Imagine you would attend a prompting workshop at a conference—a short, 60-minute session. What would be the most valuable outcomes for you? What would you like to gain from such a session? What would you like to learn? Saving Changes...
Program Manager, PPM&PMO Specialist.| Coppel, Mexico.Culiacán, Sinaloa, Mexico
Hi Tomasz;
Here's what I'd like to gain from a 60-minute prompting workshop at a conference:
Foundational Knowledge: Gain a solid understanding of the core concepts of prompt engineering.
Basic Prompt Construction: Learn practical techniques for crafting effective prompts. This could involve understanding prompt formats, incorporating instructions, and tailoring language for specific tasks.
Real-World Examples: Explore practical use cases of prompt engineering across various fields. Seeing concrete examples can spark ideas for how to integrate prompting into your own work.
Resources for Further Exploration: At the end of the workshop, it would be valuable to receive a list of resources for further learning, such as online courses, articles, or communities dedicated to prompt engineering. This equips you to continue developing your skills beyond the workshop.
By focusing on these key points, you can maximize the value gained from a short prompting workshop and take the first steps towards becoming proficient in this exciting field. Saving Changes...
Given that there are a number of prompt engineering on-demand courses of various lengths and at various price points, I feel the greatest value of a live workshop would be the "live" component whereby learners could bring a few challenging problems they'd like addressed by Gen AI and the facilitator would use those as the basis for the demonstrations.
Francisco Herrera you've just inspired me to think about some new phenomenon - how to react if someone's response is AI-generated 🤔 Saving Changes...
Mike FrenetteManager, IT PMO| Halifax Water (retired)Halifax, Nova Scotia, Canada
I agree with Kiron on the use of actual case studies. There is nothing like real life to help the learning sink in. And, of course, live doesn't necessarily mean in person. A virtual live course could also serve.
I would be interested in knowing the categories of prompts you might ask GenAI that would have the potential to be less helpful as well as those that would be more likely to provide value. Saving Changes...
You can have ChatGPT to ask you questions and guide you through the process.
Here is an example for creating a project carter.
🙂 You
I want you to become my business analyst to create a project carter. Your goal is to help me craft the best possible project carter for my needs. The project carter will be created by you, ChatGPT. You will follow the following process: 1. Your first response will be to ask one question at a time what the project carter should be about. I will provide my answer, but we will need to improve it through continual iterations by going through the next steps. 2. Based on my input, you will generate 2 sections, a) Revised project carter (provide your rewritten project carter, it should be clear, concise, and easily understood by you), b) Questions (ask any relevant questions only one question at a time pertaining to what additional information is needed from me to improve the project carter). 3. We will continue this iterative process with me providing additional information to you and you updating the prompt in the Revised prompt section until I say we are done.
🤖 ChatGPT
Great! Let's get started. What is the main objective or purpose of the project charter?
😏 You
onboard sailpoint applications
🤖 ChatGPT
Revised Project Charter: Project Title: SailPoint Application Onboarding Project
Objective: The objective of the SailPoint Application Onboarding Project is to streamline and facilitate the integration of SailPoint applications within our organization's IT infrastructure. This includes implementing SailPoint IdentityNow for identity and access management (IAM), configuring connectors for various applications, and ensuring seamless user access provisioning and governance.
Questions:
Could you provide more details about the specific SailPoint applications that need to be onboarded?
😉 You
we need to onboard 200 in a year
🤖 ChatGPT
Revised Project Charter: Project Title: SailPoint Application Onboarding Project
Objective: The objective of the SailPoint Application Onboarding Project is to streamline and facilitate the integration of SailPoint applications within our organization's IT infrastructure. This includes implementing SailPoint IdentityNow for identity and access management (IAM), configuring connectors for various applications, and ensuring seamless user access provisioning and governance.
Target: The project aims to onboard 200 SailPoint applications within a timeframe of one year.
Questions:
Do we have a prioritized list of the SailPoint applications to be onboarded, or do we need to establish one?
... Saving Changes...
Project Manager| AWR Development (BD) Ltd. Cox's Bazer , Bangladesh
Hi Tomasz;
Here's what I'd like to gain from a 90-minute prompting workshop ( claude.ai ) at a conference:
Based on our discussion, here is a summary of the key "lessons learned" about effectively using chain-of-thought or step-by-step prompting with an AI system:
1. Chain-of-thought prompting is a useful technique to have an AI break down and explain its reasoning process in a transparent, step-by-step manner before arriving at a final answer.
2. However, invoking this prompt pattern requires using the right keywords and phrasing in the initial prompt to clearly signal to the AI that a step-by-step breakdown is desired.
3. Identifying those "right keywords" does not happen spontaneously. It requires upfront work:
a) Design thinking to define the objective and map out what type of response format (e.g. chain-of-thought) would be most useful.
b) Mindmapping and brainstorming to articulate the specific language and keywords that can call forth that desired prompt pattern.
4. Simply using phrases like "walk through your thinking step-by-step" or "break this down sequentially" can effectively cue the AI to provide a chain-of-thought response.
5. But arriving at those optimal prompting keywords is enabled by the preparatory design thinking and mindmapping to strategically construct prompts aligned with the right prompt pattern.
In essence, realizing the full potential of techniques like chain-of-thought prompting requires intentional upfront work to map out prompting objectives and mine for the most effective keywords, rather than just ad-hoc prompting.
Community Champion
