Lethbridge Document Examples: Practicing with Copilot
Hands-On Exercises Using Real City of Lethbridge Documents
Learning to work effectively with AI tools requires practice with real-world scenarios that mirror actual work contexts. Research on situated learning emphasizes that skills developed in contextually relevant environments transfer better to real work situations than skills learned through abstract exercises (Lave & Wenger, 1991). These examples use actual City of Lethbridge documents, providing opportunities to practice with materials that reflect the complexity, terminology, and structure typical of municipal government work.
Domain-specific practice is particularly important for AI-assisted work because the effectiveness of AI tools varies significantly across different types of content and tasks. Studies on AI-assisted writing show that users who practice with domain-relevant materials develop better judgment about when AI outputs are reliable and when they require verification (Zhang et al., 2023). By working with familiar municipal documents, staff can develop this judgment more effectively than with generic examples.
The exercises included here follow a structured progression from basic summarization to more complex analysis tasks. This progression aligns with principles of scaffolded learning, where learners start with simpler tasks and gradually move to more complex ones as their skills develop (Vygotsky, 1978). Each exercise includes guidance on what to verify and how to iterate, supporting the development of systematic approaches to AI-assisted work.
References: Lave, J., & Wenger, E. (1991). Situated Learning: Legitimate Peripheral Participation. Cambridge University Press. Zhang, Y., et al. (2023). Evaluating Verifiability in Generative Search Engines. arXiv preprint arXiv:2304.09848. Vygotsky, L. S. (1978). Mind in Society: The Development of Higher Psychological Processes. Harvard University Press.
How to Use These Exercises
Executive Exercise Process:
- Choose a document you know well - Pick one where you understand the key points and main messages
- Write down what you expect - Before using Copilot, note the 3-5 key points you believe the document conveys
- Start with the summarize prompt - This builds your understanding of how Copilot processes the document
- Compare and reflect - Did Copilot catch the main points? What did it miss? What did it get right?
- Try the discovery prompts - These help you find insights you might not have noticed, or verify if Copilot can find specific information
- Evaluate accuracy - Check if Copilot's findings are accurate. This teaches you when to trust and when to verify
Try This Now: Pick one document from the sections below that you're familiar with. Download it, then use the summarize prompt in Copilot. Compare Copilot's summary to what you know the document says. Then try one of the discovery prompts. See what interesting insights Copilot finds—and verify if they're accurate.
What You'll Learn
By practicing with these real Lethbridge documents, you'll learn:
- How Copilot processes municipal documents - You'll see what it catches and what it might miss
- When to trust Copilot's summaries - You'll develop judgment about when the summary is accurate enough to use
- How to refine prompts - You'll learn to ask better questions to get better results
- What Copilot can discover - You'll see how it can find connections and insights you might have missed
- When to verify - You'll learn to recognize when Copilot's findings need fact-checking
Key Insight: The best way to understand Copilot is to use it with documents you know. These Lethbridge documents are perfect because you can verify Copilot's accuracy. This hands-on experience builds the understanding you need to lead AI adoption effectively.
How to Use This Guide
This guide provides real City of Lethbridge documents that you can use to practice with Copilot. Each document includes:
- A link to the document - Download or open it in Word/PDF
- A "summarize" prompt - Start here to build your understanding of what the document says
- Three discovery prompts - Use these to find interesting insights Copilot discovers in the document
Why this works: Since these are documents you likely know well (or can easily verify), you can test Copilot's accuracy and see what it finds. This builds your understanding of how Copilot works with real municipal documents.
Strategic Documents: The "North Stars"
These are the most important strategic documents that guide city decision-making. Every city official should be familiar with these.
Gateway to Opportunity: 2024 City Council Action Plan
What it is: The primary strategic roadmap for the current City Council. It outlines 26 specific priority projects and initiatives for the remainder of their term (ending Oct 2025). This is the "marching orders" document that every major decision must align with.
Open Document →Step 1: Build Understanding
"Summarize this City Council Action Plan in 5 bullet points. Focus on the main strategic priorities and key initiatives outlined for the council term."
Step 2: Discover Interesting Insights
"What are the 26 priority projects mentioned in this action plan? List them and identify which ones have budget implications or require new funding."
"What does this document say about economic development priorities? Identify specific initiatives related to business attraction, retention, or growth."
"What are the key performance indicators or success metrics mentioned in this plan? How will the city measure progress on these priorities?"
Municipal Development Plan (MDP) - Adopted 2021
What it is: The statutory "constitution" for land use and growth. It dictates how Lethbridge will grow over the next 40 years, shifting focus from "sprawl" to "urban intensification" and mixed-use nodes. This is legally binding—any development or rezoning must align with it.
Access MDP →Step 1: Build Understanding
"Summarize the Municipal Development Plan's main growth strategy. What are the key principles for how Lethbridge will develop over the next 40 years?"
Step 2: Discover Interesting Insights
"What does Policy 6 say about urban growth? Explain the shift from sprawl to urban intensification in plain language."
"What are the mixed-use nodes mentioned in this plan? Where are they located and what are the development goals for each?"
"What environmental or sustainability requirements are outlined in this development plan? How do they impact future development?"
Major Operational & Financial Reviews
These comprehensive reviews shaped how the city operates and manages finances.
KPMG Operational Review (Phases 1-3) - 2019-2021
What it is: A massive, multi-volume third-party audit of every city department to find efficiencies and cost savings. This report was a seismic event for city hall—it led to budget cuts, layoffs, and restructuring. Even in 2025, officials still reference "KPMG recommendations."
KPMG Phase 3 Report →Note: Additional phases available through City of Lethbridge Plans and Reports page
Step 1: Build Understanding
"Summarize the key recommendations from this KPMG operational review. What were the main areas identified for efficiency improvements or cost savings?"
Step 2: Discover Interesting Insights
"What specific cost-saving recommendations did KPMG make? Quantify the potential savings mentioned in the report."
"Which departments or services were identified as having the most opportunities for operational improvements? What were the specific recommendations for those areas?"
"What organizational structure changes or restructuring recommendations did KPMG propose? How would these impact city operations?"
Lethbridge Police Service (LPS) Master Plan - December 2023
What it is: A critical infrastructure and operational plan addressing the future of policing in the city, including the need for a new police headquarters and training facility. Policing takes up the largest single chunk of the city's operating budget.
Open LPS Master Plan →Step 1: Build Understanding
"Summarize the Lethbridge Police Service Master Plan. What are the main infrastructure needs and operational priorities identified in this document?"
Step 2: Discover Interesting Insights
"What are the specific infrastructure requirements mentioned in this plan? What is the estimated cost for the new police headquarters and training facility?"
"What operational challenges does this plan identify? How does it propose to address staffing, technology, or service delivery issues?"
"What timeline or phasing is proposed for implementing the recommendations in this master plan? What are the priority actions?"
Recent Infrastructure Master Plans
These comprehensive technical documents guide hundreds of millions in capital spending decisions.
Parks Master Plan - Adopted March 2025
What it is: The brand-new 15-20 year strategy for the city's parks system, replacing the outdated 2007 plan. It addresses high-profile issues like pathway connectivity, dog parks, and maintaining the river valley.
Access Parks Master Plan →Step 1: Build Understanding
"Summarize the Parks Master Plan's main vision and strategic priorities. What are the key goals for Lethbridge's parks system over the next 15-20 years?"
Step 2: Discover Interesting Insights
"What specific park improvements or new facilities are recommended in this plan? Which areas of the city are prioritized for park development?"
"What does this plan say about pathway connectivity? What are the recommendations for improving connections between parks and neighborhoods?"
"What budget or funding strategies are outlined in this plan? How does it propose to pay for the recommended park improvements?"
Transportation Master Plan (TMP) - 2023
What it is: The blueprint for all roads, transit, and cycling infrastructure. It contains controversial decisions about where the third bridge might go (Chinook Trail) and how to fix traffic bottlenecks.
Open Transportation Master Plan →Step 1: Build Understanding
"Summarize the Transportation Master Plan's main transportation priorities and infrastructure recommendations. What are the key goals for roads, transit, and cycling?"
Step 2: Discover Interesting Insights
"What does this plan say about a potential third bridge? What are the proposed locations (like Chinook Trail) and what factors are being considered?"
"What traffic bottlenecks or congestion issues does this plan identify? What solutions or infrastructure improvements are proposed?"
"How does this plan integrate with the Cycling Master Plan? What are the priorities for active transportation infrastructure?"
Critical Social Strategy Reports
These documents guide social funding and address some of the city's most visible challenges.
Community Wellbeing and Safety Strategy (CWSS) - Updated 2024
What it is: The guiding document for social funding (over $100M in grants). It dictates how the city tackles homelessness, addiction, and safety. This report governs the "encampment strategies" and shelter funding decisions that dominate local news.
Access CWSS Information →Note: Full strategy document available through Community Social Development
Step 1: Build Understanding
"Summarize the Community Wellbeing and Safety Strategy. What are the main priorities for addressing homelessness, addiction, and community safety in Lethbridge?"
Step 2: Discover Interesting Insights
"What specific funding priorities or grant categories are outlined in this strategy? How is the over $100M in social funding allocated?"
"What does this strategy say about encampment management? What approaches or policies are recommended for addressing encampments?"
"What partnerships or collaborative approaches with community organizations are emphasized in this strategy? How does it propose to coordinate services?"
Housing Needs Assessment - 2024
What it is: A data-heavy report quantifying exactly how many affordable housing units the city is missing. It's the evidence base used to apply for federal housing accelerator funds.
Access Housing Needs Assessment →Step 1: Build Understanding
"Summarize the Housing Needs Assessment. What is the housing gap in Lethbridge? How many affordable housing units are needed?"
Step 2: Discover Interesting Insights
"What are the specific 'gap numbers' mentioned in this assessment? Break down the housing need by income level or household type."
"What does this assessment say about rental vs. ownership housing needs? What are the priorities for different types of housing?"
"What strategies or recommendations does this assessment propose to address the housing gap? How does it relate to federal housing accelerator funding?"
Case Studies: From Simple to Complex AI-Enabled Municipal Workflows
Case Study 1: Automated Resident Communication Pipeline
Sarah Chen, Program Coordinator, Parks and Recreation Department
The Parks and Recreation department implemented a simple but effective AI-assisted workflow to handle routine resident inquiries and service notifications. Each week, staff use Copilot in Outlook to draft standardized email templates for common scenarios—park maintenance schedules, program registration deadlines, and facility closures. The process begins with a department manager opening a SharePoint document containing the week's service updates and using Copilot to generate personalized email drafts. Copilot analyzes the source document, extracts key dates and locations, and creates resident-friendly communications that match the city's tone guidelines. Staff then review and customize each draft before sending, reducing email composition time from 15 minutes per message to under 3 minutes. The workflow has been particularly effective for seasonal communications, where Copilot can quickly adapt templates from previous years with updated dates and program information. This simple automation has freed up approximately 8 hours per week of staff time, allowing the department to focus on program delivery rather than administrative communication tasks.
The implementation began with a pilot program involving three staff members who were already comfortable with Microsoft 365 tools. The initial training consisted of a single 30-minute session focused on effective prompting techniques specific to email composition. Staff learned to structure prompts that include context about the audience (residents, program participants, or facility users), the purpose of the communication (notification, reminder, or information request), and any specific requirements (deadlines, contact information, or action items). The department created a small library of proven prompts stored in a shared Teams channel, making it easy for staff to copy and adapt prompts for their specific needs.
One of the most successful applications has been handling program registration communications. When registration opens for summer camps or fitness programs, staff use Copilot to generate personalized emails that include program details, registration links, and important dates—all pulled directly from the program planning documents in SharePoint. Copilot ensures consistency in messaging while allowing staff to add personal touches or department-specific information. The system has also proven valuable for handling unexpected situations, such as facility closures due to maintenance or weather. Staff can quickly draft clear, informative notices that include alternative options and contact information, ensuring residents receive timely and helpful communications even during urgent situations.
Quality assurance remains a critical component of the workflow. Every email generated by Copilot undergoes human review before sending, with staff checking for accuracy of dates, correctness of contact information, and appropriateness of tone. The department has developed a quick checklist for reviewing AI-generated emails: verify all dates and times, confirm contact information is current, ensure links work correctly, and check that the tone matches the communication's purpose. This review process typically takes 2-3 minutes per email, still significantly faster than composing from scratch, while maintaining quality and accuracy standards.
The success of this simple workflow has inspired other departments to explore similar applications. The Communications department is now using Copilot to draft press releases and social media content, while the Public Works department uses it for service disruption notices. The key lesson learned is that even simple AI-assisted workflows can deliver substantial time savings when applied to repetitive, high-volume tasks. The Parks and Recreation department plans to expand the system to handle multilingual communications and to integrate with the city's customer relationship management system for even more personalized resident communications.
Case Study 2: Integrated Budget Analysis and Reporting System
Michael Thompson, Senior Budget Analyst, Finance Department
A mid-sized Canadian municipality developed a more sophisticated AI-enabled data pipeline to streamline their quarterly budget review process. The workflow integrates multiple Microsoft 365 applications: Excel workbooks containing departmental spending data, Word documents with policy context, and Teams meeting transcripts from budget committee discussions. The process begins when finance staff upload quarterly budget variance reports to a SharePoint site. Using Copilot in Excel, analysts can ask natural language questions about spending patterns: "Which departments exceeded their Q3 budgets by more than 5%?" or "What are the top three cost drivers in public works this quarter?" Copilot analyzes the data, identifies trends, and generates preliminary insights. These insights are then fed into Word, where Copilot helps draft executive summaries that synthesize the Excel analysis with relevant policy documents and meeting notes. The AI cross-references spending data against council-approved budget priorities, flagging discrepancies and suggesting areas for deeper investigation. The final reports are automatically formatted for council presentation, with Copilot ensuring consistent terminology and compliance with municipal reporting standards. This integrated approach has reduced the quarterly budget review cycle from three weeks to one week, while improving the quality and consistency of financial reporting. The system has also improved transparency by making budget data more accessible to non-financial staff through natural language queries.
The technical implementation required careful attention to data governance and security. Finance staff worked with IT to ensure that budget data remained properly secured within the Microsoft 365 tenant, with appropriate access controls and data loss prevention policies in place. The system leverages SharePoint's permission structure, ensuring that sensitive financial information is only accessible to authorized personnel. All Copilot interactions occur within the secure Microsoft 365 environment, with no data leaving the organization's tenant. This security-first approach was essential for gaining approval from the municipality's IT security team and ensuring compliance with financial data protection requirements.
The workflow has transformed how budget analysts work with data. Previously, analysts spent significant time manually extracting data from multiple Excel files, creating pivot tables, and writing formulas to identify trends. Now, they can simply ask Copilot questions in natural language: "Show me spending trends for the Parks department over the last four quarters" or "Compare actual spending to budgeted amounts for all capital projects." Copilot not only retrieves the data but also provides context and identifies patterns that might not be immediately obvious. For example, when asked about budget variances, Copilot can identify whether overspending is due to increased volume, higher unit costs, or unexpected expenses—insights that previously required hours of manual analysis.
The integration with Word has revolutionized report writing. Analysts start with the insights generated in Excel, then use Copilot in Word to draft narrative explanations that connect the numbers to policy decisions and operational context. Copilot references the original budget documents, policy statements, and meeting notes to ensure that the narrative accurately reflects the municipality's strategic priorities. The AI helps maintain consistent terminology and formatting across all reports, reducing the time spent on editing and ensuring professional presentation standards. The system can also generate different versions of reports for different audiences—detailed technical reports for finance staff, executive summaries for senior management, and plain-language summaries for council members.
One of the most valuable features has been the ability to track budget performance against strategic priorities. Copilot can analyze spending patterns and compare them to council-approved strategic plans, flagging areas where spending doesn't align with stated priorities. For example, if the strategic plan emphasizes sustainability initiatives but spending on environmental programs is declining, Copilot will flag this discrepancy and suggest areas for investigation. This capability has improved accountability and helped ensure that budget decisions align with strategic goals.
The system has also improved collaboration across departments. Non-financial staff can now query budget data using natural language, making financial information more accessible to program managers and department heads. This has reduced the number of requests to the finance department for budget information, freeing up finance staff for more analytical work. The transparency has also improved budget literacy across the organization, as staff can explore budget data and understand how their department's spending fits into the larger municipal budget picture. The municipality plans to expand the system to include predictive analytics, using historical spending patterns to forecast future budget needs and identify potential financial risks before they become problems.
Case Study 3: Advanced Multi-Source Policy Analysis and Decision Support Pipeline
Dr. Patricia Martinez, Senior Policy Advisor, Strategic Initiatives Office
A large urban municipality implemented a complex, end-to-end AI-enabled workflow that transforms how policy decisions are researched, analyzed, and communicated across departments. The system integrates data from multiple sources: internal policy documents stored in SharePoint, external research reports, provincial and federal legislation databases, public consultation feedback collected through online surveys, historical council meeting minutes, and real-time data from municipal service delivery systems. The workflow begins when a policy question emerges—for example, "Should we implement a new waste diversion program?" Staff use Copilot in Teams to initiate a research phase, where the AI searches across all connected data sources to identify relevant precedents, similar programs in other municipalities, applicable legislation, and public sentiment from past consultations. Copilot in Word then synthesizes this information into a comprehensive policy brief that includes: a summary of relevant research, analysis of legal and regulatory requirements, comparison with peer municipality approaches, cost-benefit considerations based on historical data, and recommended implementation strategies. The system uses advanced prompt engineering to ensure the analysis maintains objectivity, cites sources accurately, and presents multiple perspectives. As the policy development progresses, Copilot in Excel analyzes budget implications by querying historical program costs and projecting future expenses based on similar initiatives. The AI also monitors public feedback channels, using natural language processing to identify emerging themes and concerns that should be addressed in the final policy proposal. Throughout the process, Copilot generates draft communications for different stakeholders—technical briefings for department heads, plain-language summaries for council, and public-facing explanations for residents. The final policy document is automatically cross-checked against municipal bylaws and provincial regulations to ensure compliance, with Copilot flagging potential conflicts or required approvals. This sophisticated pipeline has transformed policy development from a 6-12 month process requiring extensive manual research and coordination into a streamlined 2-3 month workflow, while significantly improving the quality and comprehensiveness of policy analysis. The system has been particularly valuable for complex, multi-departmental initiatives where coordination and information synthesis were previously major bottlenecks.
The architecture of this system required careful design to handle the complexity of integrating multiple data sources while maintaining data quality and security. The municipality established a centralized knowledge hub in SharePoint that serves as the primary repository for all policy-related documents, research, and analysis. External data sources are connected through secure APIs and data connectors, with automated processes that regularly update the knowledge base with new research, legislation changes, and public consultation results. The system uses Microsoft Graph to access data across the Microsoft 365 ecosystem, ensuring that Copilot can search and analyze information from Teams conversations, email threads, and document libraries throughout the organization. This comprehensive data integration was essential for enabling Copilot to provide truly holistic policy analysis that considers all relevant factors.
The research phase of the workflow has been particularly transformative. Previously, policy analysts spent weeks manually searching through documents, reading research reports, and compiling information from various sources. Now, Copilot can quickly scan thousands of documents and identify the most relevant information, extracting key findings, methodologies, and conclusions from research reports. The AI can also identify patterns across multiple sources—for example, recognizing that several peer municipalities have implemented similar programs and extracting common success factors and challenges. This capability has dramatically accelerated the research phase while ensuring that policy development is informed by comprehensive, up-to-date information. The system also tracks the sources of all information, making it easy for analysts to verify claims and cite sources in final policy documents.
Legal and regulatory compliance checking has become significantly more robust with the AI-enabled system. Copilot can analyze proposed policies against existing municipal bylaws, provincial legislation, and federal regulations, identifying potential conflicts or compliance requirements. The system flags areas where the proposed policy might conflict with existing regulations, suggests required approvals or consultations, and identifies any legal precedents that should be considered. This capability has reduced the risk of legal challenges and ensured that policies are developed with full awareness of regulatory requirements. The system has been particularly valuable for complex policy areas like land use planning, where multiple layers of regulation apply and compliance requirements can be difficult to track manually.
Public engagement has been enhanced through the system's ability to analyze and synthesize feedback from multiple channels. When public consultations are conducted—whether through online surveys, public meetings, or written submissions—Copilot can analyze all feedback to identify common themes, concerns, and suggestions. The AI can distinguish between different types of feedback (supportive, concerned, neutral, or opposed) and identify the specific issues that are most important to residents. This analysis informs policy development, ensuring that public concerns are addressed and that policies reflect community priorities. The system can also generate summaries of public feedback for council and staff, making it easier to understand and respond to community input.
The communication generation capabilities have proven invaluable for ensuring that policy information reaches all stakeholders in appropriate formats. Copilot can generate multiple versions of policy documents tailored to different audiences: detailed technical briefings for subject matter experts, executive summaries for senior management, plain-language explanations for council members, and public-facing communications for residents. Each version maintains accuracy and consistency while adapting the level of detail and technical language to the audience. This capability has improved transparency and understanding of policy decisions across the organization and the community. The system also ensures that all communications use consistent terminology and messaging, reducing confusion and improving clarity.
Governance and oversight have been critical to the system's success. The municipality established a policy development oversight committee that reviews all AI-generated analysis and ensures that human judgment remains central to policy decisions. The committee includes representatives from legal, finance, communications, and relevant operational departments, ensuring that multiple perspectives inform policy development. All AI-generated content undergoes human review, with staff verifying facts, checking sources, and ensuring that recommendations align with municipal values and strategic priorities. This human-in-the-loop approach has been essential for maintaining accountability and ensuring that AI enhances rather than replaces human expertise in policy development.
The measurable outcomes of this system have been substantial. Policy development timelines have been reduced by 60-75%, with complex policies that previously took 6-12 months now completed in 2-3 months. The quality of policy analysis has improved, with more comprehensive research, better identification of risks and opportunities, and more thorough consideration of stakeholder perspectives. The system has also improved consistency across policy documents, ensuring that similar issues are addressed in similar ways and that policies align with each other and with strategic priorities. Perhaps most importantly, the system has enabled the municipality to be more responsive to emerging issues, as policy development can now proceed much more quickly when urgent decisions are needed. The municipality continues to refine the system, adding new data sources, improving prompt engineering techniques, and expanding the system to additional policy areas. The success of this advanced workflow demonstrates the transformative potential of AI-enabled systems for complex, knowledge-intensive municipal work.
Was this helpful?
Your feedback helps us improve these resources.