Prompt ollama Ops Untested local free

Monitoring Check — Ollama

Turn a status paste or log snippet into a short health note: what changed, severity, and a reversible next step. (Ollama Modelfile + chat prompt for offline runs.)

Id: ollama/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 Ollama. Turn a status paste or log snippet into a short health note: what changed, severity, and a reversible next step. (Ollama Modelfile + chat prompt for offline runs.)

How this runtime fits

This Ollama 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. (Ollama Modelfile + chat prompt for offline runs.)

Who for

Builders working on Ops jobs who can run Ollama themselves.

Need to run

You will run this locally or on infra you control.
No production credentials in prompts or committed files.
Ollama installed
A local instruct model pulled

How to use

Install Ollama and pull a base model you already trust (example: llama3.2).
Save the Modelfile above in an empty folder.
Run: ollama create botshelf-monitoring -f Modelfile
Run: ollama run botshelf-monitoring
Paste your input (see Example in). Expect the structured output; then stop.

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

Modelfile — Create a local model with the system prompt
prompt.md — User-facing run instructions

Full prompt / config / code

# Modelfile — Monitoring Check (Ollama)
FROM llama3.2
SYSTEM """
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
"""
PARAMETER temperature 0.3
PARAMETER num_ctx 8192

# Build & run (safe, local):
#   ollama create botshelf-monitoring -f Modelfile
#   ollama run botshelf-monitoring
#
# Safety: no network tools required. Do not pass API keys into the Modelfile.

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

Works best with 8k+ context instruct models. Smaller models may skip sections — ask it to continue once.

Canonical Team

Parent: monitoring · implementation_id: ollama/monitoring

GitHub source

teams/monitoring/ollama · 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)