Agentic Coding Roadmap

Practices you can use to improve your Agentic Coding workflow.

This page is under heavy development and will change. More detailed information will be added.

Level 1 Level 2 Level 3
Level 1 Code style linter

Agent generates code that looks like yours. Reviews stop being about formatting.

Read more →
Level 1 Basic prompting techniques

Better first-attempt output. Less back-and-forth. Include file paths, constraints, architecture context.

Level 1 Plan-then-execute workflow

Start with plan mode. Review the plan, stay in planning until the plan is solid, then approve implementation. Catches misunderstandings before they become code.

Level 1 Small, focused tasks

Agent succeeds more often when each prompt has one clear responsibility.

Level 1 Strong typing / type annotations

Agents understand data shapes and constraints through types. Fewer implicit rules to guess at. Free leverage in strongly typed languages like TypeScript or Go.

Level 1 Code review agent

Automated first pass catches style violations, missing tests, and common mistakes before you look at it. Invoked by coding agent for immediate feedback loop.

Level 2 Simplified project structure

Flat beats deep nesting. Agents get lost in complex directory hierarchies with many micro-packages, just like new team members do.

Level 2 Context management (CLAUDE.md / AGENTS.md)

Agent knows your codebase persistently — architecture, patterns, conventions. No more explaining from scratch. Keep it minimal: onboarding doc, not encyclopedia.

Level 2 Advanced linters (complexity)

Enforcing cognitive/cyclomatic complexity keeps generated code reviewable and maintainable.

Read more →
Level 2 Implementation plans / strategy docs

Write a markdown plan with goals, constraints, edge cases, and step breakdown before prompting. Acts as a contract between you and the agent — better plans produce better code.

Level 2 Specialized review agents

Security, performance, accessibility — different concerns need dedicated reviewers at scale.

Level 3 Integration / API testing

Agent gets a possibility to get instant feedback about written code. Reduces a chance of regression.

Level 3 E2E testing

Trust that a generated feature works as a whole, not just in parts.

Level 3 Architecture linters and scripts

Enforce boundaries programmatically — dependency rules, layer violations, import restrictions. The agent can't break what's mechanically enforced.

Level 3 Specification documents

Specs docs with acceptance criteria, edge cases, and constraints. Better specs produce better first-attempt code.

Level 3 Hooks and pre-commit automation

Automated safeguards at three levels: review during generation, pre-commit check on staged files, full branch check before PR. Creates a refactoring loop on any quality regression.

Level 3 Sub-agents orchestration

Delegate research and different components to different agents. Each agent is focused on one feature slice improving efficiency.

Is there a Level 4?

Yes, some people do magic with agents orchestration. But I will be focusing on the first 3 levels as they can make your team multiply their performance.