← Index14 entries · By Vocation
Section II · For the Tech Lead

Prompts for the Tech Lead

AI prompts for tech leads: code review, architecture decisions, mentoring, sprint planning, and engineering write-ups.

§ Overview

A tech lead's day is half code and half communication, and AI helps with both halves. You're reviewing pull requests, making architecture calls, unblocking engineers, and then turning all of it into docs and write-ups that the rest of the org can actually read. ChatGPT and Claude let you move through the mechanical parts faster so you can spend more time on the decisions only you can make.

The prompts here lean into that dual role. On the technical side you get senior-style code review with file-referenced feedback, REST API schema design with idempotency notes, performance audits with ranked optimizations, OWASP-aligned security reviews, and production-ready Dockerfiles explained line by line. On the communication side there's technical documentation generation and a PRD prompt for when you're shaping work, not just shipping it.

Prompting well matters because a vague request gets you a generic review, while a sharp one gets you the specific tradeoff analysis you'd expect from a strong senior engineer. The quality of the answer tracks the quality of the context you provide.

§ Field Notes

What makes a good prompt for a tech lead

Strong tech-lead prompts carry the constraints that make a decision real: the language and framework, the performance budget, the team's conventions, what's already been tried. A code-review prompt that includes "we care most about readability for junior maintainers" produces different, better feedback than one that just says "review this." The same goes for API design, where mentioning idempotency requirements and existing endpoint patterns keeps the model consistent with your system.

It also pays to ask for ranked output with explicit tradeoffs rather than a flat list. For performance and security work especially, you want severity or impact ordering so you can triage, not a wall of equally-weighted suggestions you have to sort yourself.

§ Pro Tips

Get sharper results

  • 01When requesting a code review, tell the model your priorities (correctness, security, readability) and paste the surrounding conventions, so feedback aligns with your team instead of generic best practices.
  • 02For architecture and API prompts, state the constraints up front (existing patterns, idempotency needs, expected scale) so the design fits your system rather than a textbook one.
  • 03Ask performance and security audits to return findings ranked by impact or severity with concrete remediations, which lets you triage and delegate instead of re-sorting a flat list.
  • 04Use the documentation and PRD prompts to draft from your rough notes, then have a second engineer review; AI is excellent at structure but you own the technical accuracy.
§ FAQ

Common questions

Can I trust an AI code review to catch real issues?

Treat it as a thorough first pass, not a replacement for human judgment. It reliably flags readability problems, missing error handling, and common security pitfalls, and the file-referenced format makes findings easy to act on. But verify anything it claims about behavior, and pair it with your own review on anything high-risk.

How much context should I paste in for architecture decisions?

More than feels necessary. Include the existing patterns, the scale you're designing for, the constraints you can't change, and what you've already ruled out. Without that, the model defaults to generic textbook designs; with it, you get recommendations that actually fit your system and surface the tradeoffs you'd want a senior engineer to raise.

Is it appropriate to use AI for security reviews?

As a supplement, yes. The OWASP-aligned review prompt is good at surfacing common vulnerability classes with severity ratings and remediation snippets, which is a strong starting point. It is not a substitute for proper security testing or a specialist on anything sensitive, so use it to catch the obvious and broaden coverage, not as your only line of defense.

§ The Prompts · 14
№ 002coding

Perform a Thorough Code Review on a Pull Request

Get a senior-engineer-style code review with categorized, file-referenced feedback.

For
claude·chatgpt
№ 021coding

Refactor Code for Readability and Maintainability

Refactor any code for readability and maintainability without changing its behavior.

For
claude·chatgpt
№ 024coding

Design a RESTful API Endpoint Schema

Design a complete REST API schema with request/response bodies, status codes, and error cases.

For
claude·chatgpt
№ 027coding

Audit Code for Performance Bottlenecks

Identify performance bottlenecks in code and get ranked, impact-focused optimization suggestions.

For
claude·chatgpt
№ 028coding

Run a Security Review on Code

Get an OWASP-aligned security review with severity ratings and remediation snippets.

For
claude·chatgpt
№ 030coding

Write Clear Technical Documentation

Generate complete Markdown technical docs with params, examples, and error handling.

For
claude·chatgpt
№ 048business

Write a Product Requirements Document (PRD)

Generate a complete PRD with goals, requirements, user stories, and open questions.

For
chatgpt·claude
№ 096coding

Generate a Production-Ready Dockerfile and Explain Each Line

Generate a hardened, multi-stage Dockerfile with line-by-line comments and matching .dockerignore.

For
claude·chatgpt
№ 098coding

Design a Clean REST API for a New Resource

Get a complete REST endpoint design with shapes, errors, and idempotency notes.

For
claude·chatgpt
№ 100coding

Optimize a Slow Function With Specific Tradeoffs

Get a ranked list of optimizations with complexity analysis and explicit tradeoffs.

For
claude·chatgpt
№ 176coding

Refactor a long, tangled function into smaller, testable units

Breaks an overgrown function into smaller, single-responsibility units while preserving behavior and the public signature.

For
chatgpt·claude
№ 179coding

Write clear API reference docs straight from source code

Generates accurate API reference documentation from source code without inventing behavior, flagging ambiguities.

For
chatgpt·claude
№ 181coding

Turn a diff into a clear, reviewer-friendly PR description

Converts a diff and context into a structured, reviewer-friendly pull request description and title.

For
chatgpt·claude
№ 185coding

Brainstorm edge-case test scenarios before you write tests

Enumerates grouped edge-case and adversarial test scenarios for a feature so nothing gets shipped untested.

For
chatgpt·claude