SaaS Is Dead. Long Live SaaaS (Subagent as a Service)
The real shift isn't adding AI to software. It's software becoming AI. Nivedit Jain calls this SaaaS: Subagent as a Service.
#AI Agents 1 min read
Articles
A chronological collection of insights on technical specification, product strategy, and AI-driven documentation.
AI Agents (9 articles)
Clear filters Agents That Run While You Sleep: The Verification Layer Autonomous Coding Needed
Without a verification layer, overnight coding creates morning cleanup. With a verification layer, it can create morning momentum.
#AI Agents
#Software Engineering 1 min read
Clinejection: How One GitHub Issue Title Turned into a Supply Chain Incident
On February 17, 2026, Cline 2.3.0 was compromised via an AI-driven CI/CD attack chain that began with prompt injection in a GitHub issue title and ended with a malicious npm release that silently installed an unauthorized AI-capable tool.
#Security
#AI Agents 5 min read
Parallel Coding Agents with tmux and Markdown Specs: A Real-World Operating System
A practical operating model for running multiple coding agents in parallel using tmux and Markdown Feature Designs as the coordination backbone.
#AI Coding
#AI Agents 1 min read
Codex App: OpenAI’s Command Center for AI Agents on macOS
OpenAI’s Codex app brings project-based agent management, a skills framework, background automations, and sandboxed security to macOS as part of ChatGPT paid plans.
#AI Agents
#Developer Tools 1 min read
Claude Cowork: Anthropic's AI Agent That Brings Claude Code Power to Everyone
Claude Cowork is Anthropic’s new AI agent built into Claude Desktop that brings Claude Code’s agentic power to everyday office workflows, with folder-based access control, natural language instructions, and autonomous task execution.
#AI Agents 1 min read
The Ralph Wiggum Technique: A Brief History of Autonomous AI Coding
An overview of the Ralph Wiggum Technique, a 2025-era approach to running autonomous AI coding agents in continuous loops, its timeline, core insights, and philosophical implications.
#AI Agents
#AI Coding 1 min read
2025: The Year in LLMs - A Comprehensive Review
2025 reshaped the AI landscape: reasoning-first LLMs, mainstream coding agents, Chinese labs leading open-weight benchmarks, a command-line renaissance, and a shift from raw capability to deployment safety at scale.
#AI Models
#AI Agents
#AI Coding 1 min read
Dynamic MCPs: Stop Hardcoding Your AI Agent's World
Dynamic MCPs let AI agents discover, configure, and compose tools at runtime instead of relying on a fixed, hardcoded toolset. With the Docker MCP Gateway, agents can search, add, configure, remove, and execute tools on demand—securely, via Docker.
#Developer Tools
#AI Agents 1 min read
