Cover photo

JavaScript is the duct tape of the Internet.

Charlie Campbell
Muhammad Azlaan Zubair

Md. Azlaan Zubair

@mdazlaanzubair

Born in
Karachi, Pakistan
The Model Is Not the Architecture
Article

The Model Is Not the Architecture

The most visible AI product is a chat box. The most instructive AI systems often have no chat box at all. Look across Google DeepMind's work on algorithms, quantum error correction, robotics, and hist

6 min read
#AI#Software Engineering#Machine Learning#AI Systems#Reinforcement Learning
An Agent API Migration Is an Ownership Audit
Article

An Agent API Migration Is an Ownership Audit

An API migration can compile, return the expected text, and still be wrong. That is the real risk in moving from OpenAI's Assistants API to Responses. The old objects do not map to new objects without

6 min read
#AI#Software Engineering#agentic AI#OpenAI API#responses api
A Tool Result Is Evidence, Not Ground Truth
Article

A Tool Result Is Evidence, Not Ground Truth

Connecting an agent to a database does not remove hallucination risk. It gives the system a second source that can be stale, malformed, unauthorized, or simply wrong—and a protocol that may make the m

7 min read
#AI#Software Engineering#agentic AI#llm evaluation#Tool Use
Code Generation Is Fast. Verification Is Not.
Article

Code Generation Is Fast. Verification Is Not.

Agentic IDEs can produce a runnable full-stack application in minutes. That does not mean the application became cheap to trust. In a controlled study of 48 generated projects, the researchers spent a

6 min read
#AI#Software Engineering#coding agents#agentic-ides#Software Testing
Are These Really Accidental Leaks?
Article

Are These Really Accidental Leaks?

A GitHub repository collecting supposedly “leaked” system prompts from ChatGPT, Claude, Gemini, Grok, and other AI products has crossed 63K+ stars and 10K+ forks. Most of the discussion naturally focu

8 min read
#AI Engineering#Prompt Engineering#ai agents#context engineering#software architecture
Benchmark the Model–Harness Pair, Not the Model
Article

Benchmark the Model–Harness Pair, Not the Model

“Which model is best for coding?” sounds like a precise engineering question. Usually, it is missing half of the system. A coding agent is a model inside a harness that chooses tools, assembles contex

6 min read
#AI#Software Engineering#coding agents#llm evaluation#benchmarks
Your Agent Passed the Eval. Its Retrieval Calls Still Tripled.
Article

Your Agent Passed the Eval. Its Retrieval Calls Still Tripled.

An AI agent can pass the task and still fail the engineering evaluation. That happens when a context-compression policy preserves the final outcome but changes how the agent gets there. The agent stil

6 min read
#ai agents#ai-evaluation#context engineering#llm#Software Engineering
Your AI Agent Eval Is a Production Security Boundary
Article

Your AI Agent Eval Is a Production Security Boundary

An AI agent can produce the correct benchmark answer and still fail the evaluation. That is what happens when the path to the answer crosses an unauthorized boundary. In July 2026, an autonomous agent

9 min read
#ai agents#ai-evaluation#cybersecurity#Software Engineering#llm
The Competence Debt of Agentic Coding
Article

The Competence Debt of Agentic Coding

A coding agent can now inspect a repository, implement a feature, modify multiple files, run tests, fix failures, and prepare code for review. That is a remarkable change in software development. It a

22 min read
#AI coding#Software Engineering#coding agents#System Design#Productivity