Cloud architecture, DevOps, AI engineering, and the journey to senior technical leadership.https://tebogosacloud.blog/en-ushttps://tebogosacloud.blog/blog/ai-governance-fastapi-eks-helm/https://tebogosacloud.blog/blog/ai-governance-fastapi-eks-helm/How I built an AI governance platform on AWS EKS — FastAPI inference endpoint with per-request audit logging, model card endpoint, fairness metadata, and Helm-packaged deployment with HPA.Wed, 29 Apr 2026 00:00:00 GMTAWS & Cloud Architectureawskubernetespythonmlopshttps://tebogosacloud.blog/blog/building-mlops-pipeline-sagemaker-telecom-churn/https://tebogosacloud.blog/blog/building-mlops-pipeline-sagemaker-telecom-churn/How I built an end-to-end MLOps pipeline with SageMaker Pipelines, automated retraining via EventBridge, and drift monitoring using KS tests and CloudWatch — for a telecom churn use case.Wed, 29 Apr 2026 00:00:00 GMTAWS & Cloud Architecturemlopsawssagemakerpythontelecomhttps://tebogosacloud.blog/blog/predicting-telecom-churn-sklearn-keras-sagemaker/https://tebogosacloud.blog/blog/predicting-telecom-churn-sklearn-keras-sagemaker/Learn how to build a telecom customer churn predictor using Random Forest, Keras neural networks, and deploy it to a real-time SageMaker endpoint. Full code included.Wed, 29 Apr 2026 00:00:00 GMTAWS & Cloud Architecturemachinelearningawssagemakerpythontelecomhttps://tebogosacloud.blog/blog/real-time-iot-pipeline-kinesis-lambda-dynamodb/https://tebogosacloud.blog/blog/real-time-iot-pipeline-kinesis-lambda-dynamodb/How I built a real-time IoT data pipeline on AWS — device simulator → Kinesis stream → Lambda consumer → DynamoDB — with anomaly detection that fires SNS alerts and CloudWatch metrics.Wed, 29 Apr 2026 00:00:00 GMTAWS & Cloud Architectureawsiotkinesislambdapythonhttps://tebogosacloud.blog/blog/local-first-agentic-development/https://tebogosacloud.blog/blog/local-first-agentic-development/The industry ships agents fast and debugs them in production. Here's the opposite approach — local-first agentic development, liftability by design, and selective promotion to AWS Bedrock AgentCore.Mon, 13 Apr 2026 00:00:00 GMTGenAI & AI Engineeringmlopsllmopsagentopsawsbedrockagentcoreserverlessmachinelearninghttps://tebogosacloud.blog/blog/the-missing-test-suite-why-ai-projects-fail-before-production/https://tebogosacloud.blog/blog/the-missing-test-suite-why-ai-projects-fail-before-production/Most AI projects never reach production. The missing piece is prompt testing — with the same rigour as TDD. Here's the strategy for shipping AI systems that actually work.Thu, 02 Apr 2026 00:00:00 GMTGenAI & AI Engineeringaitestingsoftware-engineeringprompt-engineeringtddhttps://tebogosacloud.blog/blog/building-llm-judge-that-doesnt-lie/https://tebogosacloud.blog/blog/building-llm-judge-that-doesnt-lie/Our first LLM judge gave a 9/10 to a page with invisible text. Here's how we fixed it with structural guardrails, multimodal inputs, and a fixed-weight violation catalogue.Tue, 31 Mar 2026 00:00:00 GMTGenAI & AI Engineeringaievaluationllm-as-judgetestingqualityhttps://tebogosacloud.blog/blog/beyond-text-evaluating-multi-file-ai-outputs/https://tebogosacloud.blog/blog/beyond-text-evaluating-multi-file-ai-outputs/Most LLM benchmarks evaluate text. We needed to evaluate entire websites. Here's the 4-layer evaluation framework we built to score AI-generated multi-file artifacts using a violation-deduction model.Mon, 30 Mar 2026 00:00:00 GMTGenAI & AI Engineeringaievaluationllmtestingsoftware-architecturehttps://tebogosacloud.blog/blog/comparing-llms-real-code-generation/https://tebogosacloud.blog/blog/comparing-llms-real-code-generation/We tested Claude Sonnet, Kimi K2.5, Claude Haiku, DeepSeek V3.2, and DeepSeek R1 on the same 16-action website generation pipeline. The results weren't what we expected.Mon, 30 Mar 2026 00:00:00 GMTGenAI & AI Engineeringaillmclaudedeepseekbenchmarkshttps://tebogosacloud.blog/blog/from-ide-to-cloud-lifting-agent-to-agentcore/https://tebogosacloud.blog/blog/from-ide-to-cloud-lifting-agent-to-agentcore/A practical guide to deploying a local Python MCP server to Amazon Bedrock AgentCore Runtime — from localhost prototype to production-grade cloud service with session isolation, authentication, and observability.Tue, 03 Mar 2026 00:00:00 GMTAWS & Cloud Architectureaiawspythonmcpbedrockagentcorehttps://tebogosacloud.blog/blog/how-i-create-memory-for-my-agents-on-claude-code/https://tebogosacloud.blog/blog/how-i-create-memory-for-my-agents-on-claude-code/A six-layer memory architecture for persistent AI agent knowledge — from CLAUDE.md foundations to auto memory, plans, and permissions — managing 14 specialized agents across multiple AWS projects.Tue, 03 Mar 2026 00:00:00 GMTGenAI & AI Engineeringaiclaude-codeagent-memoryproductivitydeveloper-tools