“llms”
Agentic Workflows with the Model Context Protocol (MCP)
A single prompt is not a workflow. Learn how to build multi-step agentic workflows on top of the Model Context Protocol: planning loops, tool chaining, human-in-the-loop gates, and orchestration patterns that survive production.
A/B Testing Prompts in Live Applications
You would never ship a UI change without testing it. Learn how to A/B test prompts in production: bucketing, determinism, and evaluating quality without chasing noise.
Building a Production-Ready RAG Pipeline with LlamaIndex
Move beyond the demo RAG app. Learn how to structure a production RAG pipeline with LlamaIndex: ingestion, chunking, embedding, retrieval, evaluation, and observability.
Cost Monitoring for Production LLM Applications
Stop guessing what your LLM app costs. Learn how to capture token usage, attribute spend per user and feature, set budget alerts, and build a cost dashboard that scales.
Database Agents: Natural Language to SQL in Production
Let users ask your database questions in plain English — safely. A production guide to text-to-SQL agents: schema grounding, query validation, and read-only guardrails.
Evals for Agents: Unit Testing Multi-Step Reasoning
Agents are too expensive to test by eye. Learn how to write evals for multi-step reasoning: checkpoints, tool-call assertions, rubric scoring, and regression gates in CI.
Local-First AI: Ollama, llama.cpp, and On-Prem Inference
Keep your data in-house and your bills predictable. A practical guide to running open models locally with Ollama and llama.cpp, plus when on-prem inference beats the cloud APIs.
Optimizing Context Windows: Token Budgeting Best Practices
A 10M-token window is a trap, not a license. Learn to budget tokens like memory: account for every section, prioritize by recency and relevance, and cut cost and latency.
Synthetic Data Generation for Testing and Fine-Tuning
Real data is scarce, private, and expensive to label. Learn how to generate high-quality synthetic data with LLMs — for unit tests, evals, and fine-tuning datasets.
Automating Documentation with AI: Codebase to Docs
Stale docs die by neglect; AI keeps them close to the code. Build a scan → plan → generate → verify pipeline that turns any repo into current, useful documentation.
The State of Open-Source LLMs in 2026
Open weights route most production tokens now, Qwen leads the Hub, and China out-downloads the West. Here is the data-driven 2026 map for choosing an open model.
GenAI Security: The OWASP Top 10 for LLM Applications
The 2026 OWASP GenAI LLM Top 10 is grounded in ~10,000 real incidents. Learn the actual risks — prompt injection, excessive agency, misinformation — and the concrete mitigations for devs.
Self-Hosting an LLM Gateway with LiteLLM
One OpenAI-compatible endpoint in front of every model your team uses, with routing, rate limits, spend caps, and auth. Deploy LiteLLM and stop hard-coding provider keys in your services.
Multimodal Pipelines: Images, Audio, and Video in LLMs
Stop reducing your data to text before the model sees it. Send images, audio, and video natively to Gemini and build one pipeline that understands them together.
Knowledge Graphs for AI: GraphRAG Explained
Naive RAG misses the answer that connects many documents. GraphRAG builds a knowledge graph from text and queries it. Learn the indexing pipeline, community detection, and query modes.
Semantic Caching to Reduce Latency and Spend
Users ask the same question a hundred different ways. Semantic caching serves cached answers for similar queries — cutting LLM spend by up to 86% and latency from seconds to milliseconds.
Tools, Function Calling, and the Agent Execution Loop
The agent loop is a model deciding which tools to call, observing results, and iterating. Learn function declarations, tool_choice modes, and parallel calling.
Prompt Caching Strategies to Cut LLM API Costs
Cached input tokens are ~90% cheaper than fresh ones. Learn implicit vs explicit caching, TTL design, and how to structure prompts so your cache hits.
LLM Application Architecture Patterns in 2026
The architecture of an LLM application is no longer one prompt to one model. Learn the RAG, agentic, and caching patterns that production teams actually ship in 2026.
Batch Inference at Scale with Ray
Offline LLM work — scoring, summarization, backfills — needs throughput and reliability, not latency. Distribute thousands of calls with Ray tasks and actors, retries, and structured cost tracking.
Streaming Inference with FastAPI and Server-Sent Events
Turn a blocking LLM call into an incremental, observable stream of tokens with FastAPI StreamingResponse and Server-Sent Events — including cancellation and backpressure.
Fine-Tuning vs. RAG: When to Use Which Technique
Fine-tuning changes how the model behaves; RAG changes what it sees. Use a checklist and a small offline eval to decide between the two — and when to combine them into a hybrid.
Structured Outputs: JSON Schema Validation for LLMs
Ask an LLM for JSON and you will get broken JSON. Learn to constrain generation with Gemini response_schema and Pydantic, then verify the output as an explicit, catchable step.
MLOps for LLMs: Versioning Prompts, Data, and Weights
LLM apps drift for reasons unrelated to weights. Version prompts, datasets, and models against the metrics that decide whether a change is an improvement, using MLflow tracking plus the Model Registry.
RAG Evaluation: Measuring Retrieval Quality Objectively
A RAG pipeline fails in two halves: retrieval and generation. Build a transparent Python eval harness computing hit_rate, MRR, context precision/recall, and faithfulness to know exactly which half to fix.
A Deep Dive into LangChain Expression Language (LCEL)
Learn how to construct complex AI pipelines effortlessly using the declarative power of LangChain Expression Language (LCEL).
Coding with AI using the Agent Development Kit (ADK) and llms.txt
Learn how to enhance your AI coding assistants with the Agent Development Kit documentation using the llms.txt standard across popular tools.