Blog
Cloud, automation and working with AI, in practice
How to automate business processes, improve how your team ships, run AI in production and keep cloud costs down: practical guides from the engineers who do it.
LatestAutomationFrom Idea to AI Feature in Six Weeks11 Nov 2026 · 3 min read
CI/CDCI/CD for Models and Prompts2 Nov 2026 · 3 min read
Fine-TuningFine-Tuning or Prompting? A Decision Guide for Small Teams23 Oct 2026 · 3 min read
AutomationAutomating Business Workflows with AI, Safely15 Oct 2026 · 3 min read
ObservabilityObservability for LLM Applications6 Oct 2026 · 3 min read
From Idea to AI Feature in Six WeeksHow an AI project runs end to end in six weeks: discovery, design, prototype, infrastructure, rollout, then measuring and improving.CI/CD for Models and PromptsEvaluation gates, model registries, canary releases and rollback: applying CI/CD discipline to prompts and models in LLM applications.Fine-Tuning or Prompting? A Decision Guide for Small TeamsWhen prompting, RAG or fine-tuning is the right way to adapt a language model, and what each one costs a small engineering team.Automating Business Workflows with AI, SafelyWhere AI fits in business process automation, and how human review, guardrails and audit trails keep automated workflows safe.Observability for LLM ApplicationsWhat to measure in an LLM application: tokens, latency, cost per request, OpenTelemetry traces and the quality signals that show when answers get worse.
Hosted LLM APIs or Self-Hosted Open Models?GPT, Claude and Gemini APIs against self-hosted open models, compared on cost, privacy, latency and the engineering effort each one needs.
RAG in Production: The Boring Parts That MatterIngestion, chunking, refresh, evaluation and access control: the unglamorous work that decides whether a RAG system can be trusted.
GPU Nodes on Kubernetes Without Wasting MoneyNode pools, MIG, time-slicing, scale to zero and spot instances: practical ways to keep Kubernetes GPU costs under control for AI workloads.
vLLM vs Ollama vs TGI: Choosing an Inference ServerHow vLLM, Ollama and Hugging Face TGI differ in throughput, hardware support and operations, and which one fits your workload.
Running Open Models in Production: A Practical Starting PointWhat it takes to run Llama, Mistral, Qwen, Gemma or DeepSeek in production: picking a model, sizing hardware, serving it and keeping it healthy.
Simpler Infrastructure, Faster Engineering TeamsSimpler infrastructure helps engineering teams move faster, deploy more efficiently, and focus on building products.
The Hidden Cost of Manual InfrastructureManual infrastructure creates hidden operational costs through inconsistent deployments, repeated processes, and growing engineering complexity.
Internal Developer Platforms (IDP): Build or Buy?Should you build your own Internal Developer Platform (IDP) or buy one? Compare costs, setup time, and focus on your core product with DoneDeploy.