Machine-learning Services Feature Implementation Agent Playbook
A disciplined build-a-feature workflow for machine-learning services: plan first, tests first, small diffs. Built for platform teams working in machine-learning services, tuned for ChatGPT. Fill in the placeholders, paste, and get a structured, ready-to-use result — with clear rules so the output stays specific to your situation instead of generic.
Preview
You are a staff engineer who has maintained large machine-learning services in production for years.
Inputs you will receive:
Feature: {{FEATURE}}
Stack: {{STACK}}
Codebase context: {{CODEBASE_CONTEXT}}
Constraints: {{CONSTRAINTS}}
… [purchase to unlock the full framework]Screenshots
Example outputs
Files: src/hooks/useCart.ts (new), CartBadge.tsx (edit). Edge cases: empty cart persistence, concurrent tab updates…
Version history
- v1Initial releaseJul 10, 2026
Buyers get every future update free.
Buyers also bought
Paste a slow query and schema — get back an optimized version, index recommendations, and a plain-English explanation of why it was slow.
Safely refactor gnarly legacy code: characterization tests first, seams identification, strangler-fig migration plan. Based on real enterprise migration experience.
A disciplined build-a-feature workflow for REST APIs: plan first, tests first, small diffs. Built for agency dev shops working in REST APIs, tuned for Cursor. Fill in the placeholders, paste, and get a structured, ready-to-use result — with clear rules so the output stays specific to your situation instead of generic.
A safe refactor plan for machine-learning services: characterization tests, seams, and steps that keep CI green. Built for platform teams working in machine-learning services, tuned for Windsurf. Fill in the placeholders, paste, and get a structured, ready-to-use result — with clear rules so the output stays specific to your situation instead of generic.
More from Anya Kahale
A structured way to make and document architecture calls for DevOps tooling. Built for solo developers working in DevOps tooling, tuned for ChatGPT. Fill in the placeholders, paste, and get a structured, ready-to-use result — with clear rules so the output stays specific to your situation instead of generic.
A systematic debugging workflow for internal dashboards that finds root causes instead of symptoms. Built for startup engineering teams working in internal dashboards, tuned for Replit AI. Fill in the placeholders, paste, and get a structured, ready-to-use result — with clear rules so the output stays specific to your situation instead of generic.
A thorough review pass tuned for GraphQL services — correctness first, style last. Built for agency dev shops working in GraphQL services, tuned for Replit AI. Fill in the placeholders, paste, and get a structured, ready-to-use result — with clear rules so the output stays specific to your situation instead of generic.
Meaningful test coverage for e-commerce stacks — behavior tests, edge cases and fixtures that stay maintainable. Built for solo developers working in e-commerce stacks, tuned for ChatGPT. Fill in the placeholders, paste, and get a structured, ready-to-use result — with clear rules so the output stays specific to your situation instead of generic.
Reviews
No reviews yet.