LLM application
An LLM application is software whose functionality incorporates a large language model to perform tasks, process inputs, or produce outputs.
Machine Learning Platform Engineering
An LLM application is a software system whose functionality uses a large language model to process inputs and produce outputs.
- How it is used
- Extends MLOps infrastructure with retrieval, prompt, evaluation, observability, cost, and safety capabilities for production generative workloads.
- How deep it goes
- Explains architecture, metadata, RAG flow, testing, monitoring, and governance, stopping short of implementation code in the supplied evidence.
- Examples
- Uses DakkaBot, company documentation, document ingestion, vector embeddings, semantic retrieval, prompt augmentation, and generated answers.
- What you can do after
- Build it from scratch as an observable RAG service with managed prompts, semantic tests, cost tracking, and multilayered safety controls.
Read how Machine Learning Platform Engineering explains LLM application →
AI Agents and Applications
An LLM application is software that provides a use-case-specific interface or workflow around a large language model.
- How it is used
- Frames LLM applications as use-case-specific workflows around a model, including bounded backend engines.
- How deep it goes
- Explains common workflows and Q&A ingestion and retrieval, while deferring detailed coverage of embedding models and vector stores.
- Examples
- Uses summarization and knowledge-base Q&A engines alongside a web research summarization project.
- What you can do after
- Apply LLM workflows using LangChain and LCEL to organize research summarization into chains.
Read how AI Agents and Applications explains LLM application →
Build an Advanced RAG Application (From Scratch)
A large language model application is software that integrates one or more large language models to address practical tasks or real-world challenges.
- How it is used
- Coordinates models, compute, software, data, and application goals to deliver practical natural-language capabilities.
- How deep it goes
- Explains system components, hardware, purpose, training, fine-tuning, and RAG, but stops short of implementation details.
- Examples
- Uses RAG, the Ares API, taco-search answers, and startup categories including wrappers, vector databases, and LLM frameworks.
- What you can do after
- Build practical, context-aware LLM applications by selecting resources, defining tasks, refining models, and incorporating retrieved information.
Read how Build an Advanced RAG Application (From Scratch) explains LLM application →
Also covered in
- Context EngineeringIn early access (MEAP)
What to know first
- promptA prompt is text or other input supplied to an AI model to provide instructions, context, or other information that guides its response or generated output.
- AI agentAn AI agent is a computational system that uses artificial intelligence to interpret information and select or perform actions toward goals while interacting with an environment.
- knowledge baseA knowledge base is an organized body or representation of information that people or computational systems can consult to support retrieval, reference, reasoning, or tasks.
- prompt injectionPrompt injection is an attack that introduces instructions through input or context to manipulate an AI system’s behavior or override its intended instructions.
Related concepts
- promptuses · A prompt is text or other input supplied to an AI model to provide instructions, context, or other information that guides its response or generated output.
- working contextuses · Working context is the information and intermediate state available to an AI model or agent while performing a task that can influence its behavior.
- applicationkind of · An application is a software program or system that provides functionality or performs tasks for users or other software.
- language modeluses · A language model is a computational model that represents patterns in linguistic sequences to assign probabilities, predict, generate, or evaluate language.
- monitoringuses · Monitoring is the ongoing observation and measurement of a system or process to assess its behavior or condition and detect changes, failures, or other problems.
- retrieval-augmented generationused by · Retrieval-augmented generation is a technique that retrieves relevant information from external sources and supplies it as context to a generative model when producing an output.
Questions about LLM application
What is LLM application?
An LLM application is software whose functionality incorporates a large language model to perform tasks, process inputs, or produce outputs.
Which Manning books explain LLM application?
Machine Learning Platform Engineering, AI Agents and Applications and Build an Advanced RAG Application (From Scratch).
What should I know before learning LLM application?
Manning books that teach LLM application usually introduce prompt, AI agent, knowledge base and prompt injection first.
What is LLM application a kind of?
LLM application is a kind of application. An application is a software program or system that provides functionality or performs tasks for users or other software.
What is LLM application also called?
LLM application is also called large language model application or LLM-based applications.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.


