Skip to content

demos(it-operations): add L1/L2/L3 tiered support demo#132

Open
devin-ai-integration[bot] wants to merge 3 commits into
mainfrom
devin/1781023715-it-operations-tiered-support-demo
Open

demos(it-operations): add L1/L2/L3 tiered support demo#132
devin-ai-integration[bot] wants to merge 3 commits into
mainfrom
devin/1781023715-it-operations-tiered-support-demo

Conversation

@devin-ai-integration

@devin-ai-integration devin-ai-integration Bot commented Jun 9, 2026

Copy link
Copy Markdown
Contributor

Summary\n\nAdds demos/it-operations/tiered-support-demo.md — a new facilitator-led demo showing Devin across all three tiers of IT Operations support, using OtterWorks as the live platform:\n\n| Tier | Devin's Role |\n|------|--------------|\n| L1 | Generates and maintains runbooks from actual service code (fills <!-- TODO --> skeletons in docs/runbooks/) |\n| L2 | One-click "Launch Devin" from an incident card → immediate root-cause investigation with zero operator context |\n| L3 | Alert fires → auto-incident → auto-Devin session → fix PR. Zero human intervention |\n\nAlso covers scaling: Devin Automations (no-code webhook triggers), parent-child orchestration for multi-service incidents, and scheduled sessions for runbook freshness.\n\nAll prompts reference real file paths in Cognition-Partner-Workshops/otterworks (docs/runbooks/, services/admin-service/app/services/devin_session_service.rb, observability/grafana/provisioning/alerting/alert-rules.yml)."

Link to Devin session: https://partner-workshops.devinenterprise.com/sessions/8bcb7517f6bf45e2bae805ae2346b03f
Requested by: @bsmitches


Open in Devin Review

Introduces a new demo showcasing Devin across all three tiers of
IT Operations support:
- L1: Runbook generation and maintenance from codebase analysis
- L2: One-click incident investigation (Launch Devin from incident card)
- L3: Fully automated detection-to-remediation (zero human intervention)

Uses the OtterWorks platform (chaos engineering, Grafana alerting,
admin-service Devin API integration) as the concrete example.

Includes scaling patterns: Devin Automations for no-code setup,
parent-child orchestration for multi-service incidents, and scheduled
sessions for runbook freshness.
@devin-ai-integration

Copy link
Copy Markdown
Contributor Author

🤖 Devin AI Engineer

I'll be helping with this pull request! Here's what you should know:

✅ I will automatically:

  • Address comments on this PR. Add '(aside)' to your comment to have me ignore it.
  • Look at CI failures and help fix them

Note: I can only respond to comments from users who have write access to this repository.

⚙️ Control Options:

  • Disable automatic comment, CI, and merge conflict monitoring

@devin-ai-integration devin-ai-integration Bot left a comment

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Devin Review found 2 potential issues.

View 2 additional findings in Devin Review.

Open in Devin Review

Comment thread demos/it-operations/tiered-support-demo.md Outdated
Comment on lines +67 to +92
```
Read the incomplete runbooks in docs/runbooks/ on the
Cognition-Partner-Workshops/otterworks repo. For each
runbook that has TODO placeholders:

1. Read the corresponding service source code to understand
the failure mode described in the Symptoms section.
2. Fill in Investigation Steps with specific commands:
kubectl log queries, Redis key checks, Prometheus
metric queries, and Grafana dashboard references.
3. Fill in Resolution Steps with the actual fix: which
file to change, what configuration to update, or what
service to restart.
4. Fill in Post-Incident with realistic action items:
monitoring gaps to close, code hardening, and process
improvements.

Ground every step in the actual codebase — no generic
boilerplate. Reference specific files, functions, Redis
keys, and Prometheus metrics from the service code.

Start with docs/runbooks/search-suggest-500.md (read
services/search-service/app/api/search.py for context)
and docs/runbooks/notification-processing-failure.md
(read services/notification-service/ for context).
```

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

🚩 File paths in prompts reference external repo (otterworks) — cannot verify from this repo

The prompts reference paths like docs/runbooks/search-suggest-500.md, services/search-service/app/api/search.py, services/notification-service/, and observability/grafana/provisioning/alerting/alert-rules.yml on the Cognition-Partner-Workshops/otterworks repo. The REVIEW.md rule says "Every file path referenced in a prompt should exist on the referenced repo's main branch." These paths cannot be verified from within this repository. If the otterworks repo structure has changed, these paths may be stale.

Open in Devin Review

Was this helpful? React with 👍 or 👎 to provide feedback.

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Verified — all referenced paths exist on the otterworks repo's main branch. Checked locally against the clone:\n- docs/runbooks/search-suggest-500.md ✓\n- services/search-service/app/api/search.py ✓\n- services/notification-service/ ✓\n- services/admin-service/app/services/devin_session_service.rb ✓\n- observability/grafana/provisioning/alerting/alert-rules.yml

devin-ai-integration[bot]

This comment was marked as resolved.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant