Most AI content stops at the prototype. The posts in this collection are about what comes after — building AI tools that are reliable, affordable and safe enough to put in front of real users. A lot of this work centres on the Model Context Protocol (MCP), which I think is one of the most important shifts in how we connect models to real data and tools.
You will find end-to-end builds of MCP servers, deep dives on Amazon Bedrock and RAG, and hard-won lessons on cutting token costs, controlling model output, and keeping AI systems secure. I write from a builder’s seat: every guide here comes from something I actually shipped, including where it went wrong and what I would do differently next time.
Articles in this topic
- Building an Agent on Amazon Bedrock AgentCore: End-to-End Notes Apr 2026
- Build a Semantic Cache with AWS Services (S3 Vectors + Bedrock) Jan 2026
- Designing AI Agent Tools: Cut Token Costs 70% (MCP Case Study) Jan 2026
- AWS DevOps Agent: AI-Powered Incident Investigation Dec 2025
- Docker MCP Catalog and Toolkit: Simpler AI Agent Integrations Oct 2025
- Build a Bible MCP Server: A Complete Custom AI Tool Guide Aug 2025
- How to Get Consistent AI Results: 7 Parameter Controls Jul 2025
- Streamline Location-Relevant Answers with SharePoint, Amazon Nova and Bedrock Apr 2025
- Docker Model Runner: Run AI Models Locally Apr 2025
- DeepSeek vs OpenAI: How the AI Race Is Heating Up Feb 2025
- Kubernetes Sidecar Containers: Beyond the Basics Dec 2024
- Intelligent Kubernetes Event Summarizer: A Step-by-Step Guide with a Demo Nov 2024
- Leveraging eBPF for Container Network Monitoring with Cilium Oct 2024
- Building a Unified Bible Platform: Q&A, Insights, and Ministry Matching Oct 2024
- Automating Code Reviews with GitLab CI/CD and Ollama May 2024
- AI-Driven ServiceNow Incident QnA Bot using Amazon Bedrock Jan 2024
- Revolutionize Chatbots with Pinecone OpenAI & Custom Data Aug 2023
- AI-Powered Data Parsing for Smart Answers Jul 2023