Turn

TECHNICAL DEFINITION

A complete interaction cycle within a conversational AI system, comprising a user's utterance (input) and the subsequent AI model's response (output), forming a sequential dialogue history.

BACKGROUND

Prompt engineering is the process of structuring natural language inputs to produce specified outputs from a generative artificial intelligence (GenAI) model. Context engineering is the related area of software engineering that focuses on the management of non-prompt and prompt contexts supplied to the GenAI model, such as system instructions, metadata, API tools and tokens.

SYNONYMS & ALIASES

• Dialogue turn
• conversational exchange
• interaction step

USAGE NOTE

The number of turns can impact context window limits and conversational flow.

DEVELOPERS

Organizations developing technology related to Turn.

• OpenAI

  A leading AI research and deployment company known for its large language models like GPT-3 and GPT-4, which are foundational to AI engineering and prompt design for conversational AI and complex 'turns'.

• Google AI

  Google's division for AI research and development, responsible for models like Gemini and extensive work in conversational AI and natural language processing, where prompt design and managing dialogue 'turns' are critical.

• Anthropic

  An AI safety and research company that develops advanced AI systems, including the Claude family of models. They emphasize responsible AI and prompt engineering, often involving complex conversational 'turns' and ethical considerations.

• Microsoft Azure AI

  Microsoft's cloud AI platform offering tools and services for AI development, including prompt engineering frameworks like Semantic Kernel and orchestrating multi-step AI workflows and conversational agents.

• Hugging Face

  Provides open-source tools, datasets, and models that are central to AI engineering, allowing developers to experiment with and deploy various language models and refine prompt designs for different applications and 'turns'.

• LangChain

  An open-source framework designed for developing applications powered by large language models, explicitly facilitating prompt management, chaining multiple prompts, and managing conversational memory across 'turns'.

• LlamaIndex

  An open-source data framework for LLM applications, focused on enabling LLMs to work with custom data sources. It is often used in conjunction with LangChain to manage and query information across conversational 'turns'.

• Cohere

  Develops enterprise-grade large language models and provides tools for developers to build powerful AI applications. Their focus on customizability and retrieval-augmented generation involves advanced prompt design and managing information flow across 'turns'.