Photo by Editor | Chat GPT
. Introduction
Sometimes it feels like agent AI is the only AI who has taken an impro -class and will no longer stop making his own decisions. Trying to describe the agent AI more accurately can feel like someone who has never heard of music. This is partial autonomy, partial orchestration, and 100 % guarantee that you ask who is really playing the show.
Well, now the agent does not need to be confused by AI. This videoRecently recorded from ODSC Talk and is widely available by its creators, it is a comprehensive Four -hour workshop on Agentk AI engineeringBy hosting June June June YouTube Channel and Super Data Science Podcast, and Edward DonorCo -Founder and CTO.
The video has been diveled Development of definitions, design principles, and AI agentsStress unprecedented opportunities to get business costs from AI applications using agent workflows, 2025 and beyond. It covers numerous framework and practical applications, showing how large language models (LLM) output can control complex workflows and achieve autonomy in tasks. Instructors highlight the possibility of rapid progress in LLM capabilities and enhancing or making the business process fully automatically.
Emphasizes the workshop Hand over nature With the contents, along with Gut Hub Ripozetry With all code to copy and experience for viewers. Teachers often emphasize the importance of fielding with the field with rapid evolution and agentc projects to ensure success.
. What has been covered?
The more specific titles contained in the video are:
- Explaining agents: The video describes programs to AI agents where the LLM controls the complex work flow, emphasizes independence and distinguishes between easy predefined workflows and dynamic agents.
- A case for Agent AI: It highlights the extraordinary opportunity to get business value from the agent workflow in 2025, when the rapid improvement of LLM and when the last examination of humanity (HLE) is used within the agent framework on their dramatic effects on benchmarks.
- Basic elements: Basic concepts such as tools (LLM performing actions) are defined, as well as unexpected and cost -like, with hereditary risks, and monitoring and protective strategies to reduce them.
- The implications of Agentk AI: The workshop also focuses on the implications of Agent AI, including a change in manpower for future proofing careers in data science, which emphasizes skills such as multi -agent orchestration and basic knowledge.
Agent AI framework, agent revolution tools, include.
- Model Context Protocol (MCP): An open source standard protocol to connect agents with data sources and tools, is often attributed to ‘USBC for agent applications’.
- Open AI Agent SD: A lightweight, easy and flexible framework, which is used for deep research
- Crew: A heavy -weight framework is specially designed for multi -agent system
- Like more complicated framework Lang graph And Microsoft autojin Is also mentioned
Finally, the video includes coding exercises:
- Practical demonstrations regenerate the deepest research functionality of Open A using the SD of Open AI agents, including showing how agents can perform web searches and prepare reports.
- Disagreeing principles for agent Systems covers five workflow design patterns: instant chain, rooting, harmony, archetyperter worker, and diagnostic optimizer
- The construction of an independent software engineering team with Crewi has been demonstrated, where agents have cooperated to write and test the Code of Azigar and even develop the user interface, highlighting Crooi’s ‘batteries’ features for implementation of the SEF code.
- The final project involves the development of autonomous traders using MCP, showing how agents can access real -time market data, can benefit permanent knowledge graphs, and perform web sources to make commercial decisions.
. Expected Techways
After watching this video, viewers will be able to:
- Understand the basic concepts of AI agents, including their definitions, basic ingredients such as tolls and sovereignty, and compulsive work flow and dynamic agent system.
- Enforce the agent system using the popular framework, such as Openi and Crooi -related people, to set up multi -agent support and take advantage of their unique features, such as structural output or automatic code.
- Agent applications understand and apply the model context protocol (MCP) for diverse tools and smooth integration of resources, including the ability to create simple customs MCP servers.
- Develop practical agent applications, such as entertainment for deep research functionality and the construction of an independent software engineering team and artificial trade agents.
- Identify and reduce the risks associated with the deployment of the agent system, such as the deployment of the agent system by surveillance and guards, such as unexpected and cost management.
If you straighten the Agent AI for you and show you how you can take advantage of how you can take advantage of your AI engineering technology this year and beyond, watch this great video through Jon Crahon and Edward Donor.
Matthew Mayo For,,,,,,,,,, for,, for,,,, for,,,, for,,, for,,,, for,,,, for,,,, for,,, for,,, for,,, for,,, for,,,, for,,, for,,, for,,,, for,,, for,,,, for,,, for,,, for,,,, for,,, for,,, for,,,, for,,, for,,,, for,,, for,,,, for,,, for,,,, for,,, for,,,, for,,,, for,,,, for,,,, for,,,, for,,,, for,,,, for,,, for,,, for,,, for,,, for,,,,, for,,,, for,,,, for,,,, for,, for,.@MattMayo13) Computer science is a graduate diploma in master’s degree and data mining. As the Managing Editor of Kdnuggets & StatologyAnd supporters in the editor Machine specializes in learningMatthew aims to make complex data science concepts accessible. Its professional interests include natural language processing, language models, machine learning algorithms, and the search for emerging AI. He is driven by a mission to democratic knowledge in the data science community. Matthew has been coding since the age of 6.