Hire an AI GIS solution designer

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• Success criteria for the demo
• The simplest technology path for each key interaction
• Feasibility checks with how to test each one
• A phased build plan with time limits
• A demo safety plan: offline copy, saved data and a backup
• A shortcuts list, and a table of what is production ready and what is proof only

How it does the job well

• Never fake a demo. If a part does not work yet, say so and show what does work.
• Never state effort, time or performance as a fact. Give ranges the user must check, and mark them estimates.
• Give drafts and proposals. Get the user's go-ahead before anything that sends, publishes, spends money or changes a live system.
• Agree the question and the decision it supports before analysing.
• Check the data first: date range, grain, missing values, duplicates and definitions.
• Compare like with like: same period length, definitions and segments.
• Separate what the data shows from what it might mean, and give confidence levels.

Mistakes it avoids

• Reporting a change without checking whether tracking or definitions changed.
• Treating correlation as cause.
• Averages that hide important segments or outliers.

What a good result looks like

An example, not your task: A client or boss asks "can you show me?" before they approve a GIS project.

• Brief and assumptions. The goal, audience and device as understood, with assumptions and MISSING items.
• Success criteria. What the demo must show to count as a pass, and how you will know.
• Key interactions and tools. Each interaction with the simplest tool that shows it, and why.
• Feasibility checks. Data, service, speed and licence risks, each with a quick test.
• Build plan. Phases with tasks, time limits and a done-when line.
• Demo safety. The offline copy, saved data, backup and errors to catch.

How the work is checked

• Numbers reconcile to the source totals, and the reconciliation is shown.
• Every chart and number states its source, period and definition.
• Limits and next checks are listed.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

Capabilities

• Collect the brief. It reads the goal and the key moments, and asks once for anything missing. It marks gaps as MISSING.
• Set success criteria. It defines what the demo must show to count as a pass.
• Choose the simplest path. It picks the tool for each task, such as ArcGIS Pro for analysis, ArcGIS Online for sharing and Python for automation.
• Check feasibility. It lists data, service, speed and licence risks, each with a quick test and a two hour limit on research.
• Plan the build. It plans data first, then the key path, then polish, with a test on the real device.
• Plan reliability and handoff. It plans an offline copy and a backup, and lists the shortcuts and what is proof only.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id gis-solution-engineer only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/gis-solution-engineer/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• The strategy, architecture plan or goal, in a few lines
• The three to five things the demo must show
• Your data: sources, formats and rough size
• The tools and licences you have, such as ArcGIS Pro, ArcGIS Online, QGIS or PostGIS
• Where it will run, such as a laptop, a tablet or a phone, and whether Wi-Fi is certain
• The deadline and who will build it (optional)

Helpful context (optional)

• The architecture document from your consultant or team.
• A small sample of each data source.

Tools and access

• Claude, ChatGPT or Gemini: The plan works from a pasted profile and your brief.
• Claude Code: It can read your project and sample data, so the build plan fits what you have.

Functions and deliverables

• GIS solution designer: Plan a working GIS demo or proof of concept: what it must show, the simplest tools, build steps, a safe backup and what is not production ready.
  • Success criteria for the demo
  • The simplest technology path for each key interaction
  • Feasibility checks with how to test each one
  • A phased build plan with time limits
  • A demo safety plan: offline copy, saved data and a backup
  • A shortcuts list, and a table of what is production ready and what is proof only
  Source: Michael Sitarzewski and Agency Agents contributors.
• Backup communication plan builder: Build a backup communication plan with fallback paths, owners and switch triggers. Get a worksheet, check-in card and a safe test outline.
  • A communication fallback worksheet, check-in card, test outline, and gap or correction log.
  Source: Magnus Hedemark.
• Online worked example builder: Build online worked examples for any skill. Help fades step by step, so learners move from full solutions to solving alone.
  • A sequence of examples that fade support
  • Step explanations
  • Fill-in-the-blank practice steps
  • Self-explanation prompts
  Source: Gareth Manning.
• Pre-sales proof of concept planner: Share buyer requirements and product details. Get coverage gaps, a competitor feature table and a trial plan.
  • A fit score from 0 to 100 percent
  • The count of must-have gaps
  • A bid, bid with a plan, or no bid call, with the reason
  • A feature table against each rival
  • A phased trial plan with success checks and a scorecard
  Source: Alireza Rezvani.
• Metric definition writer: Share a metric, calculation and business use. Get a YAML definition, validation results and questions for the data owner.
  • A filled metric, dimension or entity YAML
  • A validation report
  • dbt-ready field names
  • Notes on edge cases
  Source: Nimrod Fisher.

Tasks you can use it for

• A client or boss asks "can you show me?" before they approve a GIS project.
• You have an architecture plan and must prove the risky part works.
• You need a demo that runs without Wi-Fi at a conference or site visit.
• You must find out early if a data format, an API or a licence blocks your idea.

Limits to check before starting

• You need strategy, tool choice or a roadmap: use the GIS implementation planner.
• You need production ready software: use the Web GIS Developer agent and your engineering team.
• You need your data cleaned in depth: use the Spatial Data Engineer agent.
• You need the demo map styled: use the Map designer.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Add the pack to your AI as a skill. Or open a new chat and paste SKILL.md, then references/source-agent.md.
• Paste the strategy or goal. Then list the three to five things the demo must show, and your data and tools. Never paste real keys. Use a placeholder.
• Say 'Plan this demo. Do not guess my data.' Your AI asks once for what is missing.
• Read the feasibility checks first. Run the risky ones before you build anything.
• Build the one path the client cares about most. Add polish last, and make the offline backup before the day.
• Hand the shortcuts list to the engineers who will build the real version.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/gis-solution-engineer for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.