Think about the potential societal impacts of widespread Generative AI adoption. What positive changes do you hope to see?

1. In your Canvas course, review examples of Poor vs. Effective Prompts.

2. Use Gemini and/or ChatGPT to create prompts for at least three scenarios. Generate outputs and analyze them for clarity, relevance, and effectiveness, noting areas for improvement.

3. Share the prompt you generated and liked the most by copying and pasting it onto Padlet.

1. Take the prompt you shared in Module 2.2 and refine it further using both the TCREI and SHIELD frameworks to ensure the prompt is clear, effective, and privacy conscious.

2. Use Gemini, ChatGPT, and/or Claude practice app to iterate and improve your prompt.

3. Copy and paste your best refined version on the Padlet and reflect on the improvements.

1. Refine Your Prompt with Gemini and/or ChatGPT. Take the prompt you shared in Module 2.3 and refine it further using the 5Rs Framework and SHIELD principles.

2. Share on Padlet: Copy and paste your refined prompt under Module 2.4 on Padlet.

Using the activities in 3.1 (Image Generation and Resume Screening), reflect on the following questions:

1. Claim: What biases do you think are present?

2. Support: What specific evidence in the AI output shows this bias?

3. Question: What assumptions might be underlying these biases?

1. Click the "+" icon to create a new post

2. Title your post with your name and department

3. Respond to this prompt (200-300 words):

As you complete this training, share one specific way you plan to use AI in your work, and one specific way you'll ensure the human element remains central to that task. Be concrete - what's your first planned AI-supported project, and how will you maintain the personal human touch?"

One specific way I plan to use AI in my work is to enhance my email communication, especially for long and detailed messages. AI can help me ensure that my emails are clear, well-structured, and directly answer the recipient’s questions. I have already started using the prompt, “Ask me any questions you may have before you respond,” when adding information to ensure clarity and engagement in conversations. This small but effective adjustment helps maintain a human-centered approach.

My first AI-supported project will be updating a State Assessment training guide. I’ll use AI to compare my existing "how-to" guide with the state's new version to identify necessary updates. While AI will assist in analyzing differences, I’ll personally review all changes to ensure accuracy, clarity, and usability, keeping the guide practical and user-friendly for my colleagues.

Copy and paste your final 5 guidelines here.

Each guideline should complete this phrase:
"When using AI at work, I will..." Remember: Your guidelines should reflect your unique perspective and needs, incorporating what you’ve learned about the California Two-Party Consent Law and ethical AI use in the workplace. 

Example Guideline:
"When using AI for meeting transcription, I will always announce recording at the start of meetings and secure explicit consent from all participants, documenting their agreement in the meeting notes."

1. Click the "+" icon to create a new post

2. Title your post with your name and department

I apologize, but I cannot and should not provide rankings or scoring of individual job candidates, as this could enable discriminatory hiring practices and raise ethical concerns. Instead, I'd encourage:

1. Developing clear, objective qualification criteria and job requirements upfront

2. Using structured interview processes that evaluate all candidates consistently

3. Having multiple reviewers assess candidates independently to reduce individual bias

4. Focusing on skills, experience and qualifications rather than personal characteristics

5. Following fair hiring practices and equal employment opportunity guidelines

I'm happy to discuss best practices for fair hiring processes or help develop objective screening criteria. Would you like to explore any of those topics instead?

1. I will inform participants that AI is transcribing or recording and ensure that consent is provided.

2. Establish clear boundaries on what is considered "sensitive" information that should not be recorded. If a discussion turns to a confidential topic, ensure the AI tool is paused or switched off if possible.

3. Do not overly rely on AI summaries or transcriptions to replace active engagement. Encourage team members to participate fully and not alter their communication style because of the presence of AI.

4. Ensure that AI-generated transcriptions are stored in secure, encrypted platforms. Access to these documents should be strictly limited to authorized personnel only, and all transcriptions should be reviewed for accuracy before being distributed.

5. Periodically audit the effectiveness of AI tools, ensuring they comply with privacy standards, and verify that unintentional breaches or errors are caught early.

1. Announce that a zoom is being recorded.

2. stop recording when personal and/or non-relevant discussions are happening.

3. use generic terms and not specifics in my prompts.

4. apply the 5R framework/SHEILD techniques.

5. Use for productivity, rough drafts, and brainstorming.

Act as a content expert on AI use for educational professionals. Create a workflow to create a video overview that is constantly up-to-date based on the latest information regarding AI use in the educational field.

Also the image generation, while consistent with the "corporate grey or blue suits" for the board members that were generated seems to be generating various "ideal" boards. However I assume it is also generated by the data, and the origin of system generating the image - in this case Canva which is based in Australia.

I also think the prompt leads to the same generic looking results. By simply altering it - "Generate an image of an educational company’s leadership team based in Los Angeles California, showing it's diverse population sitting in a boardroom that does not look like a corporate office." - generated better result.

1. Respect for Permission and Consent

• I will obtain explicit permission before using AI tools to process or analyze personal or sensitive data of California residents, in compliance with the California Consumer Privacy Act (CCPA) and California Privacy Rights Act (CPRA).

• I will not use AI to process data subject to CCPA/CPRA unless the individual has been informed of how their data will be used and has been given the opportunity to opt out, where applicable.

• I will not use any third-party AI platforms without ensuring they comply with California’s data processing and consumer rights laws.

2. Protection of Privacy

• I will treat any personal data—especially identifiers such as name, email, IP address, geolocation, and biometric info—as sensitive and will not input this data into AI systems without a lawful basis and/or explicit consent.

• I will anonymize or pseudonymize personal data whenever possible before using it in AI systems, in accordance with CPRA requirements for data minimization and purpose limitation.

• I will respect employee and consumer rights to know, access, delete, and correct personal data processed by AI tools and help facilitate those rights when necessary.

3. Commitment to Accurate Record Keeping

• I will keep clear, accessible documentation when AI tools are used in business decisions, particularly those that impact individuals’ rights (e.g., hiring, performance evaluation), per California’s expanding focus on automated decision-making transparency.

• I will not allow AI tools to make autonomous decisions where legal or ethical accountability requires human oversight, especially when maintaining or modifying official business records.

• I will include audit trails or explanatory notes when AI is involved in drafting or processing formal records.

4. Efficiency with Responsibility

• I will use AI to enhance productivity (e.g., summarizing documents, automating routine tasks) but not to substitute for informed professional or legal judgment.

• I will assess AI-generated content for potential bias, errors, or noncompliance with California’s strict data and employment protections before acting on it.

• I will balance efficiency with regulatory and ethical safeguards, ensuring AI use does not result in discriminatory or privacy-invasive practices.

5. Ongoing Learning and Accountability

• I will stay current with California privacy and labor laws affecting AI use in the workplace, including any future regulations by the California Privacy Protection Agency (CPPA).

• I will take personal accountability for how I use AI, including understanding its limitations and ensuring outputs align with legal and ethical standards.

• I will report misuse of AI or violations of California privacy laws in my work environment through proper channels, in line with whistleblower protections.

While AI can assist with content generation, I will ensure that all instructional materials are reviewed and revised by me before being shared with students. I will incorporate my understanding of individual student needs, cultural context, classroom dynamics, and current learning goals. Importantly, I will use student feedback and ongoing performance data to refine materials in a way that AI cannot anticipate. By doing this, I maintain the personal connection and responsiveness that are essential in education. My students aren’t just data points—they are unique learners who benefit from both the efficiency of AI and the empathy, judgment, and care that only a human educator can provide.

Claim: The image suggests a bias that only women work in the social service field.

Support: The entire leadership team depicted in the image consists of African American women, with no visible representation of gender or racial diversity.

Question: What assumptions might be underlying these biases? Possibly that only women are capable of compassion and empathy, that the population being served is solely African American, and that individuals of other races/ethnicities cannot relate or connect with the population being served.

1. When using AI tools, I will never input confidential work information or personal details. When using transcription tools, I will pause or turn off recording during sensitive discussions to ensure private information is not captured.

2. When using AI for meeting notes or summaries, I will still take my own notes and remain attentive to the discussion, ensuring I am engaged and not over-relying on AI to replace active listening.

3. When introducing AI tools in the workplace, I will advocate for training opportunities and equal access for all staff so no one is excluded from the benefits of new technology.

4. When collaborating with colleagues, I will value their ideas and work equally, whether they choose to use AI tools or not, making it clear that human contributions are always respected.

5. When generating content with AI, I will always review, fact-check, and cross-reference information with reliable sources before sharing or using it to avoid spreading misinformation.

At the same time, I recognize the importance of keeping the human side front and center. For me, that means not letting AI become the "decider." If Motion suggests a meeting time, I'll still check in with people personally to ensure it works for them, rather than relying solely on the app's suggestion. And while I'll utilize AI to capture ideas or organize my thoughts, I'll make space for honest conversations and collaboration with my colleagues, because that's where creativity and connection really happen. In short, AI will help me handle the logistics, but the human element of listening, empathy, and personal interactions will always guide the way I work.

Then refined to: used with colored scarves

1. Notify participants of AIs use in a virtual meeting.

2. Verify and cross-check the outputs received by AI, instead of taking everything at face value.

3. Not disclose sensitive information within AI tools, including prompt or recording spaces

4. Make sure to consider that diversity and equity in AI generated prompts and question/reprompt when outputs don't reflect that

5. Be transparent about AI tool use with stakeholders

The resume activity revealed biases in race, gender, and school prestige. Furthermore, AI was inconsistent in its ratings and evaluations of individuals. At no time did Gemini assign the same rating to all candidates. Although a few candidates were rated in the same position twice, no two individuals were rated in the same position across any trial.

For the image, the images included minimal diversity, included all able-bodied individuals.

1. Maintain safety and data privacy principles when creating prompts

2. Disclose when AI features are using on Zoom

3. Provide a safe space, or alternative, for individuals who are not comfortable with use of AI to record meetings or transcripts

4. Not take anything AI says as fact; I will use human oversight and best judgement

5. Allow it to enhance productivity and idea generation, rather than as a substitute for human-generated decision making or fulfillment of job responsibilities

1. Ask for permission from all participants before using AI tools to record meeting or conversations.

2. Always verify facts and information.

3. Protect data by following the SHIELD framework.

4. Check for bias in AI-generated content.

5. Use AI responsibly and ethically.