Skip to main content

Stage 9: Operations

Overview

Operations covers the ongoing lifecycle after delivery, including incident response, documentation maintenance, prompt refinement, and system monitoring. This stage provides tooling for keeping production systems healthy and documentation current.

When You Enter This Stage

You enter Operations after completing the final sprint delivery in Stage 8: Delivery.

NOTE

Prerequisites: Production deployment complete. Monitoring and alerting configured.

Available Tools

Primary Agents

ToolTypeHow to InvokePurpose
doc-opsAgentSelect doc-ops agentUpdate and maintain documentation
prompt-builderAgentSelect prompt-builder agentRefine and optimize operational prompts

Prompts

ToolTypeHow to InvokePurpose
doc-ops-updatePrompt/doc-ops-updateUpdate documentation for the latest release
incident-responsePrompt/incident-responseDocument and triage incidents
prompt-analyzePrompt/prompt-analyzeEvaluate prompt effectiveness
prompt-refactorPrompt/prompt-refactorRefactor and improve existing prompts
checkpointPrompt/checkpointSave operational state for continuity

Auto-Activated Instructions

InstructionActivates OnPurpose
writing-style**/*.mdEnforces voice and tone conventions
markdown**/*.mdEnforces Markdown formatting rules
prompt-builderAI artifactsEnforces authoring standards

Templates

TemplatePurpose
incident-responseStructured template for incident documentation

Role-Specific Guidance

SREs lead Operations, handling incident response and system monitoring. Tech Leads contribute to architecture-level maintenance decisions. Engineers address hotfixes and ongoing code maintenance.

Starter Prompts

Incident Response

/incident-response Users are reporting 504 Gateway Timeout errors on the
/api/v2/orders endpoint in East US 2. Errors started at 14:32 UTC after
the App Service scaled down during a scheduled maintenance window.
Severity 2. Phase is triage.

Documentation Maintenance

Use the /doc-ops-update prompt to target a specific scope and focus area:

/doc-ops-update scope=docs focus=accuracy

For ad-hoc documentation work outside the predefined scopes, select the agent directly.

Select doc-ops agent:

Scan docs/getting-started/ for accuracy against current scripts/ and
.github/ artifacts. Several install scripts changed in the v3.2 release
and the setup guides may reference outdated flags or file paths.

Prompt Refinement

/prompt-analyze .github/prompts/rpi/task-research.prompt.md

After analysis, apply the suggested improvements:

/prompt-refactor .github/prompts/rpi/task-research.prompt.md Remove
duplicate input declarations and consolidate the research scope section
into a single structured list.

To create a new prompt from an existing implementation file, select prompt-builder agent:

Create a prompt from src/api/handlers/search.py that generates search
handler implementations following the same query parsing, pagination,
and response envelope patterns.

Operational Continuity

Save conversation state before ending a session:

/checkpoint mode=save description=incident-response-playbook-updates

Resume a previous session:

/checkpoint mode=continue description=incident-response

Stage Outputs and Next Stage

Operations produces updated documentation, incident reports, refined prompts, and maintenance artifacts. When a hotfix is needed, transition back to Stage 6: Implementation to address the issue through the standard implementation workflow.

🤖 Crafted with precision by ✨Copilot following brilliant human instruction, then carefully refined by our team of discerning human reviewers.