BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:Asia/Kolkata BEGIN:STANDARD DTSTART:19451014T230000 TZOFFSETFROM:+0630 TZOFFSETTO:+0530 TZNAME:IST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20251231T170455Z UID:9D66BE4B-34F2-4179-BBD1-AB3B9793317A DTSTART;TZID=Asia/Kolkata:20251120T134500 DTEND;TZID=Asia/Kolkata:20251120T160000 DESCRIPTION:The session began with a warm welcome and sincere greetings to all participants by the IEEE Sensors Council\, which clearly explained the purpose and objectives of organizing HelloGPT. The club highlighted the i mportance of gaining awareness of emerging AI technologies\, encouraging h ands-on learning\, and enabling participants to develop the skills require d to interact effectively with AI systems.\n\nZulqarnain Mohammed\, Chairp erson\, opened the session with a brief introduction\, outlining the overa ll structure of the program and emphasizing the key learning outcomes. Thi s introduction helped participants understand the goals of each segment an d prepared them for active engagement throughout the session.\n\nThe first segment was presented by Samia Rahman\, Web Master\, who delivered a comp rehensive introduction to Artificial Intelligence (AI) and Large Language Models (LLMs) such as ChatGPT\, Gemini\, and Claude. She explained the con cept of AI and how LLMs are trained on large datasets to identify patterns and generate coherent\, contextually relevant text. The session clearly d istinguished between training\, which involves teaching the model using da ta\, and prompting\, which focuses on giving instructions to obtain specif ic outputs. Samia also discussed the role of prompt engineers in real-worl d applications and demonstrated how natural language is converted into mac hine-understandable instructions\, effectively connecting theoretical conc epts with practical use cases.\n\nThe second segment\, conducted by Zubair Ahmed Khan\, Joint Secretary\, focused on the fundamentals of prompt engi neering. He explained what a prompt is and emphasized how well-structured instructions can greatly improve the accuracy and relevance of AI-generate d responses. He introduced the anatomy of an effective prompt\, highlighti ng four essential components: Context\, Task\, Constraints\, and Examples. He stressed the importance of clarity\, specificity\, and aligning the pr ompt with the intended tone\, role\, and audience. To reinforce these conc epts\, he demonstrated the difference in outcomes between a well-crafted p rompt and a poorly written one.\n\nThe third segment was delivered by Moha mmed Omer\, Execom Member\, who discussed various prompt types and advance d prompting techniques. He explained how role-based prompts assign specifi c personas to guide AI behavior\, while instruction-based prompts provide clear\, task-focused directions. He highlighted the effectiveness of examp le-based prompts in maintaining tone and style and demonstrated chain-of-t hought prompting to encourage step-by-step reasoning. Additionally\, he in troduced zero-shot and few-shot prompting\, illustrating how the inclusion or absence of examples affects accuracy. Through practical demonstrations \, he showed how each technique influences AI responses and supports diver se user goals.\n\nThe hands-on segment\, facilitated by Chairperson Zulqar nain Mohammed\, actively engaged participants through a series of interact ive\, prompt-based activities. The session began with a CTCE rewriting exe rcise\, where participants improved poorly structured prompts by incorpora ting Context\, Task\, Constraints\, and Examples to achieve clearer and mo re precise AI outputs. This was followed by a creative prompt challenge in which participants composed a three-line horror story containing specific elements\, such as a door and a clock\, demonstrating how constraints can guide creativity. The final activity introduced prompt chaining\, allowin g participants to create multi-step prompts and observe how sequential ins tructions enhance coherence and output quality. These practical activities provided participants with first-hand experience in designing\, refining\ , and optimizing prompts for real-world applications.\n\nThe fifth and fin al segment was presented by Sara Farzana\, Execom Member\, who introduced the concept of Reverse Prompt Engineering. She explained that this techniq ue involves analyzing AI-generated outputs to identify the underlying inst ructions\, structure\, and reasoning patterns that influenced them. Sara d iscussed its practical applications in improving prompt quality\, increasi ng model accuracy\, and gaining a deeper understanding of how AI interpret s natural language. She also demonstrated clear examples of reverse prompt ing\, showing participants how to break down an output\, identify missing or implied context\, and reconstruct a more effective prompt based on thos e insights.\n\nThe session concluded with an engaging quiz conducted by th e Chairperson\, which assessed participants’ understanding of the topics covered and provided an energetic and interactive conclusion to the overa ll learning experience.\n\nAgenda: \nThe main objective of the HelloGPT ev ent was to provide participants with a clear understanding of Artificial I ntelligence and Large Language Models\, and to help them learn how to inte ract effectively with AI tools. The event aimed to build practical skills in prompt engineering through hands-on activities\, enabling participants to create accurate\, meaningful\, and high-quality AI responses while enco uraging curiosity and confidence in using modern AI technologies.\n\nRoom: Seminar Hall\, Bldg: Block 4\, Mount Pleasant\, 8-2-249\, Rd Number 3\, V enkateshwara Hills\, Banjara Hills\, Hyderabad\, Telangana 500082\, Hydera bad\, Telengana\, India\, 500034 LOCATION:Room: Seminar Hall\, Bldg: Block 4\, Mount Pleasant\, 8-2-249\, Rd Number 3\, Venkateshwara Hills\, Banjara Hills\, Hyderabad\, Telangana 50 0082\, Hyderabad\, Telengana\, India\, 500034 ORGANIZER:160422735072@mjcollege.ac.in SEQUENCE:49 SUMMARY:Hello Gpt URL;VALUE=URI:https://events.vtools.ieee.org/m/525743 X-ALT-DESC:Description: <br /><div class="flex flex-col text-sm">\n<article class="text-token-text-primary w-full focus:outline-none [--shadow-height :45px] has-data-writing-block:pointer-events-none has-data-writing-block:- mt-(--shadow-height) has-data-writing-block:pt-(--shadow-height) [&amp\;:h as([data-writing-block])&gt\;*]:pointer-events-auto [content-visibility:au to] supports-[content-visibility:auto]:[contain-intrinsic-size:auto_100lvh ] scroll-mt-[calc(var(--header-height)+min(200px\,max(70px\,20svh)))]" dir ="auto" tabindex="-1" data-turn-id="request-WEB:f6e71863-2ddb-4c2a-bcd0-71 4987a3f94c-0" data-testid="conversation-turn-2" data-scroll-anchor="true" data-turn="assistant">\n<div class="text-base my-auto mx-auto pb-10 [--thr ead-content-margin:--spacing(4)] @w-sm/main:[--thread-content-margin:--spa cing(6)] @w-lg/main:[--thread-content-margin:--spacing(16)] px-(--thread-c ontent-margin)">\n<div class="[--thread-content-max-width:40rem] @w-lg/mai n:[--thread-content-max-width:48rem] mx-auto max-w-(--thread-content-max-w idth) flex-1 group/turn-messages focus-visible:outline-hidden relative fle x w-full min-w-0 flex-col agent-turn" tabindex="-1">\n<div class="flex max -w-full flex-col grow">\n<div class="min-h-8 text-message relative flex w- full flex-col items-end gap-2 text-start break-words whitespace-normal [.t ext-message+&amp\;]:mt-1" dir="auto" data-message-author-role="assistant" data-message-id="4cc41e8e-be77-457b-b14c-9dfc72d9f001" data-message-model- slug="gpt-5-2">\n<div class="flex w-full flex-col gap-1 empty:hidden first :pt-[1px]">\n<div class="markdown prose dark:prose-invert w-full break-wor ds dark markdown-new-styling">\n<p data-start="0" data-end="398">The sessi on began with a warm welcome and sincere greetings to all participants by the IEEE Sensors Council\, which clearly explained the purpose and objecti ves of organizing HelloGPT. The club highlighted the importance of gaining awareness of emerging AI technologies\, encouraging hands-on learning\, a nd enabling participants to develop the skills required to interact effect ively with AI systems.</p>\n<p data-start="400" data-end="708">Zulqarnain Mohammed\, Chairperson\, opened the session with a brief introduction\, ou tlining the overall structure of the program and emphasizing the key learn ing outcomes. This introduction helped participants understand the goals o f each segment and prepared them for active engagement throughout the sess ion.</p>\n<p data-start="710" data-end="1480">The first segment was presen ted by Samia Rahman\, Web Master\, who delivered a comprehensive introduct ion to Artificial Intelligence (AI) and Large Language Models (LLMs) such as ChatGPT\, Gemini\, and Claude. She explained the concept of AI and how LLMs are trained on large datasets to identify patterns and generate coher ent\, contextually relevant text. The session clearly distinguished betwee n training\, which involves teaching the model using data\, and prompting\ , which focuses on giving instructions to obtain specific outputs. Samia a lso discussed the role of prompt engineers in real-world applications and demonstrated how natural language is converted into machine-understandable instructions\, effectively connecting theoretical concepts with practical use cases.</p>\n<p data-start="1482" data-end="2133">The second segment\, conducted by Zubair Ahmed Khan\, Joint Secretary\, focused on the fundame ntals of prompt engineering. He explained what a prompt is and emphasized how well-structured instructions can greatly improve the accuracy and rele vance of AI-generated responses. He introduced the anatomy of an effective prompt\, highlighting four essential components: Context\, Task\, Constra ints\, and Examples. He stressed the importance of clarity\, specificity\, and aligning the prompt with the intended tone\, role\, and audience. To reinforce these concepts\, he demonstrated the difference in outcomes betw een a well-crafted prompt and a poorly written one.</p>\n<p data-start="21 35" data-end="2847">The third segment was delivered by Mohammed Omer\, Exe com Member\, who discussed various prompt types and advanced prompting tec hniques. He explained how role-based prompts assign specific personas to g uide AI behavior\, while instruction-based prompts provide clear\, task-fo cused directions. He highlighted the effectiveness of example-based prompt s in maintaining tone and style and demonstrated chain-of-thought promptin g to encourage step-by-step reasoning. Additionally\, he introduced zero-s hot and few-shot prompting\, illustrating how the inclusion or absence of examples affects accuracy. Through practical demonstrations\, he showed ho w each technique influences AI responses and supports diverse user goals.< /p>\n<p data-start="2849" data-end="3760">The hands-on segment\, facilitat ed by Chairperson Zulqarnain Mohammed\, actively engaged participants thro ugh a series of interactive\, prompt-based activities. The session began w ith a CTCE rewriting exercise\, where participants improved poorly structu red prompts by incorporating Context\, Task\, Constraints\, and Examples t o achieve clearer and more precise AI outputs. This was followed by a crea tive prompt challenge in which participants composed a three-line horror s tory containing specific elements\, such as a door and a clock\, demonstra ting how constraints can guide creativity. The final activity introduced p rompt chaining\, allowing participants to create multi-step prompts and ob serve how sequential instructions enhance coherence and output quality. Th ese practical activities provided participants with first-hand experience in designing\, refining\, and optimizing prompts for real-world applicatio ns.</p>\n<p data-start="3762" data-end="4447">The fifth and final segment was presented by Sara Farzana\, Execom Member\, who introduced the concept of Reverse Prompt Engineering. She explained that this technique involves analyzing AI-generated outputs to identify the underlying instructions\, structure\, and reasoning patterns that influenced them. Sara discussed it s practical applications in improving prompt quality\, increasing model ac curacy\, and gaining a deeper understanding of how AI interprets natural l anguage. She also demonstrated clear examples of reverse prompting\, showi ng participants how to break down an output\, identify missing or implied context\, and reconstruct a more effective prompt based on those insights. </p>\n<p data-start="4449" data-end="4676" data-is-last-node="" data-is-on ly-node="">The session concluded with an engaging quiz conducted by the Ch airperson\, which assessed participants&rsquo\; understanding of the topic s covered and provided an energetic and interactive conclusion to the over all learning experience.</p>\n<p data-start="4449" data-end="4676" data-is -last-node="" data-is-only-node="">&nbsp\;</p>\n<p data-start="4449" data- end="4676" data-is-last-node="" data-is-only-node=""><img src="https://eve nts.vtools.ieee.org/vtools_ui/media/display/9fe99c0b-19c4-4adc-9964-1c6072 7990a9" width="457" height="343"><img src="https://events.vtools.ieee.org/ vtools_ui/media/display/6448cf2b-0140-4b78-81f6-1a0ebbc4733e" width="255" height="341"><img src="https://events.vtools.ieee.org/vtools_ui/media/disp lay/809ebc03-a47f-4955-bef5-1b7986c97aa6" width="256" height="341"><img sr c="https://events.vtools.ieee.org/vtools_ui/media/display/dc1c1d3a-5114-4a 2e-8cd4-e5d892e10c79" width="537" height="403"></p>\n</div>\n</div>\n</div >\n</div>\n<div class="z-0 flex min-h-[46px] justify-start">&nbsp\;</div>\ n</div>\n</div>\n</article>\n</div>\n<div class="pointer-events-none h-px w-px absolute bottom-0" aria-hidden="true" data-edge="true">&nbsp\;</div>< br /><br />Agenda: <br /><div class="text-base my-auto mx-auto pb-10 [--th read-content-margin:--spacing(4)] @w-sm/main:[--thread-content-margin:--sp acing(6)] @w-lg/main:[--thread-content-margin:--spacing(16)] px-(--thread- content-margin)">\n<div class="[--thread-content-max-width:40rem] @w-lg/ma in:[--thread-content-max-width:48rem] mx-auto max-w-(--thread-content-max- width) flex-1 group/turn-messages focus-visible:outline-hidden relative fl ex w-full min-w-0 flex-col agent-turn" tabindex="-1">\n<div class="flex ma x-w-full flex-col grow">\n<div class="min-h-8 text-message relative flex w -full flex-col items-end gap-2 text-start break-words whitespace-normal [. text-message+&amp\;]:mt-1" dir="auto" data-message-author-role="assistant" data-message-id="bd5f5e56-bf8b-46d8-9eca-6bfb8cff27c9" data-message-model -slug="gpt-5-2">\n<div class="flex w-full flex-col gap-1 empty:hidden firs t:pt-[1px]">\n<div class="markdown prose dark:prose-invert w-full break-wo rds dark markdown-new-styling">\n<p data-start="0" data-end="463" data-is- last-node="" data-is-only-node="">The main objective of the HelloGPT event was to provide participants with a clear understanding of Artificial Inte lligence and Large Language Models\, and to help them learn how to interac t effectively with AI tools. The event aimed to build practical skills in prompt engineering through hands-on activities\, enabling participants to create accurate\, meaningful\, and high-quality AI responses while encoura ging curiosity and confidence in using modern AI technologies.</p>\n</div> \n</div>\n</div>\n</div>\n</div>\n</div> END:VEVENT END:VCALENDAR