Agents

Agent memory is the state an AI agent keeps across steps or sessions, such as scratchpad notes, retrieved facts, user preferences, or task history.

Agents

Agent2Agent, or A2A, is an open protocol from Google for agent-to-agent communication, capability discovery, task management, and artifact exchange.

Agents

Agentic AI refers to AI systems that can plan, call tools, maintain task state, and take multi-step actions toward a goal.

Agent security

Agentjacking is an informal term for hijacking an AI agent's tools, context, or execution path so it performs attacker-directed actions.

AI Concepts

Systems that can operate independently to perform tasks without human intervention.

Agents

A computer use agent is an AI agent that can inspect screenshots and control a desktop or browser with mouse and keyboard actions.

learning methodology

A framework where multiple agents learn and adapt through interaction with each other and the environment.

Artificial Intelligence

Systems composed of multiple interacting intelligent agents.

Machine Learning

A type of machine learning focused on teaching agents to make decisions by maximizing cumulative rewards.

Machine Learning

An approach in reinforcement learning where human feedback is used to shape agent learning and decision-making.

Models

Sarvam 105B is Sarvam AI's flagship open-weight 105B+ MoE reasoning model for Indian-language chat, coding, long-context work, and agents.

AI platforms

Sarvam AI is an India-based sovereign AI platform focused on Indian-language LLMs, speech, translation, document digitization, and enterprise AI agents.

Reinforcement Learning

A learning paradigm where agents learn optimal behaviors through exploration without labeled feedback.