Monitoring Check — Open WebUI

Turn a status paste or log snippet into a short health note: what changed, severity, and a reversible next step. (Open WebUI system prompt / custom agent notes.)

Id: open-webui/monitoring · Slug: monitoring · Status: Untested · Untested on this machine — recipe reviewed for safety (no secrets, no destructive commands, no auto-spend). Mark tested after you run it locally.

What is this

Prompt for Open WebUI. Turn a status paste or log snippet into a short health note: what changed, severity, and a reversible next step. (Open WebUI system prompt / custom agent notes.)

How this runtime fits

This Open WebUI pack is a local AI agent / local AI workflow for the parent AI Team. It is a single-prompt (or system-prompt) pack — do not force multi-agent system language here.

Parent AI Team: monitoring · What is an AI Team?

What it does

Turn a status paste or log snippet into a short health note: what changed, severity, and a reversible next step. (Open WebUI system prompt / custom agent notes.)

Who for

Builders working on Ops jobs who can run Open WebUI themselves.

Need to run

You will run this locally or on infra you control.
No production credentials in prompts or committed files.
Open WebUI reachable
Backend model configured

How to use

In Open WebUI, create a custom model/agent.
Paste the system prompt.
Optional: attach a knowledge collection with non-secret docs only.
Chat using Example in; verify structured sections appear.

Limitations

Not a substitute for professional legal, medical, or investment advice.
Outputs can be wrong; human review required before publish or spend.
Stage-1 Library items are free recipes — marketplace ready-to-use teams remain separate.
Local models may omit sections; re-prompt once if needed.

Test status

Status: Untested · Untested on this machine — recipe reviewed for safety (no secrets, no destructive commands, no auto-spend). Mark tested after you run it locally.

Files

system-prompt.txt — Custom GPT / Model system prompt
knowledge-notes.md — Optional collection intro (no secrets)

Full prompt / config / code

# Open WebUI — Monitoring Check
## System prompt
You are an ops monitoring note-taker. Goal: short health note from a status paste.

RULES:
- Severity: info|warn|critical based only on provided signals.
- Prefer reversible next steps. No destructive commands.
- No auto-remediation that spends money or deletes data.
- If signal is insufficient, say so.

OUTPUT:
1) Status one-liner
2) What changed
3) Severity + evidence
4) Reversible next step
5) Owner / wait condition

## knowledge-notes.md
- Collection name: botshelf-monitoring
- Add only documents you have rights to use.
- Do not upload API keys, .env, or customer PII.
- This job should remain read-only against knowledge files.

## Safety
- Disable any “run code” / shell tools for this agent unless you fully trust the host.
- No auto-spend connectors.

Example in

Status paste:
- netlify deploy: ok
- checkout function p95: 1800ms (was 400ms)
- error rate 2.1% (was 0.3%)
Window: last 30m

Example out

Status: checkout latency + errors elevated
Changed: p95 400→1800ms; errors 0.3→2.1%
Severity: warn (not confirmed outage)
Next: check last deploy diff; freeze new deploys if rising
Wait: 15m trend

Model / runtime notes

Backend may be Ollama or another OpenAI-compatible local server. Keep tools off for stage-1 safety.

Canonical Team

Parent: monitoring · implementation_id: open-webui/monitoring

GitHub source

teams/monitoring/open-webui · commit eb87e8e049fdf9908e438305ff827c7b617505b5 · license: free-use-at-own-risk

Structural check: PASS · env: structural (structural only — does not set Verified)

Related Library items

Related marketplace Team pages

Soft thematic links only — not identity merges. Marketplace Teams ≠ Library AI Team records.

Recurring Price Check (marketplace Team page — separate entity)
Evidence Gate Check (marketplace Team page — separate entity)