
🧠 AI & Machine Learning
RAG chatbots, AI agents, model training and serving, LLM gateways and MLOps pipelines. Open any template to see the finished diagram, then use it as the starting point for your own in the Studio.
11 templates
A chatbot that answers staff questions from company documents: documents are split and indexed in a vector database, and each question pulls the most relevant passages before the language model writes an answer.
What happens when a user asks the document chatbot a question: permission check, embedding, vector search, prompt building and a cited answer.
How documents become searchable passages for an AI assistant: extraction, cleaning, chunking, embedding and indexing, with changed files re-processed automatically.
How an AI agent completes a task by planning, calling tools, checking results and asking a person to approve risky actions before it finishes.
Where each part of an MLOps setup runs: feature store, training jobs on GPU nodes, experiment tracking, model registry and automated deployment to serving.
The states a machine learning model moves through, from experiment to production to retirement, including rollback when live performance drops.
One gateway that every app in a company uses to reach language models: it applies budgets, rate limits, content filters and caching, and records usage per team.
Tables that keep machine learning work reproducible: datasets and their versions, experiments, runs, metrics, and registered models with their deployments.
How an app gets a live prediction: features are fetched from an online store, the model scores the request, and the result and inputs are logged for monitoring.
How a self-hosted language model is deployed for many users: autoscaled GPU pods behind a gateway, with model weights cached close to the GPUs.
Where generative AI is used across a typical company, grouped by department, to help plan which projects to start first.
More AI & Machine Learning templates are being added regularly.
AI and machine-learning diagrams show how data becomes a model and how the model reaches users: data pipelines, feature stores, training and evaluation, model registry, serving, and monitoring for drift.
For generative AI they also show retrieval-augmented generation (RAG): document ingestion, embeddings, the vector database, the LLM call and the guardrails around it.
Document sources, the ingestion and chunking step, the embedding model, the vector database, the retriever, the LLM, the chat app, and guardrails such as access checks and output filtering.
Show data sources, the feature pipeline and store, training jobs, evaluation, the model registry, the serving endpoint and monitoring, with a feedback arrow from monitoring back to training.
Yes. Describe it in the Studio, for example "support chatbot using RAG over Confluence with OpenAI and pgvector", and the AI draws it.