Technical Lead & System Architect

What it does

Technical Lead & System Architect is a Cursor agent playbook named tech-lead. AgenticKit installs it so a session can adopt this role instead of acting as a generic coding assistant.

The tech-lead agent acts as your repository's senior engineering manager and principal architect. When invoked in Cursor, it evaluates feature requirements against your CURSOR.md guidelines, establishes modular boundaries, enforces strict TypeScript standards, and breaks complex requirements down into safe, verifiable pull requests.

Oversees architecture, enforces code conventions, and coordinates agent workflows. Senior technical architect for Cursor that validates full-stack system architecture, designs API contracts, and guides autonomous AI coding workflows.

Why it exists

A pile of agent files is not a team. tech-lead exists so one job, technical lead & system architect, has a written brief, required skills, and a stop condition.

It ships in the Engineering Kit. Skills it must read: Project Conventions & CURSOR.md Standards; SaaS Architecture Patterns & Multi-Tenancy; Strict TypeScript Standards & Type Safety; Resilient Error Handling & Fault Tolerance. Commands that adopt this role: /ship: End-to-End Feature Pipeline Shipper; /audit: Codebase Quality & Security Auditor; /feature-spec: PRD & Product Feature Requirement Spec; /release: Release Notes & Changelog Generator.

When to use it

• Starting large multi-file features or microservices
• Refactoring legacy spaghetti code into clean domain boundaries
• Establishing strict project conventions in CURSOR.md

When not to use it

• Do not let tech-lead write production code. Planning and implementation in one role is how the first workflow failed.
• Do not keep the same chat after this agent has finished its artifact. Start a reviewer in a new thread.
• Do not invoke every agent in the kit for a small change.

Example workflow

1. Install the Engineering Kit so .cursor/agents/tech-lead is on disk.
2. Run /ship: End-to-End Feature Pipeline Shipper, or start a chat and tell Cursor to adopt the tech-lead role.
3. The agent should read: Project Conventions & CURSOR.md Standards; SaaS Architecture Patterns & Multi-Tenancy; Strict TypeScript Standards & Type Safety; Resilient Error Handling & Fault Tolerance.
4. It produces the artifact for this role only, then stops.
5. A different agent or you review. Same-chat self-review is not a review.

Example usage

Example: "You are tech-lead. Starting large multi-file features or microservices. Read project-conventions before you edit."

Or let the pipeline invoke it: /ship: End-to-End Feature Pipeline Shipper.

Capabilities you should actually see: Full-stack architecture reviews and modular system design

Example output

• tech-lead should leave files or a written verdict, not a vibe check. Full-stack architecture reviews and modular system design Repository-wide code conventions and lint rule enforcement
• Engineering agents should touch the slice they were given (schema, route, test, or review note) and nothing else.

Best practices

• Full-stack architecture reviews and modular system design
• Repository-wide code conventions and lint rule enforcement
• Multi-agent task decomposition and execution choreography
• API contract definition (OpenAPI / Type specifications)
• Technical debt identification and refactoring roadmaps
• One role per chat unless a command is explicitly orchestrating a sequence.

Common mistakes

• Using tech-lead as a synonym for 'the Cursor agent'. It is a brief, not the product.
• Skipping the required skills and hoping the role name is enough.
• Letting the writer approve its own PR.
• Invoking this agent and three unrelated ones in the same prompt.