A set of protocols and tools that allow different software applications to communicate with each other. In the context of Asimov, APIs are used to connect with external services like GitHub and Microsoft Teams.
A technique that stores previously processed information to avoid recomputing it, improving performance and reducing latency in subsequent requests.
The amount of text or data that an AI model can process and consider simultaneously when generating responses. Asimov uses expanded context windows to maintain awareness of large codebases.
Security framework that manages digital identities and controls access to resources. In VPC deployments, your team’s IAM roles manage access to Asimov within your cloud infrastructure.
The collective knowledge, experience, and understanding that exists within an organization, including undocumented processes, decisions, and context that team members accumulate over time.
AI systems trained on vast amounts of text data to understand and generate human-like text. Asimov uses LLMs to process and reason about your codebase and documentation.
A protocol that enables AI models to connect with external data sources and tools through standardized interfaces.
Any information that can be used to identify a specific individual, such as names, email addresses, or social security numbers.
A technique that combines information retrieval with text generation, where relevant documents are first retrieved and then used to inform the AI’s response. Asimov uses a different approach with expanded context windows.
A security model that restricts access to resources based on the roles assigned to users within an organization. Asimov implements RBAC with Owner, Admin, and Member roles.
A private network environment within a public cloud infrastructure that provides isolation and security for your resources. Asimov can be deployed within your VPC for enhanced security.
The various systems and platforms that Asimov connects to for gathering information, including GitHub repositories, Microsoft Teams conversations, documentation, and other integrated tools.
A feature that allows you to correct Asimov’s understanding by providing specific information that it will remember and use in future responses.
The process by which Asimov combines information from multiple sources to provide comprehensive answers that connect disparate pieces of information across your engineering ecosystem.
Informal knowledge and insights that exist within development teams, often shared through conversations, chat messages, and discussions rather than formal documentation.