AI Orchestration and Agentic Workflows

With the following suite of features, Orkes Conductor enables you to efficiently build AI-powered or agentic applications that leverage AI models and vector databases:

• AI System Tasks—Drag and drop common AI tasks, like storing embeddings or chat completions.
• AI/LLM and Vector Database Integrations—Seamlessly connect and access dozens of AI-related integrations in a secure and governed manner.
• AI Prompt Studio—Refine, test, and govern prompt templates for AI models.

Some common use cases for AI orchestration include:

• AI agents or agentic workflows
• RAG (retrieval augmented generation) systems
• LLM-powered chatbots
• AI classifiers

Orchestrating AI-powered tasks

Orkes Conductor provides a variety of system AI tasks, which can execute common logic without the need to write code. Depending on the type of tasks, using these tasks may require an AI/LLM integration, a vector database integration, or an AI prompt.

System AI Task	Description	Prerequisites
LLM Get Document	Retrieve text or JSON content from a URL.	NA
LLM Generate Embeddings	Generate text embeddings.	Integrate an AI model
LLM Store Embeddings	Store text embeddings in a vector database.	Integrate an AI model Integrate a vector database
LLM Index Text	Generate and store text embeddings in a vector database.	Integrate an AI model Integrate a vector database
LLM Index Document	Chunk, generate, and store text embeddings in a vector database.	Integrate an AI model Integrate a vector database
LLM Get Embeddings	Retrieve data from a vector database.	Integrate a vector database
LLM Search Index	Retrieve data from a vector database based on a search query.	Integrate an AI model Integrate a vector database
LLM Text Complete	Generate text from an LLM based on a defined prompt.	Integrate an AI model Create an AI prompt
LLM Chat Complete	Generate text from an LLM based on a user query and additional system/assistant instructions.	Integrate an AI model Create an AI prompt

If custom logic is required, you can create an external worker instead of using the system AI tasks. To do so, follow the guide on Using External Workers instead.

Once you have decided which task to use, check out the following guides to begin building AI-powered or agentic applications.

Learn more

📄️ Using AI Models or LLMs

Learn how to use AI models or LLMs with Orkes' system LLM tasks, including the steps for integration, access control, and more.

📄️ Using Vector Databases

Learn how to use vector databases in Orkes' system LLM tasks, including the steps for integration and access control.

📄️ Using AI Prompts

Learn how to create prompt templates and use them in Orkes' system LLM tasks.