Hire Your First Employee

Follow this guide to end up with a “news assistant” that organizes the market trends you care about every morning. Takes about 5 minutes.

In UpServe you don’t write behavior instructions by hand. Press hire and someone new starts right away, and they ask you what the job is themselves. You just answer like you would a new colleague, and they write their own name, mission, and personality from that conversation.

Prerequisites

• An UpServe account (sign up at upserve.app )
• 1 to 3 keywords you care about (e.g. “AI startups”, “semiconductor market”)

The Manager (your AI manager) is already there the moment you sign up. Right after sign-up the manager opens and shows a Getting started card that walks you through the same steps as this guide. On the web, even after you close the manager, a Getting started bar stays at the top of the screen, so you can see which step you’re on without opening the manager. Finishing a step shows a small celebration and moves you on to the next one. Feel free to skip it and pick it up later. In the mobile apps, open the manager to check your progress.

Step 1: Press hire

1. Open the Home screen 
2. Click the + Hire button at the top of the screen (the sidebar’s + → Hire goes to the same place. On mobile, tap + at the top right → Hire)
3. Confirm on the dialog. On web it reads “Hire a new employee?” with a Confirm button; in the mobile apps the button says Hire

That card asks one thing and one thing only. No name, no job, no specs. The new employee asks about all of that themselves.

Confirming creates the employee immediately and opens their chat. There is no waiting screen.

Step 2: The new hire asks first

Your new employee opens by asking what job they’re taking on. That conversation is their Work setup.

New hire: Hi, I started today. Could you tell me what I’ll be working on?

You: Keep an eye on the markets I care about and brief me every morning. Mostly AI startups and semiconductors.

New hire: So the job I’d be taking on is a morning briefing on the market, centered on AI startups and semiconductors, right? I’ll plan on delivering it at 8 AM every day as a summary you can read in five minutes.

You: Yes, that’s right. Call yourself Morning Brief.

When the instruction is specific, the new hire doesn’t ask about each detail one by one. It names the job back in one sentence and picks a sensible default for anything left open, like the time. The “8 AM” above is a default the new hire chose for itself; if it doesn’t suit you, just say so. Once you confirm, it carries on with Work setup; if you want to see a result right away, just ask for one as in Step 4 below. When the instruction is vague (“just keep an eye on things for me”), it asks a short question first and proposes a few concrete job candidates.

You don’t have to pick a name. If you don’t, the new hire chooses one from the conversation and shows it in the confirmation summary (Step 3), where you can ask for a different one.

What the new hire decides for themselves

Every change is shown to you as a card. Each time the new hire writes their own name, mission, or personality, a card appears in the chat showing exactly what changed, with a Revert button if you don’t like it.

Work setup only ends when you confirm it

It doesn’t end on its own just because time passes. It ends only once the new hire finishes and you approve (Step 3 below). Until then, put off Work setup and the new hire just waits.

No time for Work setup right now? Just leave it. If nothing moves forward for a long while (72+ hours), the progress card at the top of the chat switches to “Setup stopped partway” so it’s easy to notice. Nothing to worry about: just say something to the new hire and it picks right back up. You can also reopen it later with the Resume Work setup button in the employee’s settings.

While Work setup is underway, the top of the chat shows a progress card with four stages (Joined → Deciding the work → Preparing the workspace → Assignment) marking how far along things are.

Step 3: Confirming ends Work setup

When things are settled, the new hire shows you a summary and asks whether to confirm. Once you do:

• The new-hire badge disappears and they become a regular employee
• Self check-in, where they look around and work on their own initiative, switches on
• The Work-setup-only ability to rewrite their own profile is taken back (name and mission are edited from Settings after this)

Approve everything they mentioned in one go

If tools or connections came up during Work setup (“I’ll use Drive”, “I’ll send emails”), a “Getting ready to work” card appears in the chat right after confirming. It lists the skills, account connections, and send permissions mentioned in the conversation, checked by default.

• One Approve all click handles skills and send permissions at once. An account connection (like Google Drive) needs its own Connect button next to that item, which opens the browser sign-in window.
• You can uncheck any item and approve only what you want.
• Approving here means the same kind of task won’t ask again later. Anything left unchecked still asks for approval the first time that tool is used, as usual.
• If tools or connections never came up in Work setup, this card doesn’t appear. The assistant just asks for approval as usual when it first needs a tool.

Installing a ready-made employee template straight from Templates (without Work setup) shows the same card right after install if that template ships with service connections or send permissions.

Right after confirming, they’ll usually propose how they intend to work.

Morning Brief: Every morning at 8 I’ll go through the last 24 hours of AI-startup and semiconductor news, and give you the five that matter plus one line on the trend to watch today. Shall I set that up to run daily?

From here you do one of two things.

• Happy with it → “Yes, do that.” → They register the scheduled run, and the briefing starts tomorrow morning.
• Want changes → Just say so. e.g. “Make it 7:30 instead of 8”, “Drop the trend line”, “Include source links”

Employees can refine their own behavior instructions through chat, so you never need to open a settings screen to edit them.

Step 4: Try it once by direct instruction

If you want to preview the result before the auto-run kicks in, just ask the assistant on the spot.

Show me today's news briefing.

When it gets your request, the assistant runs tools like web search several times on its own to gather material, manages the work steps as a checklist, and then delivers an organized result. The chat shows which tools it used and how many times (e.g. web_search (13×)) alongside the progress.

Keep it as-is if you like it, or refine it through chat:

• “Lengthen the trend line to two lines”
• “Drop the emojis”
• “Group US-listed companies separately”

This is how the assistant works in two modes side by side: (a) automatic runs: on its own through scheduled runs and self check-ins, and (b) direct instruction: instantly when you ask.

If you like the result, save how it was done. Press Draft a save request in the row that appears under the result to save it as a workflow, and next time you only swap the material (keywords, time period) and hand it over again with the same steps. For the full flow, see Save your first task as a workflow and reuse it.

Step 5: Adjust scheduled runs (optional)

Self check-in: “look around on its own”, on by default

Your assistant has self check-in on by default. While self check-in is on, the assistant looks at the situation and decides on its own when to check in next: less often when there’s nothing to do, more often when something’s pending. So even without an exact scheduled run, the assistant wakes up, looks for work on its own, and does real work within its allowed scope when needed. Each check-in uses some AI usage (SU). If you want it to only handle what you ask, turn self check-in off in the Automatic runs tab.

Want it to run at a fixed time? Add a scheduled run

If you want it to run at an exactly fixed time like every morning at 8 AM, add a scheduled run. If you accepted the assistant’s proposal in Step 3, it may already be registered. To change the time or the trigger message, just ask the assistant, or adjust it in the UI.

Ask the assistant:

Schedule this to run automatically every morning at 8 AM.

Set it up in the UI

Open https://upserve.app/agents/{agentId}/schedules (or the Automatic runs tab on the employee page) to register one. You never write a cron expression by hand.

1. Click Add scheduled run in the top right
2. At the top of the form, pick Repeat (or Once for a single, one-time run)
3. In the Request field, type the message the assistant should receive each time this scheduled run fires (e.g. Summarize today's news briefing). This field is required before you can save.
4. Choose a repeat rule: at a specific time (pick days, plus one time of day; Every day / Weekdays only shortcuts are provided) or on a fixed interval (pick one of 30 min to 12 hours, repeating all day)
5. Click Add scheduled run at the bottom of the form to register. From then on, every time this scheduled run fires, the message you typed in step 3 is sent to the assistant automatically, and it acts on its own behavior instructions, so you don’t have to send a chat message yourself each time. To change what it does, edit the request, or just chat with the assistant: “update your behavior instructions like so.”

Tip: For a single fire at 8 AM daily, choose at a specific time, then set Every day + 08:00.

The timezone follows your profile setting (e.g. Asia/Seoul) automatically. The first push arrives tomorrow at 8 AM.

For the full breakdown of scheduled run types (repeat/once), limits, and safeguards, see Scheduled Runs.

What happens every morning at 8 AM

   ⏰ Every day, 8 AM
        │
        ▼
 ┌──────────────────────────────────┐
 │  Morning Brief: news assistant   │
 │  (running the mission it wrote)  │
 └──────────────────────────────────┘
        │
        │  ① Web search "AI startups (last 24h)"
        │  ② Web search "semiconductor market (last 24h)"
        ▼
 ┌───────────────────────────────────┐
 │  Pick top 5 + one-line summaries  │
 │  + one trend to watch             │
 └───────────────────────────────────┘
        │
        │  ③ Deliver to user
        ▼
 📱 Push notification   ✉️ In-app chat message

Variations

The same pattern (hire → Work setup with the new employee → they propose how to operate) works for employees like:

• Competitor price assistant: “An assistant that keeps an eye on competitor price changes”
• To-do reminder assistant: “An assistant that pokes me about pending items each morning”
• Weekly report assistant: “An assistant that wraps up the week into a Friday report”

Advanced

Author the behavior instructions by hand

If you’d rather skip the full Work setup conversation and write the behavior instructions yourself, this section is for you. It’s best suited to users who already craft instructions by hand in tools like Claude Code or Cursor.

After hiring, hand the new employee everything at once (“here’s the mission, write it up and confirm”) and they’ll do exactly that in a single turn, with no back-and-forth.

Once the employee is created, you can adjust Name · Mission (core purpose) · Description, and so on, directly in the employee’s Settings screen. The AI performance tier and per-tool approval policy are changed on the employee’s Permissions screen on the web, and still in the Settings screen on the mobile apps. Just write your intended purpose clearly in the Mission field, like this:

Organize AI startup and semiconductor market trends every morning so they can be read in 5 minutes.
Focus on the few changes that can't be missed and what they mean for today.

UpServe has no separate box for writing whole behavior instructions. You steer the detailed behavior (tone, format, rules) through chat, and the assistant folds it into its own instructions. Just message the employee things like “update your behavior instructions like so” or “always attach source links”.

Tools: nothing to turn on. Every employee is born with all of them, web search included. Scheduled run: Automatic runs tab → Add scheduled run → under the repeat rule, choose at a specific time, then set Every day + 08:00 → register with Add scheduled run at the bottom of the form. (Or leave self check-in on and let the assistant look around on its own.)

Installing a template that needs customization

Some employee templates you install from Templates include items that need to be tailored to your setup, such as keywords or account connections. When you install one of these templates, a short What to delegate screen appears first. Answer the questions and your personalized employee is created automatically. Once that’s done, the UI takes you straight to the new employee’s chat screen.

For the full installation flow, see Installing Skills & Templates.

What does the manager do?

Your Manager (AI manager) doesn’t hire. Hiring is the button in Step 1. The manager does two things:

• Looks after the employees you’ve hired: ask how someone has been getting on, whether anything is stuck, how last week went, and they’ll check the actual run history before answering.
• Answers questions about UpServe: pricing, limits, where a setting lives, how a feature behaves.

The manager is already set up when you sign up, so there’s nothing to add first. On the web they’re the button at the bottom right; on mobile, the manager icon in the top toolbar. Ask where something is and they’ll often point at the button on screen for you.

The manager stays with your account at all times, so there’s no way to remove or delete it. However many employees you hire, or let go, the manager is always there.

Next steps

• Save your first task as a workflow and reuse it: Save how a result you liked was made, then rerun it with new material
• Equipping Tools: Which tool fits which situation
• Installing Skills & Templates: Use UpServe’s official skills & templates