BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/New_York BEGIN:DAYLIGHT DTSTART:20260308T030000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:EDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20261101T010000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:EST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20260725T225247Z UID:E046234B-6606-4596-A92B-B5A98B9007AF DTSTART;TZID=America/New_York:20261003T133000 DTEND;TZID=America/New_York:20261024T163000 DESCRIPTION:Oct 3 through Oct 24\, 2026. Four Saturdays 1:30-4:30pm (10/3\, 10/10\, 10/17\, 10/24).\n\nThe IEEE North Jersey Section Communications S ociety Chapter is offering a course entitled\n"Agents and Agentic Workflow s: A Hands-On Introduction".\n\nThis four-week introductory course in Agen ts designed for a technical audience\nwith no prior specialization in AI o r machine learning. It provides a practical\,\nhands-on approach to unders tanding how Agent Workflows operate and how they can be applied across tas ks.\n\nAgents are autonomous software systems that use a large language mo del in order to perceive their environment\, make decisions\, and take act ions toward a specific goal. Unlike standard chatbots that just answer que stions\, agents can reason\, plan and use external tools independently. Th is course is a four-week introduction to building agent-based applications designed for a general technical audience with no prior specialization in AI or machine learning.\n\nEach week combines a lecture with interactive demos and assignments to reinforce learning through real-world use cases. It provides a practical\, hands-on approach to implementing agentic workfl ows using the LangChain platform.\n\nThe IEEE North Jersey Section's Commu nications Society Chapter can arrange for providing IEEE CEUs - Continuing Education Units (for a $5 charge) upon completion of the course. Course p rices: $75 for Undergrad/Grad/Life/ComSoc members\, $100 for IEEE members\ , $150 for non-IEEE members. If paying by check\, make payee out to "IEEE North Jersey Section".\n\nCo-sponsored by: Education Committee\n\nSpeaker( s): Thomas Long\, \n\nAgenda: \nAgenda: The primary objective of this cour se is to provide students with an understanding of Agents\, tools and tech niques used\, the wide variety of applications\, and an Agentic future.\nT he material covered includes an introduction to the concepts and how to bu ild applications using these concepts. On the completion of the course\, s tudents will learn:\n\nWeek 1: Generative AI Agents and Autonomous Workflo ws\nTheme: Overview of AI agents\, their architecture\, and how they orche strate autonomous tasks using LLSs.\nOutline:\n-Whare are AI agents ?\n-Re view of important LLM concepts\n-LLMs as the brains of agents\n-Overview o f how agents use tools\, memory\, and planning\n-Introduction to LangChain \n\nWeek 2: Tools\nTheme: Empowering agents with external tools\nOutline:\ n-Tools are the callable functions that allow an LLM to do something in th e "real world"\n-Customize the capabilities of the LLM with external tools \n-Creating tools in LangChain: name\, description\, arguments\n-The agent -tool loop and execution\n-Built-in tools (harness) vs. custom tool creati on\n-Subagents as tools\n-Error handling\n\nWeek 3: Model Context Protocol \nTheme: Connecting agents to proprietary data sources and systems.\nOutli ne:\n-MCP is a standardized way for agents to securely access proprietary databases and APIs\n-Client-server architectures: agent\, client\, server\ n-Moving beyond tools: resources (data streams) and prompts (templates gen erated by the server)\n-Security issues: client-server architecture allows controlled access to sensitive data\n\nWeek 4: Skills\nTheme: Step-by-ste p procedures for domain specific tasks\nOutline:\n-Skills encode workflow\ , judgment\, and step-by-step reasoning\n-SKILL.md files\n-Progressive dis closure: availability of skills based on context or user needs\n-Condition al loading: load only the right procedure at the right time to avoid conte xt bloat\n-Reusability: the same skill format can be used across multiple projects\n\nTechnical Requirements :\n\nAny coding demos in this course wi ll use the Python programming language and will be distributed in the form of Colab notebooks. Since Colab is a cloud-based platform\, participants will not need to install any software locally on their own devices.\n\nThe main platform used during this course will be LangChain\, an open-source framework for building agents. At the heart of any agentic workflow is a L arge Language Model. This course will specifically demonstrate how to inco rporate Gemini into LangChain agents. However\, LangChain treats the LLM a s a swappable component of the workflow. Participants with access to other LLMs\, such as GPM or Claude\, are welcome to incorporate those models in stead.\n\nBasic programming skills and some familiarity with the Python la nguage are assumed.\nStudents are expected to be able to bring a laptop in order to use Google Colab Notebooks.\n\nThe course is intended to be subd ivided into 4 sessions\, each three hours long for a total of 12 course ho urs. Each lecture is further subdivided into lecture\, guided and independ ent project based exercises to build experience with hands-on techniques. CEUs will be made available.\n\nThis course will be held at FDU - Teaneck\ , NJ campus. Checks should NOT be mailed to this address. Can physically b ring (preferred) checks in person on the first day or use online payments at registration. Email the organizer for any questions about course\, regi stration\, or other issues.\n\nRoom: Room 205\, Bldg: Becton Building \, F DU Metropolitan Campus\, 960 River Road\, Teaneck\, New Jersey\, United St ates\, 07666 LOCATION:Room: Room 205\, Bldg: Becton Building \, FDU Metropolitan Campus\ , 960 River Road\, Teaneck\, New Jersey\, United States\, 07666 ORGANIZER:a.j.patel@ieee.org SEQUENCE:61 SUMMARY:Agents and Agentic Workflows: A Hands-On Introduction URL;VALUE=URI:https://events.vtools.ieee.org/m/568675 X-ALT-DESC:Description: <br /><p>Oct 3 through Oct 24\, 2026. Four Saturday s 1:30-4:30pm (10/3\, 10/10\, 10/17\, 10/24).</p>\n<p>The IEEE North Jerse y Section Communications Society Chapter is offering a course entitled <br >"Agents and Agentic Workflows:&nbsp\; A Hands-On Introduction".&nbsp\;</p >\n<p>This four-week introductory course in Agents designed for a technica l audience&nbsp\;<br>with no prior specialization in AI or machine learnin g. It provides a practical\,&nbsp\;<br>hands-on approach to understanding how Agent Workflows operate and how they can be applied across tasks.</p>\ n<p>Agents are autonomous software systems that use a large language model in order to perceive their environment\, make decisions\, and take action s toward a specific goal.&nbsp\; Unlike standard chatbots that just answer questions\, agents can reason\, plan and use external tools independently .&nbsp\; This course is a four-week introduction to building agent-based a pplications designed for a general technical audience with no prior specia lization in AI or machine learning.</p>\n<p>Each week combines a lecture w ith interactive demos and assignments to reinforce learning through real-w orld use cases. It provides a practical\, hands-on approach to implementin g agentic workflows using the LangChain platform.</p>\n<p>The IEEE North J ersey Section's Communications Society Chapter can arrange for providing I EEE CEUs - Continuing Education Units (for a $5 charge) upon completion of the course.&nbsp\; Course prices: $75 for Undergrad/Grad/Life/ComSoc memb ers\, $100 for IEEE members\, $150 for non-IEEE members.&nbsp\; If paying by check\, make payee out to "IEEE North Jersey Section".</p><br /><br />A genda: <br /><p>Agenda: The primary objective of this course is to provide students with an understanding of Agents\,&nbsp\;tools and techniques use d\, the wide variety of applications\, and an Agentic future.<br>The mater ial covered includes an introduction to the concepts and how to build appl ications using these concepts. &nbsp\;On the completion of the course\, st udents will learn:</p>\n<p>Week 1: Generative AI Agents and Autonomous Wor kflows<br>Theme: Overview of AI agents\, their architecture\, and how they orchestrate autonomous tasks using LLSs.<br>Outline:<br>-Whare are AI age nts ?<br>-Review of important LLM concepts<br>-LLMs as the brains of agent s<br>-Overview of how agents use tools\, memory\, and planning<br>-Introdu ction to LangChain</p>\n<p>Week 2: Tools<br>Theme: Empowering agents with external tools<br>Outline:<br>-Tools are the callable functions that allow an LLM to do something in the "real world"<br>-Customize the capabilities of the LLM with external tools<br>-Creating tools in LangChain:&nbsp\; na me\, description\, arguments<br>-The agent-tool loop and execution<br>-Bui lt-in tools (harness) vs. custom tool creation<br>-Subagents as tools<br>- Error handling</p>\n<p>Week 3: Model Context Protocol<br>Theme: Connecting agents to proprietary data sources and systems.<br>Outline:<br>-MCP is a standardized way for agents to securely access proprietary databases and A PIs<br>-Client-server architectures:&nbsp\; agent\, client\, server<br>-Mo ving beyond tools:&nbsp\; resources (data streams) and prompts (templates generated by the server)<br>-Security issues:&nbsp\; client-server archite cture allows controlled access to sensitive data</p>\n<p>Week 4: Skills<br >Theme: Step-by-step procedures for domain specific tasks<br>Outline:<br>- Skills encode workflow\, judgment\, and step-by-step reasoning<br>-SKILL.m d files<br>-Progressive disclosure:&nbsp\; availability of skills based on context or user needs<br>-Conditional loading: load only the right proced ure at the right time to avoid context bloat<br>-Reusability:&nbsp\; the s ame skill format can be used across multiple projects</p>\n<p>Technical Re quirements :</p>\n<p>Any coding demos in this course will use the Python p rogramming language and will be distributed in the form of Colab notebooks .&nbsp\; Since Colab is a cloud-based platform\, participants will not nee d to install any software locally on their own devices.</p>\n<p>The main p latform used during this course will be LangChain\, an open-source framewo rk for building agents.&nbsp\; At the heart of any agentic workflow is a L arge Language Model.&nbsp\; This course will specifically demonstrate how to incorporate Gemini into LangChain agents.&nbsp\; However\, LangChain tr eats the LLM as a swappable component of the workflow.&nbsp\; Participants with access to other LLMs\, such as GPM or Claude\, are welcome to incorp orate those models instead.</p>\n<p>Basic programming skills and some fami liarity with the Python language are assumed.<br>Students are expected to be able to bring a laptop in order to use Google Colab Notebooks.</p>\n<p> The course is intended to be subdivided into 4 sessions\, each three hours long for a total of 12&nbsp\;course hours. Each lecture is further subdiv ided into lecture\, guided and independent project based exercises to buil d experience with hands-on techniques.&nbsp\; CEUs will be made available. </p>\n<p>This course will be held at FDU - Teaneck\, NJ campus.&nbsp\; Che cks should NOT be mailed to this address. Can physically bring (preferred) checks in person on the first day or use online payments at registration. Email the organizer&nbsp\;for any questions about course\, registration\, or other issues.</p> END:VEVENT END:VCALENDAR