agentic systems
AI systems that act autonomously by reasoning, using tools, accessing data, and spawning sub-agents to accomplish tasks.
As defined in Lex Fridman Podcast #494 - Jensen Huang
Other definitions
AI systems designed to take actions in the world to accomplish goals, as opposed to systems that only generate text or classify information.
Yann LeCun Says LLMs Have 2 Years Left…
Where it comes up · 7
- Architecting Agent Memory: Principles, Patterns, and Best Practices — Richmond Alake, MongoDB4 claims
- Martin Casado - Entering Uncharted AI Territory - [Invest Like the Best, EP.381]2 claims
- Lex Fridman Podcast #494 - Jensen Huang2 claims
- I Built My Own AI Memory by Talking to Claude. It Did 80% Itself.1 claim
- The future of intelligence | Demis Hassabis (Co-founder and CEO of DeepMind)1 claim
- Ex-Google CEO: What Artificial Superintelligence Will Actually Look Like w/ Eric Schmidt & Dave B1 claim
- Yann LeCun: Special Lecture on AI and World Models1 claim
Most important claims · 10 of 12Search all claims for “agentic systems” →
- Nature has created the most effective form of intelligence available today (the human brain), and AI architects should look inward to understand biological memory and intelligence systems when building agentic systems.Architecting Agent Memory: Principles, Patterns, and Best Practices — Richmond Alake, MongoDB
- The notion that AI will destroy software and make tools unnecessary is wrong; by analogy, a humanoid robot in your house would use your existing microwave (reading its manual to become an expert) rather than beaming microwaves from its fingers, so future digital workers will access files, do research, and use tools—the properties exhibited by OpenClaw and agentic systems.Lex Fridman Podcast #494 - Jensen Huang
- Casado is technically bearish on agents because memory, correctness over long horizons, and planning are unsolved, and it is not clear that LLM advances carry over to fully automated agentic systems.Martin Casado - Entering Uncharted AI Territory - [Invest Like the Best, EP.381]
- MongoDB acquired Voyage AI earlier in the year to acquire the best embedding models in the market, including text, multimodal, and re-ranker models, enabling MongoDB to reduce AI hallucination in RAG and agentic systems.Architecting Agent Memory: Principles, Patterns, and Best Practices — Richmond Alake, MongoDB
- Agentic systems—AI agents connected to solve business processes, government processes, and so forth—will be adopted fastest in companies and countries with lots of money and high time-latency costs, and slowest in government which has no innovation incentive and functions as a job program.Ex-Google CEO: What Artificial Superintelligence Will Actually Look Like w/ Eric Schmidt & Dave B
- LLMs perform autoregressive token prediction by generating probability distributions over a finite token dictionary and sampling from them sequentially, which is fundamentally different from the optimization-based inference required for planning with world models.Yann LeCun: Special Lecture on AI and World Models
- Progress in large language models, multimodal models, agentic AI, drug discovery acceleration, and robotics integration represent the major shifts in AI over the past year, moving beyond large language models as the center of gravity toward agentic systems.The future of intelligence | Demis Hassabis (Co-founder and CEO of DeepMind)
- An agent is a system with a control loop and state: it takes a high-level objective, performs multiple steps while maintaining state, and uses a feedback loop to decide each next step, a combination Casado thinks has not been solved.Martin Casado - Entering Uncharted AI Territory - [Invest Like the Best, EP.381]
- Agentic systems can do three things—access sensitive information, execute code, and communicate externally—and you can keep things safe by granting any two of those three capabilities at a time but never all three simultaneously, combined with access control and a policy engine.Lex Fridman Podcast #494 - Jensen Huang
- In February 2026, the key problem with AI agents was that they forgot user context, didn't listen to preferences, and chats would restart cold, meaning users had to re-explain their preferences each time.I Built My Own AI Memory by Talking to Claude. It Did 80% Itself.