Topic
Moving beyond single prompts: practical patterns for building, deploying, and operating reliable AI agents that automate complex organizational workflows.
The real value of AI agents isn’t in generalist chatbots or simple prompt wrappers. It shows up when you pair LLMs with deterministic tools to handle multi-step workflows that previously required manual oversight.
These posts explore what it takes to take agents from local prototypes into reliable production assets: from choosing initial use cases to structuring instruction layers, managing state, and maintaining reliability.
Part 4 of 4 ·
How I set up an AI agent with the Figma MCP and a component library to generate editable, on-brand social media visuals.
Regenerating AI images for every small tweak is slow and costly. How I generate editable social media visuals with an AI agent, the Figma MCP and a skill.
Part 3 of 4 ·
Why I run my own assistant instead of relying only on provider apps.
Running Hermes Agent on a VPS gives me one assistant with my tools, files, context, recurring workflows, and review points across Telegram and email.
Part 2 of 4 ·
The agent demos browse the web, write the code, and seemingly do your job. The agents that actually survive inside an enterprise are far less impressive – and that's exactly why they work. A case for starting boring.