What's new
Everything that has changed, newest first
This page is assembled from the dates on the content itself rather than a list someone remembers to update, so nothing that ships can be left off it.
Subscribe by feedWhat's new
The timeline
October 2026
- New guideAutoGenBuild multi-agent conversations and event-driven agent systems with Microsoft AutoGen. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideClaude Agent SDKBuild autonomous agents on the same harness that powers Claude Code: tools, permissions, subagents and MCP. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideCrewAIOrchestrate role-based teams of AI agents that plan, delegate and collaborate on tasks. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideDSPyProgram LLMs instead of prompting them, and let optimisers tune prompts and weights for you. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideFeastServe consistent features for training and inference with the Feast feature store. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideGoogle ADKBuild, evaluate and deploy multi-agent systems with Google’s Agent Development Kit. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideOpenAI Agents SDKBuild agents with tools, handoffs, guardrails and tracing on OpenAI’s lightweight agent SDK. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideSemantic KernelIntegrate LLMs, plugins and agents into C#, Python and Java applications with Microsoft Semantic Kernel. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideBentoMLPackage and serve models as production APIs with BentoML. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideDelta LakeAdd ACID transactions, time travel and schema enforcement to data lakes with Delta Lake. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideSeldon CoreDeploy, scale and monitor models on Kubernetes with Seldon Core. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideAzure OpenAIRun OpenAI models in Azure: deployments, quotas, private networking and enterprise controls. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideHaystackBuild production RAG and search pipelines from modular, testable components. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideLangChainBuild LLM applications from composable models, prompts, retrievers and tools. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideLangGraphBuild stateful, controllable agents as graphs, with memory, human-in-the-loop and durable execution. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideLlamaIndexConnect LLMs to your own data: ingestion, indexing, retrieval and agentic RAG. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideModel Context Protocol (MCP)Connect LLM applications to tools and data through the open Model Context Protocol: build servers and clients. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guidePydantic AIBuild type-safe agents and structured-output LLM apps in Python with Pydantic AI. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guidesmolagentsBuild lightweight code-writing agents with Hugging Face smolagents. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideAxolotlFine-tune LLMs from a single YAML config with Axolotl: SFT, LoRA, multi-GPU and more. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideChromaAdd embeddings search to your app in minutes with the open-source Chroma database. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideDeepSpeedTrain and serve large models across many GPUs with DeepSpeed’s ZeRO and parallelism. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideFAISSBuild fast similarity-search indexes in-process with Meta’s FAISS library. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideMilvusRun billion-scale vector search with the cloud-native Milvus database. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guidePEFT & TRLFine-tune LLMs efficiently with LoRA/QLoRA (PEFT) and align them with SFT, DPO and RLHF (TRL). Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guidepgvectorStore and query embeddings inside PostgreSQL with the pgvector extension. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guidePineconeStore and search embeddings at scale with Pinecone’s managed vector database. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guidePyTorch LightningOrganise PyTorch training code and scale it across GPUs and nodes with Lightning. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideQdrantRun fast, filterable vector search with the open-source Qdrant engine. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideRay ServeServe models and composed inference pipelines at scale with Ray Serve. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideText Generation InferenceServe open LLMs in production with Hugging Face Text Generation Inference. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideTriton Inference ServerServe models from any framework on GPUs and CPUs with NVIDIA Triton. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideUnslothFine-tune open LLMs faster and with less GPU memory using Unsloth. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guidevLLMServe LLMs with high throughput using vLLM’s PagedAttention and OpenAI-compatible server. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideWeaviateRun hybrid vector and keyword search with the open-source Weaviate database. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideAlibi DetectDetect outliers, adversarial inputs and drift with Alibi Detect. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideAnsibleAutomate server configuration and deployments with Ansible playbooks. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideArgo CDDeploy to Kubernetes the GitOps way with Argo CD. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideArize PhoenixTrace and evaluate LLM apps with the open-source Arize Phoenix, built on OpenTelemetry. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideAzure Machine LearningBuild, train and deploy models on Azure with Azure Machine Learning. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideCometTrack, compare and register models with Comet’s ML platform. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideDagsterBuild asset-based data and ML pipelines with Dagster. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideDatabricksRun data engineering, ML and GenAI on the Databricks lakehouse platform. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideDeepEvalUnit-test LLM apps with DeepEval’s metrics, test cases and CI integration. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideELK StackSearch and analyse logs with Elasticsearch, Logstash and Kibana. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideFastAPI for MLWrap ML models in fast, typed, well-documented APIs with FastAPI. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideFluxKeep Kubernetes clusters in sync with Git using Flux. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideGitLab CI/CDBuild, test and deploy with GitLab CI/CD pipelines. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideGrafanaVisualise metrics, logs and traces in Grafana dashboards and alerts. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideGreat ExpectationsValidate and document data quality with Great Expectations. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideGuardrails (NeMo Guardrails & Guardrails AI)Keep LLM apps safe and on-topic with NeMo Guardrails and Guardrails AI validators. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideHeliconeLog, monitor and control LLM usage and cost with the Helicone gateway. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideHelmPackage and release Kubernetes applications with Helm charts. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideJenkinsAutomate builds and deployments with Jenkins pipelines. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideKedroStructure maintainable, production-ready data-science code with Kedro. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideKServeServe models on Kubernetes with autoscaling and canaries using KServe. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideKubeflowRun ML pipelines, notebooks and training jobs on Kubernetes with Kubeflow. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideKubernetesDeploy, scale and operate containers with Kubernetes. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideKustomizeCustomise Kubernetes manifests per environment without templates using Kustomize. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guidelakeFSVersion data lakes with Git-like branches, commits and merges using lakeFS. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideLangSmithTrace, evaluate and monitor LLM applications with LangSmith. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideMetaflowBuild and scale data-science workflows from laptop to cloud with Metaflow. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideNannyMLEstimate model performance without labels and detect drift with NannyML. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideOpenTelemetryInstrument services with vendor-neutral traces, metrics and logs using OpenTelemetry. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideOpikTrace, evaluate and optimise LLM apps with Comet’s open-source Opik. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guidePrefectOrchestrate Python data and ML workflows with Prefect flows, tasks and deployments. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guidePrometheusCollect metrics and alert on them with Prometheus and PromQL. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guidepromptfooTest prompts, models and RAG pipelines, and red-team them, with promptfoo. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guidePulumiProvision infrastructure in Python, TypeScript or Go with Pulumi. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideRayScale Python and ML workloads — data, training, tuning — across a cluster with Ray. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideAmazon SageMakerBuild, train and deploy models on AWS with SageMaker. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideApache SparkProcess big data and train models at scale with Apache Spark and PySpark. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideTerraformProvision cloud infrastructure declaratively with Terraform. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideTorchServeServe PyTorch models in production with TorchServe. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideTrivyScan images, code, IaC and Kubernetes for vulnerabilities and misconfigurations with Trivy. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideTruLensEvaluate and track LLM apps with TruLens feedback functions. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideHashiCorp VaultManage secrets, encryption and dynamic credentials with HashiCorp Vault. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideVertex AIBuild, train and deploy models on Google Cloud with Vertex AI. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideWeights & BiasesTrack experiments, sweep hyperparameters and version artefacts with Weights & Biases. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
- New guideZenMLBuild portable ML pipelines that run on any stack with ZenML. Taught at three levels — Beginner, Mid-level and Senior — each with an in-depth guide, interview prep, and practical tips.
September 2026
- New guideEvidentlyLearn ML monitoring at your level: compare reference and current data, build dependable drift and quality checks, or govern a secure multi-team monitoring platform.
- New guideLangfuseLearn Langfuse at the level that fits your work: build and read a first trace, make observability reliable in production, or govern a multi-team evaluation platform.
- New guideRAGASLearn RAG evaluation at your level: score a first dataset, build calibrated regression gates, or govern a secure multi-team evaluation platform.
- Live sessionThe MLOps Practitioner — Session 3Inference, Serving & Release Strategies
- New guideAirflowA full workflow orchestration course taught at three levels. Pick Beginner, Mid-level, or Senior, then read the detailed explanation, a fast interview review, or the practical tips and traps.
- New guideClearMLA full experiment tracking and MLOps platform course taught at three levels. Pick Beginner, Mid-level, or Senior, then read the detailed explanation, a fast interview review, or the practical tips and traps.
- New guideDockerA full containers course taught at three levels. Pick Beginner, Mid-level, or Senior, then read the detailed explanation, a fast interview review, or the practical tips and traps.
- New guideDVCA full data and pipeline versioning course taught at three levels. Pick Beginner, Mid-level, or Senior, then read the detailed explanation, a fast interview review, or the practical tips and traps.
- New guideMLflowA full experiment tracking, model packaging, and registry course taught at three levels. Pick Beginner, Mid-level, or Senior, then read the detailed explanation, a fast interview review, or the practical tips and traps.
- New guideGitHub ActionsA full CI/CD and repository-automation course taught at three levels. Pick Beginner, Mid-level, or Senior, then read the detailed explanation, a fast interview review, or the practical tips and traps.
August 2026
- Live sessionHands-on CI/CD and GitHub ActionsBuild a working workflow file you can drop into your own repo the same day
- Live sessionDocker Deep DiveDocker: Building the Foundation for MLOps — Day 1
- ArticleTokenization: How LLMs Turn Text Into Something They Can ProcessYou type a sentence and assume the model receives it as you wrote it. It does not. What actually happens to your text before the model ever sees it.
- Live sessionThe On-Prem MLOps PlaybookBridging Traditional DevOps and Private AI Workloads
- ArticleIntroduction to Large Language Models: Understanding the Foundation of Modern AIWhat a large language model actually is, and why these models are called 'large' — the foundation piece, before tokenization and everything built on top of it.
July 2026
- ArticleThe DevOps to MLOps Transition RoadmapYou already own 60–70% of the skillset. This roadmap adds only the ML layer on top — the fastest career pivot in tech, in five phases over three to five months.
- ArticleMLOps Roadmap for SeniorsSeven specializations — LLMOps, model optimization, production Kubernetes, advanced monitoring, performance and load testing, system design for ML, and soft skills. Pick two or three and go deep.
- RoadmapThe DevOps to MLOps Transition RoadmapThe fastest career pivot in tech
- RoadmapMLOps Roadmap for SeniorsDepth, system thinking, and production scale
June 2026
Follow it in any feed reader: /feed.xml