"OpenAI has released Open Responses, an open specification to standardize agentic AI workflows and reduce API fragmentation. Supported by partners like Hugging Face and Vercel and local inference providers, the spec introduces unified standards for agentic loops, reasoning visibility, and internal versus external tool execution. It aims to enable developers to easily switch between proprietary models and open-source models without rewriting integration code."
"The core concepts introduced in the specification are items, tool use, and agentic loop. An item is an atomic unit representing model input, output, tool invocations, or reasoning states, with examples including message, function_call, and reasoning types. Items are extensible, allowing providers to emit custom types beyond the specification. One notable item type is reasoning, which exposes model thought processes in a provider-controlled manner."
Open Responses defines an open specification to standardize agentic AI workflows and reduce API fragmentation across providers. The specification formalizes items, tool use, and agentic loop concepts to manage multi-step workflows involving repeated cycles of reasoning, tool invocation, and reflection. Items represent atomic units such as messages, function_call, and reasoning, and are extensible to permit provider-defined types. Reasoning items can contain raw reasoning, protected content, or summaries to balance transparency with provider control. The spec distinguishes internal and external tools to clarify where orchestration executes, supports multimodal inputs, streaming events, and cross-provider tool calls, and enables providers to return final results in a single API request.
Read at InfoQ
Unable to calculate read time
Collection
[
|
...
]