top of page

Blogs


Agentic AI Architecture: The Foundation of Autonomous Intelligence
What is Agentic AI Architecture? Agentic AI is an advanced framework designed to create intelligent systems that operate autonomously, adapt dynamically, and make data-driven decisions with minimal human intervention. Unlike traditional AI, which follows predefined rules, Agentic AI evolves, continuously refining its strategies and responses based on real-time data and past experiences. At its core, Agentic AI architecture enables AI agents to: Plan & Strategize – Define obje
4 min read


DeepCoder: Unlocking the Power of 14B Parameters with Open-Source Code Generation
DeepCoder is an open-source AI model designed for high-performance code generation, leveraging 14 billion parameters. Developed by UC Berkeley's Agentica team and Together AI, it is fine-tuned using Reinforcement Learning (RL) techniques and provides an innovative approach to training coding models. Training & Data Details DeepCoder was trained over 2.5 weeks on 32 Nvidia A100 GPUs, utilizing a curated dataset of 24,000 verified coding problems. This dataset includes: 7.5K pr
2 min read
bottom of page