Staff Software Engineer – AI Enablement

Purpose
Seeking a consultant to help establish the foundation for an AI-first
software engineering organization using Claude Code. This is not a request for a traditional
training workshop. We are looking for a hands-on engagement that combines assessment,
engineering enablement, and coaching using our production codebase.
This document intentionally defines our business objectives and desired outcomes rather
than prescribing the engagement approach. Respondents should propose the project plan,
phases, timeline, staffing, deliverables, and pricing they believe will best achieve these
objectives.
We do not expect every capability described in this document to be fully implemented
during this engagement. Instead, we expect the consultant to establish the engineering
foundation, demonstrate selected capabilities, and provide a prioritized roadmap for future
implementation.

Current Environment
• Backend: .NET / C#
• Frontend: React / TypeScript
• Database: Microsoft SQL Server
• Cloud: Microsoft Azure
• Source Control, CI/CD and Project Management: Azure DevOps
• Financial services / regulated environment

Business Objectives
• Establish an AI-first engineering operating model.
• Maximize developer productivity with Claude Code.
• Standardize engineering workflows and best practices.
• Reduce repetitive engineering work through automation.
• Create reusable team assets (CLAUDE.md, prompts, agents, hooks, MCP configuration).
• Leave the team self-sufficient with a practical 90-day roadmap.
Primary Areas of Focus
1. Claude Code Engineering Workflow
• Recommended end-to-end developer workflow.

Planning vs. implementation.

• Session and context management.
• Manual edits vs. AI-assisted edits.
• Model selection, Thinking/Effort settings, performance and cost optimization.

2. Repository & Documentation Strategy
• CLAUDE.md architecture (single vs. distributed).
• Business rules and architectural documentation.
• Documentation as AI context.
• Shared prompts and engineering standards.

3. Shared Engineering Assets
• Reusable agents.
• Hooks.
• MCP server recommendations and setup.
• Custom commands, skills and prompt library.

4. Azure DevOps Integration
• Work item analysis.
• Implementation planning.
• Pull request workflow.
• Acceptance criteria validation.
• Recommended automation opportunities.
5. Hands-on Coaching
• Pair programming using our production code.
• Best practices.
• Knowledge transfer.
• Team adoption strategy.

6. Security & Governance
• Secrets management.
• PII handling.
• Safe tool usage.
• Guidance for regulated environments.
Long-Term Vision (Not Expected to be Fully Implemented)
The following capabilities represent our long-term vision. We expect the consultant to
recommend priorities, demonstrate selected capabilities where appropriate, and provide a
roadmap rather than fully implementing every item.
• AI-powered feature development from Azure DevOps work items.
• Autonomous integration and regression testing.
• Production monitoring and AI-assisted root cause analysis.
• Automatic documentation and architecture maintenance.
• AI-assisted solution design and impact analysis.
• AI coaching and engineering standardization.

Expected Outcomes
• AI-first engineering workflow.
• Claude Code configured and adopted by all developers.
• Repository documentation strategy (CLAUDE.md).
• Shared prompts, agents, hooks and MCP configuration.
• Azure DevOps integration recommendations.
• Engineering playbook and best practices.
Proposal Requirements