Troubleshooting

When something feels off in UpServe, this page lists the first things to check, grouped by symptom. Each item follows the same shape — If you see this → Check these in order. Work through the steps top to bottom.

1. The agent isn’t responding

If you see this

• You sent a message and got no reply for one or two minutes.
• There’s no tool activity label anywhere in the chat (such as “searching the web” or “using the browser”).

Check these in order

1. Confirm it’s actually running. Look at the chat for tool activity (“searching the web”, “using the browser”, etc.). Some tasks legitimately take tens of seconds to a few minutes.
2. Check for approval or question cards. A highlighted card saying “approval needed” or “the agent has a question” blocks progress until you respond. See Approvals for details.
3. Make sure the agent isn’t paused. In agent settings, the status should be Active. An agent is automatically paused when its credit balance reaches zero — open Credits & Billing to check. An agent is also automatically deactivated if you don’t open its chat or send it a message for a week, to avoid wasted cost (you get one heads-up notification beforehand). In that case, simply reopening the chat or sending a message reactivates it automatically.
4. Refresh and retry. If the above looks fine, refresh the page and send the same message again. Most transient connection issues clear up on refresh. If the message still gets no response, a second refresh often helps.
5. Open the logs. From the agent’s side menu, open Logs to see the most recent run result and any error. If the same error keeps coming back, jump to the Advanced section below.

Note: When a model is temporarily unavailable, the agent automatically switches to a standby model within the same tier for that turn. No notification is shown — this is handled silently.

2. I rejected an approval by mistake

If you see this

• You hit “Reject” on a tool approval card, but it was actually the action you wanted.

Check these in order

1. Ask again. The simplest fix — send a message like “I rejected by mistake, please try that again”. The agent will request the same tool again.
2. Change auto-approval settings. If you use that tool often, open agent settings → Tools and turn on auto-approval for it. From then on it runs without asking.
3. Be careful with risky tools. For things like file deletion or external payments, keeping auto-approval off and reviewing each request is the safer default. The rules for what counts as risky are in Approvals.

3. My schedule didn’t run

If you see this

• You scheduled the agent to run every morning at 8 AM, but the time passed and nothing happened.

Check these in order

1. Is the agent active? Paused agents skip their schedules.
2. Credit balance. If the balance is zero, the run is skipped and the agent is automatically deactivated. A near-empty balance may run out mid-task, so top up in advance.
3. Are all required tools enabled? If a tool the schedule relies on is turned off, the run fails.
4. Open the schedule history. The Schedules side page shows each schedule’s next run time and a History button that jumps to the Logs tab. The Logs tab is where you see each run’s result status and failure reason, alongside credit usage trends and daily statistics.
5. Recheck the schedule itself. It’s easy to enter the wrong time or repeat interval. See Scheduling for how times are interpreted.

Note: During autonomous runs, if the agent repeatedly produces empty output without calling any tools, it is automatically stopped as a safety measure.

4. Push notifications aren’t arriving

If you see this

• An autonomous run finished, but no notification showed up on your phone.

Check these in order

1. In-app notification settings. Under Settings → Notifications, confirm the toggles for the categories you want (like Agent Response) are on.
2. System permission. In iPhone settings → Notifications → UpServe, Allow Notifications must be on.
3. Do Not Disturb. If the in-app DND window is on, push won’t be sent during that time range. The notification is still recorded in the app so you can see it when you reopen UpServe.
4. Device registration. If you reinstalled the app or signed out and back in, open the UpServe app once to re-register the device.
5. You’re already on that chat. If you’re actively viewing the same agent’s chat, the notification shows inline only — push is intentionally skipped. This is expected.

The full guide is in Notifications.

5. My credit usage suddenly jumped

If you see this

• Your balance is dropping faster than usual, or one agent’s usage looks unusually high.

Check these in order

1. See what’s running. The agent’s side menu → Logs shows total credit usage, model breakdown, and daily trends; the chat view groups tool calls so you can see how many times each tool ran. If you see the same tool repeating, go to the next step.
2. Is the agent stuck in a loop? If it keeps calling the same tool as if it doesn’t see its own results, message it: “use the result you already have and wrap up.” That gives it an explicit stop condition.
3. Drop the model tier. Simple tasks rarely need the top model. Lowering the agent’s model tier by one step in settings cuts cost meaningfully.
4. Trim heavy tools. Browser and computer use cost more per call. Keep them on only when needed. There’s a feel for relative tool cost in Adding Tools.
5. Review your credit plan. Free credit refresh and subscription options are explained in Credits & Billing.

6. An external service connection expired

If you see this

• A skill or tool that talks to GitHub, Linear, Notion, Slack, etc. shows “unauthorized” or “please reconnect”.

Check these in order

1. Check connection status. You can find the connection status in either of these two places:
   • Marketplace → Skills — On the skill list page, a “Reconnect required” banner appears directly on the skill card.
   • Agent settings → Skill selector — Expand the skill row in agent settings. The external service connection row appears there too; an amber warning icon shows when reconnection is needed.
2. Reconnect. Hit the Reconnect button from either location and complete the external sign-in again.
3. Scopes changed. If the external service revoked permissions or the required scopes changed, make sure to grant all the ones you need when you reconnect.
4. Retry. After reconnection, ask the agent to retry the same task.

7. A skill keeps failing or was deactivated

If you see this

• A skill card shows a red health dot.
• You received a library cleanup notification and the skill is listed under “Often failing”.
• Or you received a skill deprecated notification.

Check these in order

1. Open Settings → Skill library cleanup. Find the skill in the candidates list and note its category.
2. If the skill is listed as “Often failing” — identify the likely cause and choose an action:
   • If an external service login expired, reconnect from agent settings or the Marketplace skills list (see section 6 above).
   • If the external service changed its API, search the Marketplace for a replacement skill that does the same job.
   • If you want to fix it yourself, fork the skill and make the changes directly.
3. If the skill is listed as “Deprecated” — the original author has marked it as no longer maintained. Search the Marketplace for a successor or updated alternative, or fork the skill to maintain it yourself.
4. If an expired external service login is the cause — follow the steps in section 6 to reconnect.

8. Someone I shared with can’t open the link

If you see this

• You sent a share link to someone outside UpServe, and they report seeing “link unavailable” or “temporarily blocked”.

Check these in order

1. Share toggle. Open the agent’s side menu → Snapshot and confirm the share is Active. Turning it off cuts access immediately.
2. Your (owner’s) credits. A shared agent runs on the owner’s credits. If your balance hits zero, the external user is blocked too.
3. Session / daily cap reached. If the per-session credit cap is hit, that session is permanently blocked. If the daily link cap is hit, new sessions are blocked for the rest of the UTC day and automatically permitted again after midnight UTC. Raising the cap unblocks access immediately.
4. Link manually disabled. If you turned off the share toggle for that link, access is blocked. Creating a new snapshot does not automatically disable previous links — only manual deactivation or credit exhaustion does.

The full sharing model is explained in Sharing Agents (Snapshots).

9. Computer use / browser tools look stuck

If you see this

• The preview hasn’t visibly changed for a while, or there’s progress but no result is coming.

Check these in order

1. Watch the activity labels. Captions like “taking screenshot”, “click”, “typing” updating every few seconds mean the agent is working. Slow pages and busy sites just take time.
2. Wait briefly. Heavy pages — sign-in dashboards, ad-heavy sites — can take 10–30 seconds to settle.
3. Ask the agent where it is. Send “what step are you on? if you’re stuck, move on” — the agent will report current state or switch approach.
4. Retry or simplify. If it keeps getting stuck on the same page, ask it to “find that info another way” or break the task into smaller steps and try again.

Note: If the agent returns empty tool responses several times in a row, it is automatically stopped as a safety measure. Give it more specific instructions and try again.

Advanced

The content below isn’t needed by most users. Read it only when an issue keeps repeating or you want to dig into root cause.

Reading the last error category in the activity log

The agent’s Logs side panel records the result status of each run (completed / failed / skipped) along with the last error message. When you see the same failure repeating, here’s how to map it to action.

When the same failure keeps repeating

If the same error fires three or more times, this sequence works well.

1. Pause the agent. Scheduled and autonomous runs stop together.
2. Message the agent: “summarize what you’ve tried and where you got stuck, and save it in memory.” That tidies its working memory.
3. Reactivate the agent and retry the task in smaller chunks.
4. If it still blocks at the same spot, look in Adding Tools for an alternate tool combo that gets you past the obstacle.