Hire an AI GIS implementation planner

Everything it can hand back

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

• A current state summary and a gap list
• A comparison of Esri, open source and mixed options
• A layered design from data sources to apps, and where it runs
• A roadmap in phases, starting with a data audit
• Three tiers: quick win, full solution and large scale
• A hidden cost list and draft RFP sections if you ask

How it does the job well

• Never invent a saving, a percentage, a price, a timeline or a return. Ask for the user's own numbers. If none, show the formula and write MISSING for each value.
• 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: You run a utility, council, property or field team and wonder where maps could cut costs.

• Problem and assumptions. The problem and current state as understood, with assumptions and MISSING items.
• Gap list. Each pain point matched to a location capability and the value to measure.
• Options. Esri, open source and mixed setups compared on cost, skills, upkeep and lock in.
• Recommended design. The layers from data sources to apps, links to other systems and where it runs.
• Roadmap and tiers. Phases from data audit to scale, and a quick win, full and large scale tier.
• Hidden costs and risks. Costs people forget, such as data licences, training, upkeep and cloud fees.

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.

A second opinion

Before it hands back, your AI reviews the draft the way Marty Cagan would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Understand the problem. It restates the business problem and the current workflow, and marks missing facts as MISSING.
• Map pain to capability. It links each pain point to a location capability and where the value would show up.
• Compare the options. It compares Esri, open source and mixed setups on cost, skills, upkeep and lock in, without taking a side.
• Design the layers. It plans sources, data loading, storage, services and apps, plus links to other systems and where it runs.
• Set the roadmap. It orders a data audit, a quick win, scale and tuning, and sets who owns each data set.
• List costs and risks. It lists hidden costs and failure risks, and offers draft RFP text if you ask.

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-technical-consultant 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-technical-consultant/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 business problem in plain words, and what it costs you if you know
• How location data is used today: tools, file types, spreadsheets, CAD
• Team skills and rough budget
• Systems the GIS must connect to, such as finance, customer, sensor or field apps (optional)
• The RFP text or list of requirements (optional)
• The size of the organization and your deadline (optional)

Helpful context (optional)

• A list of the systems and data files you use now.
• Any past reports or complaints about the current process.

Tools and access

• Claude, ChatGPT or Gemini: The plan works from a pasted profile and your description of the organization.
• Claude Code: It can read a folder of your documents, such as an RFP or a data list, so the plan fits them.

Functions and deliverables

• GIS implementation planner: Turn a business problem into a GIS plan: gap review, Esri or open source choice, phased roadmap, hidden costs and RFP text. No building.
  • A current state summary and a gap list
  • A comparison of Esri, open source and mixed options
  • A layered design from data sources to apps, and where it runs
  • A roadmap in phases, starting with a data audit
  • Three tiers: quick win, full solution and large scale
  • A hidden cost list and draft RFP sections if you ask
  Source: Michael Sitarzewski and Agency Agents contributors.
• RFP response builder: Turn an RFP or security questionnaire into a sorted requirements list, a fit check and a bid or no-bid call. Gaps are shown, never made up.
  • Requirements tagged by priority
  • A fit matrix with proof points and gaps
  • Three to five win themes
  • A win-chance estimate and bid call
  • Draft answers
  Source: Alireza Rezvani.
• Product outcome roadmap planner: Turn a feature roadmap into outcomes. Paste your features and dates. Get three to five customer problems, each with a result you can measure.
  • Each item marked as a feature, a problem or a result
  • Three to five problems, each for a named customer
  • One measurable result per problem
  • Review points in place of dates, with the evidence each needs
• Notion build task planner: Turn a spec in Notion into a clear implementation plan and linked tasks, with gaps and assumptions listed before work starts.
  • A list of gaps and assumptions in the spec
  • A plan page, quick or full
  • Tasks created in your database
  • Links between spec, plan and tasks
  • Status updates as work moves
  Source: OpenAI.
• 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.
• Marty Cagan: Review a product idea using Marty Cagan’s recorded approach. Test its value, ease of use, build limits and fit with the business.
  • Your problem worked on the way Marty Cagan would: their questions, their method, their push-back
  • The answer or the work, in Marty Cagan's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step

Tasks you can use it for

• You run a utility, council, property or field team and wonder where maps could cut costs.
• You must choose between ArcGIS and open source tools such as QGIS and PostGIS.
• You are replacing AutoCAD files, a legacy GIS or spreadsheets with a proper system.
• You are writing the technical part of an RFP or a bid.

Limits to check before starting

• You need someone to open ArcGIS Pro and build a map: use the GIS analyst.
• You need a working demo to show: use the GIS solution designer.
• You need Python code or a data pipeline: use the Spatial Data Engineer agent.
• You need legal, survey or licence terms decided: ask a qualified professional or the vendor.

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.
• Write the problem in business words. Then list your data, tools, people and systems. Leave out private details.
• Say 'Plan this GIS project. Do not guess my budget or my data.' Your AI asks once for what is missing.
• Read the gap list and the options first. Tell it what it got wrong before it builds the roadmap.
• Use your own numbers for savings. Ask the vendors for prices. The AI cannot know either.
• Take the quick win phase to your team. Ask the Solution Engineer agent to plan a demo of it.

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-technical-consultant 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.