A low-stakes place to grab a starter prompt from this program and run it in your own AI. Copy one, paste it into Claude, Gemini, or NotebookLM, and see what comes back. Each one lives in full (with steps and checks) inside its module.
Live · voice
Practice out loud with the Voice Simulator
Copying prompts is one way to practice. Speaking is another. Rehearse a hard conversation by voice with an AI partner, then get a debrief.
Before AI can help you, it has to understand your corner of government. In this exercise you let the AI interview YOU. It asks targeted questions about your role, your programs, and your constituents, then synthesizes a reusable Context Document you paste at the start of every future AI session. It does double duty: it models good prompting AND it produces an institutional asset that makes every later interaction more accurate. Adapted from the CMHA Housing Expert Interview.
Answer these for yourself before opening any AI:
1. What is your role, and which programs or departments do you work with most closely?
2. Who are the residents, applicants, or stakeholders you interact with most? What are their most common challenges?
3. What are your biggest administrative or communication pain points on a weekly basis?
4. What do you wish residents understood better about their rights or responsibilities?
5. What do you wish partners (landlords, vendors, other agencies) understood better about your process?
6. Where do you currently spend time on tasks that feel repetitive or inefficient?
7. What is one outcome you would love AI to help you achieve in the next 90 days?
Defining Your Workflow: The Court Clerk's AI Delegation
Best in Claude
Right now, the quality of document intake, docketing, and case-file summaries depends entirely on which clerk does the work. When an experienced clerk leaves, their knowledge walks out the door. This exercise uses AI to capture that institutional knowledge inside a reusable template, so any clerk, including someone brand new, can run a consistent, accurate workflow. You are not using AI to do the clerk's job. You are using AI to BUILD a template that encodes the job, with a human-review checkpoint baked into every consequential step, because in government AI recommends and humans decide.
Write your answers on paper before opening any AI:
1. What must happen to EVERY document before it is accepted into the record? (Non-negotiables: required fields, signatures, fees, filing deadlines, jurisdiction check.)
2. What do filers and the public ask clerks over and over? (The repeated questions that eat your day.)
3. Where do cases most often go wrong: mis-filed, mis-scheduled, sent back for correction? (The friction points.)
4. How does the workflow differ for a self-represented filer vs. an attorney e-filing? (Variation by profile.)
5. Which steps are purely administrative (a new clerk could do with a checklist) vs. which require clerk or judicial judgment (deadline calculations, conflicts, sealing, anything consequential)?
Five Rules Readiness & Pilot Selection
Best in Claude
Before you pitch, fund, or launch an AI pilot, you need an honest read on whether your entity is ready, and which pilot fits. This exercise walks you through scoring your department against the Five Rules of Government AI (0 to 2 each, max 10), then matching your score and your department mix to the right Ascend 2030 pilot template. The output is a one-page readiness brief you can take to a governance team or council.
Score my entity on Rule 1 of the Five Rules of Government AI: "Inventory Before You Innovate."
Rubric: 0 = no signal of this in our operations; 1 = some elements present, not formalized; 2 = published policy, documented practice, or operational evidence.
Here is what we have today: [DESCRIBE any AI tool inventory, vendor inventory, departmental AI catalog, or mentions of "AI inventory" in council minutes/audits, or say "none that I know of"].
Give me a 0/1/2 score, the one-line evidence behind it, and the single most valuable next step to raise the score.
Intelligent Document Processing Workflow
Best in Claude
Permits, applications, and records pile up, and reading and routing them by hand eats staff time. This exercise builds a repeatable workflow where AI reads a de-identified document, extracts the key fields into a structured table, flags what is missing instead of guessing, and produces a ready or not-ready determination. The approval decision stays with a human. Operationalizes Ascend Pilot 1 and its cognitive delegation zones.
I am building an Intelligent Document Processing workflow for government records. Before we process anything, confirm these cognitive delegation boundaries and hold to them:
- AI Zone (AI may do this): document classification, data extraction from forms, completeness checking, status tracking, regulatory citation lookup.
- Human Zone (only a human decides): final approval decisions, complex zoning interpretations, variance determinations, constituent communication, policy judgment calls.
- Collaboration Zone (AI assists, human confirms): AI flags incomplete applications for staff review, AI drafts compliance checklists for staff validation, AI summarizes reports and staff confirms.
Confirm you understand these zones. For this workflow you will extract and flag, but you will NEVER issue an approval or denial. A human makes every consequential decision. Acknowledge before we proceed.
Default to Transparency: The Plain-Language Resident Notice
Best in Claude
Government notices are often written in dense, legal language that scares residents instead of helping them act. This exercise turns one of those notices into a plain-language, trust-building communication, adds a clear AI-use disclosure line, and runs an equity check before it goes out. Built on Rule 4 (Default to Transparency) and the CMHA plain-language approach.
I am a government staff member rewriting a resident notice to be clearer and less frightening.
The audience is: [DESCRIBE the resident group, no individual identifiers, e.g. "elderly residents, many with limited English, in senior housing"].
When they receive a notice like this, the fear it usually triggers is: [DESCRIBE the anxiety, e.g. "they think they are losing their housing"].
The one action they actually need to take is: [DESCRIBE the action and deadline].
Do not rewrite anything yet. First, tell me back what you understand about this audience and what would build versus break their trust.
Community Safety Planning Data Brief
Best in Claude
A community safety plan only works if it belongs to the community, not just to city administrators. This exercise uses AI to aggregate and visualize neighborhood data so residents can see what is happening, while the priorities, interpretation, and the plan itself stay in human hands. AI coaches the process, but the safety plan belongs to the community. Operationalizes Ascend Pilot 2.
I am preparing a community safety planning data brief. Hold these boundaries:
- AI Zone: aggregate public data, summarize trends, visualize patterns, surface questions worth asking.
- Human Zone: deciding what matters, setting priorities, interpreting why a pattern exists, and designing the plan.
- Collaboration Zone: AI surfaces data insights, residents interpret and prioritize them.
This pilot puts data in the hands of residents, not just city administrators. The safety plan belongs to the community. You coach the process. You do not set the priorities. Confirm you understand before we begin.