Skip to content
Back to blog

Tag

ai-agents

6 posts with this tag

I connected AI to my mail. The hard part was deciding what to hide from it

mailmcp gives ChatGPT and Claude access to Gmail, Outlook and Seznam. After a year of building it, the most valuable features turned out to be the ones where the server says no. Version 0.13 adds a guard that keeps verification codes and 2FA mail away from the model, set per mailbox.

13 min read

From Ticket to Merge Request: How AI Handles the Whole Fix for Me

A customer reports a problem, AI takes it from plan to code to checks and opens a merge request. I review only the final result and ship it to production. How I actually run this workflow with clients — and on this very site, through GitLab.

4 min read

Cowork Turns AI from Chat into Work: What to Tackle This Week

Cowork is out of preview, Opus 4.7 changes how you write prompts, and Claude for Small Business packs AI into ready-made workflows. A practical filter on Anthropic's latest — without launching a big pilot.

10 min read

Skills vs. Agents: When You Need a Recipe and When You Need a Chef

Structured prompts or autonomous AI agents? A practical guide across the spectrum from simple prompt to multi-agent system — with real business examples.

9 min read

AI Agents Are Not Ready for Your Business (And That's OK)

Agentic AI is the 2026 buzzword, but reality is sobering. Where agents actually work, where they don't, and how to decide whether to experiment or wait.

5 min read

/loop — How I Turned Claude Code Into an Autonomous Agent

One terminal command turns an AI assistant into an agent that plans, implements, and cleans up. A detailed walkthrough of my /improve-gitlab setup.

10 min read