David Bridges
Jack Dorsey’s innovative company, Block, has launched its own open-source AI agent designed to revolutionize how users interact with technology. This advanced tool, known as “Goose,” empowers users to accomplish various tasks by leveraging popular large language models. The introduction of Goose marks a significant step in integrating artificial intelligence into everyday workflows, making it easier for individuals to harness the full potential of AI in their projects.
According to Block, “Goose serves as a highly capable assistant, prepared to take your instructions and execute tasks on your behalf.” This AI agent can autonomously perform engineering tasks, such as identifying bugs in code or implementing necessary modifications. This capability not only enhances productivity but also alleviates the burden on developers, allowing them to focus on more complex and creative problem-solving.
Users have the flexibility to configure Goose to operate using their preferred large language model (LLM). It supports a variety of models including Anthropic, Gemini, and OpenAI, with the company highlighting that it “functions optimally” with Anthropic’s Claude 3.5 Sonnet and OpenAI’s o1 model. Additionally, Goose is compatible with a range of extensions, enabling seamless integration with popular developer tools such as GitHub and Google Drive, thus streamlining workflow and enhancing user experience.
Block is widely recognized for its financial applications, including Square and Cash App, alongside the music streaming platform Tidal, which it acquired in 2021. While these sectors might not be the first that come to mind when discussing AI development, it’s important to note that Block’s founder, Jack Dorsey, has long been a proponent of open-source software. The company also envisions Goose evolving beyond engineering applications into “non-engineering use cases.” Block engineer Brad Axen shared with ZDNET that they foresee more “creative” applications for Goose, such as music generation, showcasing the versatile potential of this AI agent.
Daniel Mercer
