0C

Text/Primary

Border

HEX #E5E5E5

- Secondary text
HEX #747474
Text/Secondary
- Muted text
HEX #969695
Text/Muted
- Card
HEX #FAFAF8
Surface/Card

Geist

- Regular
- Medium

Every screen

## Every screen, straight from the file.

Final designs from the product file, with demo data: sign-up, threads, documents, the team board, agents, automations and settings.

- Create your Lumis account
- AI Threads
- Documents and folders
- Workspace Board with tasks by status
- Agent run history
- Create a new workflow
- AI preferences

Design system

## A small, strict spec behind every screen.

Every screen is built from the same type scale, surfaces and controls, written down in the file so engineers build from the spec rather than from screenshots.

- Instrument Serif headings, Geist body and labels
- Type scale: 24/32, 20/24, 14/20, 12/18
- Cards: 1px #E5E5E5 border, 8px radius
- 32px buttons, 20px badges, 16/20/24 icons

Outcomes

## A complete product, designed and ready to build.

What we delivered. Measured business results will be added only with evidence and approval.

- ### One assistant, every page
The Lumis panel and AI Assist bring summaries and next steps to the dashboard, threads and documents.
- ### AI people can check
Labels, models, accuracy and confidence sit beside every result, and nothing is applied without a person.
- ### Automation with a fallback
Agents and workflows are configured in plain fields, with low-confidence results routed to review.

## Designing an AI product people will trust?

Gr8r helps teams turn complex data and AI workflows into clear products and working software.

[Discuss your product](https://gr8rstudio.com/contact)

## Next project

- [SaaSCRMCloseCRMA structured CRM for busy sales teams: tasks, deals, records and automation that reps can scan in seconds. Read the case study ](https://gr8rstudio.com/work/closecrm)
- [AIAnalyticsPulse AIAI analytics that detect what changed, explain why with visible evidence and suggest what to do next. Read the case study ](https://gr8rstudio.com/work/pulse-ai)
- [AIFintechLedgerOSFinance operations where AI agents handle the routine work and people make the risky calls. Read the case study ](https://gr8rstudio.com/work/ledgeros)
- [SaaSProductivityTask Management AppOne workspace for projects, tasks, deadlines and updates, from each person's list to the company timeline. Read the case study ](https://gr8rstudio.com/work/task-management-app)
- [AISaaSSellerOSOne workspace for marketplace sellers: sales, stock, shipments and profit, with an AI briefing. Read the case study ](https://gr8rstudio.com/work/selleros)
- [ProcurementOnboardingVelunoSupplier onboarding with parallel reviews, documents, renewals and a supplier portal in one workspace. Read the case study ](https://gr8rstudio.com/work/veluno)
- [AIAutomationRelayA workflow automation workspace where AI agents run the work and people approve the risky steps. Read the case study ](https://gr8rstudio.com/work/relay)
- [DronesLogisticsSortieMission control for autonomous delivery drones, with a live 3D map of every flight. Read the case study ](https://gr8rstudio.com/work/sortie)
- [LogisticsOperationsAxleA fleet command centre for live tracking, dispatch, safety, compliance and maintenance. Read the case study ](https://gr8rstudio.com/work/axle)
- [HealthcareSaaSCendaraHealthcare claim denials worked to resolution: documents, appeals, reviews and payer replies. Read the case study ](https://gr8rstudio.com/work/cendara)
- [3DLogisticsLoadlineA transport operations platform with 3D load planning, dispatch and live fleet tracking. Read the case study ](https://gr8rstudio.com/work/loadline)
- [WebsiteTravelContrailFlight search where every flight opens a 3D model of its aircraft, so you choose your seat inside the cabin. Read the case study ](https://gr8rstudio.com/work/contrail)
- [WebsiteLearningKnowspaceA zoomable canvas of surprising facts, explored by topic, search and a small daily goal. Read the case study ](https://gr8rstudio.com/work/knowspace)
- [BrandingReal estateHostOpA brand identity for a real estate operations platform: one mark and one blue, from the app icon to the billboard. Read the case study ](https://gr8rstudio.com/work/hostop)
- [WebsiteWellbeingHinterlandAn illustrated mental health publication: topics, essays, short practices and a clear route to support. Read the case study ](https://gr8rstudio.com/work/hinterland)
- [WebsiteAgencyAtlasA design agency website told as a gallery visit, with old master paintings reworked as dot prints. Read the case study ](https://gr8rstudio.com/work/atlas)
- [UX auditProcurementVeluno UX AuditOur own supplier onboarding product, audited like a client’s: 13 findings, 3 high, and what to leave alone. Read the case study ](https://gr8rstudio.com/work/veluno-ux-audit)
- [UX auditHealthcareCendara UX AuditOur own claims product, audited like a client's: 12 findings ranked by impact, from sideways tables to hidden logins. Read the case study ](https://gr8rstudio.com/work/cendara-ux-audit)

Ask Ali