First, build with AI — start from yourself. Promote and advocate for AI internally.
Second, make your company AI Native. Find sustainable patterns where AI delivers predictably.
Third, optimize the processes for even greater outcomes. Do not optimize before that step. Make the AI motion grow first.
Recent Posts
Install, Launch, Update: Shipping a CLI on Five Platforms — the devrig Approach Personal Assistant without OpenClaw or Hermes: Just One Prompt A Real macOS Desktop for a Linux Agent: Driving Tart VMs over SSH with Agent Skills A Real IntelliJ IDEA Inside Docker: Integration Tests with X Server, Window Manager, and Live Video Inside the Git Hooks: Tagging Every AI Agent Commit (Part 3) Inside the Git Proxy: Capturing What an AI Agent Pushed (Part 2) What Did the Agent Just Push? Auditing Git for AI Agents devrig: MCP Steroid Goes Level 3 — Autonomous IDE Setup for AI Agents From HTTP MCP to stdio: Lessons Connecting an AI Agent to a Desktop IDE 130 Release-Roadmap Issues, 818 Agent Runs: A Mid-Iteration Reality Check IntelliJ Plugin Hot-Reload: HTTP 413 Building an IntelliJ Plugin That Works Across Multiple IDE Versions: 7 Approaches Booting NVIDIA Jetson AGX Thor: Headless, from macOS, via Serial Console IntelliJ as a Skill Factory MCP Steroid Is Now Open Source Agentic Experience and Tools: My Program run-agent.sh v2.0: Hardened Runner with 115 Tests, Random Selection, and Agent Environment Contract From Voice Memos to Searchable Text with Local Whisper on macOS MCP Steroid Project Assessment: 75 Days, 1300+ Commits, One Plugin Testing Your MCP Server with Real AI Agents in Docker CLI Is the New API and MCP: Building Agent-Ready Tools for Enterprise Teams JVM ClassLoaders & IntelliJ: When it fails in production The Cost Return of Local AI: When Does Your Hardware Pay for Itself? run-agent.sh: Orchestrating Dozens of AI Agents from Your Terminal Git Fork Pattern: Full Checkouts Without the Bloat View all posts →