Perspectives
Stop Prompting. Design the Loop.
The unit of work moved from the prompt to the loop. The five pieces of loop engineering, the memory that makes it compound, and what it won't do for you.
Engin Diri
9 min readEngin Diri
9 min read
Perspectives
Stop Tuning Prompts. Build a Harness.
In a large codebase, the model is the smaller variable. The harness around it does the work: CLAUDE.md, hooks, skills, LSP, MCP, subagents.
Engin Diri
11 min read
Perspectives
How Building AI Agents Has Changed in 2026
A year ago, building an AI agent meant frameworks, RAG, and glue code. The Claude Agent SDK, Codex SDK, and skills replaced most of that middle layer.
Engin Diri
8 min read
Perspectives
Agent Sprawl Is Here. Your IaC Platform Is the Answer.
Developers are shipping AI agents to production. Your Pulumi platform already supplies the seven things those agents need to be governed.
Engin Diri
11 min read
Perspectives
Superpowers, GSD, and GSTACK: Picking the Right Framework for Your Coding Agent
Three frameworks for AI coding agents compared: Superpowers enforces TDD, GSD prevents context rot, and GSTACK adds role-based governance.
Engin Diri
10 min read
Perspectives
Token Efficiency vs Cognitive Efficiency: Choosing IaC for AI Agents
We benchmarked Terraform HCL and Pulumi TypeScript across two LLMs. HCL uses fewer tokens, but Pulumi's total pipeline cost is 41% lower.
Engin Diri
10 min read
