Designing with AI

Inside Claude Code

Issue #63 | What 500,000 lines of production agent code teach us about building and optimizing agents

Published on Designing with AI • Apr 6

Inside Claude Code

Issue #63 | What 500,000 lines of production agent code teach us about building and optimizing agents

Apr 6 • Victor Dibia, PhD

15

6

Building Your Own Claude Code from Scratch

Issue #61 |Three Extensions That Turn your For Loop into an Agent like Claude Code

Apr 1 • Victor Dibia, PhD

9

1

March 2026

Agentic Noise: How AI Agents Can Break the Delicate Balance of Human Attention

Issue #60 | When AI Agents Flood One Side of a Platform, Everyone Loses

Mar 30 • Victor Dibia, PhD

8

5

How to Implement Context Engineering Strategies for your Agent (Claude Code)

#59 | Managing context growth, preventing early stopping, and measuring what works

Mar 11 • Victor Dibia, PhD

12

1

February 2026

Implementing Claude Code Skills from Scratch

#58 | The pattern behind Claude Code's extensibility - and a working implementation in 100 lines of Python.

Feb 25 • Victor Dibia, PhD

32

8

Use Coding Agents (Claude Code) to Build Your Product. Don't Make Them Your Product.

#57 | On where general-purpose coding agents like Claude Code shine, where they break, and how to integrate them into your workflow.

Feb 18 • Victor Dibia, PhD

18

5

January 2026

Is Scaling a Dead End? Why Model Scaling is Necessary Infrastructure

#56 | The bitter lesson isn’t dying. It’s being amortized.

Jan 19 • Victor Dibia, PhD

8

4

The Arc of Agent Action from Code to Tools and Back to Code - And Why Anthropic's SKILLS.md is Not New

Issue #55 | Early agents (LIDA, AutoGen) supported actions via code. Then the industry moved to action via tools/structured output. And now we are back…

Jan 5 • Victor Dibia, PhD

13

4

December 2025

Vibe Coding .. With Engineering Discipline: Building Real Apps with AI Agents

#54 | Five practices to make your AI-assisted coding more production-ready

Dec 19, 2025 • Victor Dibia, PhD

11

4

Agent Middleware: Adding Control and Observability to AI Agents

Issue #53 | How to intercept agent operations for logging, safety, rate limiting, and compliance - the middleware pattern for production AI agents.

Dec 16, 2025 • Victor Dibia, PhD

11

1

The Agent Execution Loop: How to Build an AI Agent From Scratch

Issue #52 | How AI agents work under the hood - the execution loop that enables reasoning, tool calling, and iterative problem solving.

Dec 11, 2025 • Victor Dibia, PhD

20

4