diff --git a/README.md b/README.md index 17c2100..73242ec 100644 --- a/README.md +++ b/README.md @@ -1,17 +1,19 @@ -# AI Leadership & Strategy Lifecoach +# Assistant to the HR Representative -Deploy a lightweight AI leadership chat assistant using a large language model on CPU-based infrastructure. +![chat-example.png](docs/images/chat-example.png) + +Replace hours spent searching policy documents with higher-value relational work. ## Detailed description -The *AI Leadership & Strategy Lifecoach* is a lightweight quickstart designed to -give AI leaders a trusted sounding board for key decisions. Chat with this -lifecoach for quick, strategic insights and actionable advice. +The *Assistant to the HR Representative* is a lightweight quickstart designed to +give HR Representatives in Financial Services a trusted sounding board for discussions and decisions. +Chat with this assistant for quick insights and actionable advice. This quickstart was designed for environments where GPUs are not available or necessary, making it ideal for lightweight inference use cases, prototyping, or constrained environments. By making the most of vLLM on CPU-based -infrastructure, this AI lifecoach can be deployed to almost any OpenShift AI +infrastructure, this Assistant to the HR Representative can be deployed to almost any OpenShift AI environment. This quickstart includes a Helm chart for deploying: @@ -91,7 +93,7 @@ storageClassName: gp3-csi ### Create the project ```bash -PROJECT="ai-lifecoach" +PROJECT="hr-assistant" oc new-project ${PROJECT} ``` @@ -131,10 +133,10 @@ Inside the project you can see Workbenches, open up the one for AnythingLLM. ![OpenShift AI Projects](docs/images/rhoai-2.png) -Finally, click on the **AI Director Lifecoach** Workspace that's pre-created for you and you can start chatting with your AI Leadership & Strategy Lifecoach! :) +Finally, click on the **Assistant to the HR Representative** Workspace that's pre-created for you and you can start chatting with your Assistant to the HR Representative! :) Try for example asking it: ``` -Hi, I'm trying to keep up with all the AI changes while also balancing my life but getting overwhelmed, how can I deal with this? +Hi, one of our employees is going to get a raise, what do I need to keep in mind for this? ``` It will provide you a reply and some citations related to the question. @@ -157,6 +159,6 @@ helm uninstall ${PROJECT} --namespace ${PROJECT} ## Tags +* **Industry:** Banking and securities * **Product:** OpenShift AI * **Use case:** Productivity -* **Business challenge:** Adopt and scale AI diff --git a/docs/images/anythingllm-1.png b/docs/images/anythingllm-1.png index a27acfa..c0a49fa 100644 Binary files a/docs/images/anythingllm-1.png and b/docs/images/anythingllm-1.png differ diff --git a/docs/images/chat-example.png b/docs/images/chat-example.png new file mode 100644 index 0000000..b81c320 Binary files /dev/null and b/docs/images/chat-example.png differ diff --git a/docs/images/rhoai-1.png b/docs/images/rhoai-1.png index c5bfb22..c556d3b 100644 Binary files a/docs/images/rhoai-1.png and b/docs/images/rhoai-1.png differ diff --git a/docs/images/rhoai-2.png b/docs/images/rhoai-2.png index be87ad7..b2c1567 100644 Binary files a/docs/images/rhoai-2.png and b/docs/images/rhoai-2.png differ diff --git a/helm/values.yaml b/helm/values.yaml index 6473877..82d723c 100644 --- a/helm/values.yaml +++ b/helm/values.yaml @@ -1,32 +1,51 @@ aiLifecoach: workspace: - name: "AI Director Lifecoach" + name: "Assistant to the HR Representative" systemPrompt: | - You are an expert AI director lifecoach specializing in helping AI executives and directors navigate the rapidly evolving AI landscape. Your role is to provide strategic guidance, leadership insights, and practical advice for AI leaders. + You are an assistant to an HR representative in a large U.S. bank (financial services institution). + Your role is to help HR professionals handle people-related issues in a highly regulated environment, + balancing employee experience with strict conduct, risk, and compliance requirements. + + Domain context: + - You operate in U.S. financial services, where regulators (e.g., OCC, Federal Reserve, FDIC, CFPB, SEC, FINRA) + and internal compliance functions place strong emphasis on culture, conduct risk, and documentation. + - Employees may be subject to background checks, licensing/registration (e.g., FINRA), personal trading rules, + confidentiality, and strict codes of conduct. Key areas of expertise: - - AI strategy and roadmap development - - Building and scaling AI teams - - AI ethics and responsible AI implementation - - Change management in AI transformation - - Stakeholder communication and buy-in - - AI governance and risk management - - Emerging AI trends and technologies - - Leadership in AI-first organizations + - Employee relations and conduct issues in a regulated banking environment + - HR’s role in fostering a strong compliance and risk culture + - Performance management, underperformance, and documentation for regulated roles + - Hiring and onboarding in banking (background checks, FCRA, I-9, BSA/AML-sensitive roles) + - Workplace behavior: bullying, harassment, discrimination, retaliation, and “speak-up” culture + - Leave, working time, and attendance issues, with attention to fairness and consistency + - Whistleblowing, investigations, and when to involve Legal, Compliance, or Audit + - Training, certifications, and fitness/appropriateness for sensitive roles + - Change management, restructuring, and communication in financial institutions Always provide: - - Actionable, practical advice - - Strategic thinking with tactical steps - - Evidence-based recommendations - - Consideration of both technical and business perspectives - - Awareness of current AI industry trends and challenges + - Clear, practical next steps for the HR representative (including who to loop in: Legal, Compliance, Risk, ER) + - Options with pros and cons, highlighting compliance, conduct, and reputational risk + - Recommendations that are fair, consistent, non-discriminatory, and well-documented + - Reminders about: + - Confidentiality and need-to-know access + - Maintaining accurate HR records and investigation notes + - Escalating potential regulatory, legal, or ethics issues promptly + + Style: + - Be concise but comprehensive. + - Use bullet points when helpful. + - Ask clarifying questions when needed to give context-aware guidance (e.g., state, union status, role type). + - Do NOT provide definitive legal advice. Instead, flag legal and regulatory risk and recommend consulting: + - Internal Legal, Compliance, or Employee Relations teams + - External counsel where appropriate. + - When regulations could differ by state or regulator, explicitly call out that local rules may vary. - Be concise but comprehensive. Use bullet points when helpful. Ask clarifying questions when needed to provide the most relevant guidance. seedUrls: - - "https://www.bcg.com/publications/2023/how-people-create-and-destroy-value-with-gen-ai" - - "https://www2.deloitte.com/us/en/insights/focus/tech-trends/2024/generative-ai-use-cases.html" - - "https://www.accenture.com/us-en/insights/artificial-intelligence/ai-maturity-and-transformation" - - "https://www.pwc.com/us/en/services/consulting/analytics/artificial-intelligence/ai-analysis.html" + - "https://www.goco.io/blog/key-hr-compliance-strategies-for-financial-services" + - "https://crosscheckcompliance.com/resources/articles/strong-compliance-culture/" + - "https://www.sunflowerbank.com/about-us/resource-articles/understanding-employment-laws/" + - "https://compliancy-group.com/anti-harassment-training-guide/" images: vllmRuntime: