Your AI Coding Agent Should Not Trust Your Logs
Agentjacking is a timely reminder that AI coding agents must treat logs, monitoring data, tickets, and MCP tool output as untrusted input, not authority.
K
Kyluke McDougall 
The Approval Prompt Is Not the Boundary
SymJack is a useful warning for teams adopting AI coding agents: permission prompts only matter when path boundaries, repository trust, and agent configuration are designed properly.
K
Kyluke McDougall 
The Prototype Is Not the Product
AI builders such as Replit Agent, Lovable, Devin, Cursor, and Claude Code can create convincing software quickly. The hard decision is when a prototype is ready to become a serious product.
K
Kyluke McDougall 
The Rule of Two for AI Agents in CI/CD
AI agents in GitHub Actions and delivery pipelines need clear boundaries. Teams should avoid combining untrusted input, secrets, and external communication in one workflow.
K
Kyluke McDougall 
AI Coding FinOps: When Agents Become a Delivery Cost
AI coding agents can speed up delivery, but only if teams can see what they cost, where they help, and where they quietly create rework.
K
Kyluke McDougall 
Your Legacy Codebase Is Not AI-Ready Just Because You Bought an AI Coding Tool
AI coding agents can help serious teams move faster, but only when the existing system is legible enough for them to work safely. For many products, the first AI productivity project is making the codebase understandable.
K
Kyluke McDougall 
AI Coding Sandboxes Are Not Enough. Design the Blast Radius.
Sandboxes, permissions, and allowlists matter. But serious teams also need to decide how far an AI coding agent mistake can spread.
K
Kyluke McDougall 
AI Coding Agents Did Not Remove the Bottleneck. They Moved It.
Coding agents can create more implementation throughput. The serious question for product teams is whether planning, review, integration, and architecture can keep up.
K
Kyluke McDougall 
AI Coding Agents Need Guardrails Before They Get Near Production
Claude Code, Cursor, MCP tools, and similar agents are becoming more powerful. For serious product teams, the key question is no longer speed. It is control.
K
Kyluke McDougall