2.1 Workspaces and Automation: Let the Work Continue
There are two kinds of work you can bring to AOS Work.
One is a one-off task — "summarize this document" — raised, finished, done.
The other is ongoing work — a season, a buying round, a product launch — which runs across several stages, each one depending on the conclusions of the last.
Handling the second like the first means a new session at every step and the same background explained again: which season, which competitors, where the data sits, what format to output. By the third repetition the cost is obvious.
What a Workspace Is
A workspace is a long-lived space for one business topic: conversations, files, and outputs in one place, with later sessions able to build on earlier conclusions.
The product has three names across two levels:
| Name | What it is | Where it sits in the sidebar |
|---|---|---|
| Task | One conversational execution | The session you have open |
| Standalone conversation | A task outside any workspace | The "Conversations" group |
| Workspace | A container of tasks for one business topic | The workspace list |
In short: a task is the unit of execution, a workspace is the unit of organisation. With no workspace selected, the task goes to a standalone conversation; with one selected, it belongs to that workspace.
Deciding Whether You Need One
The test is not "how big is this". It is three conditions:
| Condition | The question | If it holds |
|---|---|---|
| Context reuse | Will the next task refer back to this one's material or conclusions | Yes → create a workspace |
| Output consolidation | Do the outputs need to sit in one place for review or handover | Yes → create a workspace |
| Shared assets | Will the same files, tables, or knowledge be called on repeatedly | Yes → create a workspace |
When none of the three holds, a standalone conversation is lighter: the output is delivered and the work ends.
Two cases do not need one: the goal is still being explored and the boundary keeps moving, or you simply need somewhere to store files — that is Library, not a workspace.
Three Typical Scenarios
Scenario A: Seasonal range selection and the buying meeting (about 6 weeks, 5 stages)
| Stage | What happens | Handover |
|---|---|---|
| 1 | Pull last season's sales and sell-through data; produce a sell-through and slow-mover list | Sales and inventory tables in Base |
| 2 | Competitor and trend research; produce a trend brief | Trend brief in Library |
| 3 | Produce the range plan and SKU structure | The "Range Review" table in Base |
| 4 | Build the buying meeting deck | Brand templates and deck in Library |
| 5 | Write back orders after the meeting and review selection accuracy | Order table in Base |
With and without: tasks scattered across conversations require separate searches for material and decisions. Grouping them in one workspace and identifying the Base records and Library files makes all five stages easier to review.
Scenario B: Supplier onboarding and contract review (2–3 weeks once, re-reviewed annually)
| Stage | What happens | Handover |
|---|---|---|
| 1 | Collect qualification documents and contract versions | Supplier folder in Library |
| 2 | Compare against standard clauses and flag differences | Standard clauses in Library |
| 3 | Produce the risk list and remediation requirements | Supplier register in Base |
| 4 | Follow up remediation over several emails | The inbox read and written through a Connector |
| 5 | Annual re-review, citing the previous round's conclusions | The previous workspace |
With and without: clause versions, risk judgements, and remediation records scattered across conversations take time to find during re-review. Grouping them in one workspace makes review and consolidation easier.
Scenario C: New product launch content (about 2 weeks, 4 channels)
| Stage | What happens | Handover |
|---|---|---|
| 1 | Extract selling points from reviews and after-sales records | Review analysis table in Base |
| 2 | Generate multilingual copy | Writing standards in the Skill |
| 3 | Produce hero images and detail pages | Brand assets in Library |
| 4 | Adapt size and length to each channel's rules | Channel specification table in Base |
| 5 | Review conversion and return reasons after launch | Content performance table in Base |
With and without: the channel adaptation stage keeps referring back to stage 1's selling points and stage 3's assets. Grouping these tasks in one workspace makes the material easier to find and reference in the next task.
When You Do Not Need One
Translate a contract, tidy up meeting notes, capture a few competitor screenshots — a standalone conversation is enough. The test: the output is delivered and the work ends, it will not be cited by a later task, and no one else needs to take it over.
The Boundary Rule: By Business Cycle, Not by Department
A workspace boundary should line up with a deliverable: a season, a buying round, a launch, an onboarding review. Three reasons:
- Memory already holds the person. Role and preferences apply across workspaces, so there is no need for one per person.
- Shared assets live in Library and Base. Workspace tasks can reference those materials and save files generated during the task.
- Hand over through specific outputs. In the new conversation, name the workspace file, Library file path, or Base table and records to continue the work.
The third is the most practical: turning "what we said last time" into "which table we wrote, which file we saved" is what lets someone else take the work over.
Creating and Using One
- Start a conversation. Click 【New Chat】 on the left.
- Select or create a workspace. Use the workspace area above the input box to pick an existing one or create one, for example "Spring 2027 launch".
- Work inside it. Every message and output belongs to that workspace.
- Review outputs. Task Outputs holds every deliverable in one place and can trace back to the source message.
- Continue the work. In the next conversation, specify the files, records, and earlier conclusions to reference.
For creating a workspace and continuing a conversation, see New Tasks and Conversations. For files and source-message navigation, see Task Outputs.
Exercise: Continue from a Report to an Owner Checklist
Complete two conversations in the demo workspace named Product Team. First, select the added Weekly Report Work package and turn the work notes into a report named Weekly Report.md.
Click 【New Chat】 and select the same workspace and Work again. Ask the agent to read that report, identify the owner of each task, and save the list as Owner Checklist.md.
How Workspace and Memory Divide the Job
| Comparison | Memory | Workspace |
|---|---|---|
| Content | Your preferences, habits, role | The files, conversations, and outputs of one topic |
| Scope | Global, across all sessions | Local to that workspace |
| Question it answers | "Who am I and how do I work" | "Where has this piece of work got to" |
They work together: Memory tells the agent who you are; the workspace tells it the background of this work.
How Workspace and Skill Divide the Job
| Comparison | Workspace | Skill |
|---|---|---|
| Provides | Context (files, history, outputs) | Method (how this class of task is done) |
| Scope | One business topic | One class of task |
| Rate of change | Evolves as the work advances | Relatively stable, revised occasionally |
One workspace can invoke several Skills. The workspace supplies the background, the Skill supplies the method — together they make the collaboration repeatable.
Workspaces and Automation: Let the Flow Run
A workspace solves context persistence, but if you still start every run by hand, you have removed the explanation and kept the action.
To repeat the work at fixed times, combine the workspace with a scheduled task: create a task in 【Scheduled Tasks】 and select its workspace, the agent runs on its own timetable, and the result waits for you there.
| Scenario | Pain | Trigger | Automated flow |
|---|---|---|---|
| A. Daily industry brief | 30 minutes browsing, still missing things | Daily 09:00 | Search the news → filter for business relevance → build a structured brief (3–5 items with summary and source) → email it |
| B. Sales monitoring | Two hours every Monday on week-on-week comparison | Mondays 09:00 | Pull the data table → compare with last week → flag growth, decline, anomalies → generate an HTML report → send to management |
| C. Competitor social monitoring | Manual checks, easy to miss | Daily 08:00 | Collect competitor posts → classify and analyse → generate a weekly report → write to the table and send |
| D. Contract expiry alerts | Renewal windows slip past | Daily 08:00 | Scan the contract register → find items expiring within 60 days → build an alert list → email the owner |
For creating one, changing the schedule, and reviewing runs, see Scheduled tasks.
Summary
Use a standalone conversation for a one-off task and a workspace for ongoing work. Three tests: will it be cited later, do the outputs need consolidating, and will the assets be shared.
One level up, the chain runs itself — with a scheduled task attached, your role moves from initiator to reviewer. The next lesson turns to capability building, starting with how a Skill is structured inside.
1.10 Choose Resources and Deliverables for Your Task
Match resources to the task, then specify the source material, output format, and destination.
2.2 Understanding a Skill: Structure, Progressive Disclosure, and Reuse Value
Lesson 1.5 covered what a Skill is and how to install one. This lesson looks inside — how it is organised and why.