Platform engineering, Go, DevOps, and applied AI.
I benchmarked the Jev model against an LLM agent on real browser navigation: 13x faster per task, and one setup mistake that broke every single test.
jev is an open-source CLI for TypeSafe AI's Jev model: ask any text a typed question, get a calibrated probability back, and branch on the exit code.
Wire a Slack CLI into Claude Code, Cursor, and Codex in 10 minutes — read channels, post messages, summarise threads. xoxc browser tokens for personal automation, OAuth apps for production.
Claude Code in Docker Compose with network isolation — full docker-compose.yml, persistent Pro/Max auth, Squid egress allowlist, and per-project profiles. 2026 setup.
AI agent workflow evaluation framework — deterministic, CI-ready scoring of multi-step instructions with a three-tier hybrid engine and dual-metric reporting.
GitHub issue to production in 40 minutes — automated Claude Code workflow with pre-commit, CI/CD, and PR-review feedback loops to ship 90%+ merge-ready code.
Yes, there's a Slack CLI. SlackCLI is an open-source command-line tool to read and send Slack messages from your terminal — built for AI agents and automation.
Why selecting GenAI tools for an enterprise is challenging, and why building your own foundational capabilities might be the best approach for sustainable innovation.
Learn how the Model Context Protocol (MCP) enables AI models to access external tools and services, breaking free from their isolated environments to perform real-world tasks.
A practical Bash script that collects Git repository data to provide context for AI models to generate meaningful changelogs automatically.