{
 "schema": "aiblocks-page/1",
 "id": "agency-gis-geoai-ml-engineer",
 "type": "agent",
 "name": "Geospatial machine learning planner",
 "summary": "Plan a model that finds buildings, roads or land cover in satellite and aerial images, with data checks, a test plan and deployment steps.",
 "headline": "Geospatial machine learning planner",
 "subhead": "Tell it what you want to find in your images and where. It checks your imagery and labels, picks a model type, and plans the tests that show whether it works on new places. You get a plan to review, not a trained model.",
 "job": {
  "id": "build-software",
  "name": "Build and ship software"
 },
 "level": "intermediate",
 "thinking": "high",
 "tested": true,
 "updated": "2026-11-03",
 "first_published": "2026-10-26",
 "inputs": [
  {
   "type": "question",
   "required": true,
   "label": "Question",
   "what": "the problem, decision or piece of work you want help with, and what a good outcome looks like"
  },
  {
   "type": "map_data",
   "required": false,
   "label": "Map data",
   "what": "map data, such as GeoJSON, a shapefile, a GeoPackage, a raster or a point cloud, with its coordinate system and fields"
  },
  {
   "type": "training_data",
   "required": false,
   "label": "Training data",
   "what": "examples used to train or fine-tune an AI model, such as labelled text pairs or images, with how they are split"
  }
 ],
 "outputs": [
  {
   "type": "plan",
   "required": true,
   "label": "Plan",
   "what": "a dated plan: what to do, in what order, with a decision rule for each step"
  }
 ],
 "you_give": [
  "What you want to find, such as buildings, roads, vehicles, water or crop types",
  "Your imagery, with its source, pixel size, bands, dates and the area it covers",
  "Any labelled examples you already have, and how many (optional)",
  "The accuracy you need and what the result will be used for",
  "The computer you will train on, such as one GPU or none (optional)"
 ],
 "you_get": [
  "A clear target with the accuracy you need",
  "A check of your imagery, and whether a ready-made dataset or model could do the job",
  "A model plan with tile size, training split and model type, and why",
  "A test plan with results per class and a test on places the model has not seen",
  "A deployment plan from image tiles to map layers",
  "A list of ways the model may fail, and the checks left for you"
 ],
 "use_when": [
  "You want building outlines, roads or vehicles pulled from satellite or drone images.",
  "You need a land cover or crop map from Sentinel-2 or Landsat images and want to know if you have enough data.",
  "You want to compare images from two dates to find change, such as new buildings or lost trees.",
  "A model works in your notebook and you need the steps to make it work on a whole city."
 ],
 "skip_when": [
  "You need a buffer, overlay or simple map analysis. Use the GIS analyst.",
  "You need a study of spatial patterns or statistics. Use the Spatial data scientist.",
  "You need drone photos turned into maps and 3D models. Use the Drone mapping specialist.",
  "Your files need cleaning and converting before any model. Use the Spatial Data Engineer agent first."
 ],
 "output_sample": {
  "input": [
   "What you want to find in your images, and the area",
   "Notes on your imagery, such as source, pixel size, bands and dates",
   "Labelled examples, if you have any (optional)",
   "The accuracy you need and how the result will be used"
  ],
  "prerequisites": [
   "An AI that can read files, such as Claude, ChatGPT or Gemini",
   "Your imagery on a machine you control, since the AI never sees the images"
  ],
  "output": [
   {
    "name": "Target and assumptions",
    "contains": "What to find, the accuracy needed, what the map is for and what the plan assumes."
   },
   {
    "name": "Imagery and data check",
    "contains": "Whether your images and labels are enough, and any ready-made data or model worth trying first."
   },
   {
    "name": "Model plan",
    "contains": "The model type, tile settings, data split and training steps, each with a reason."
   },
   {
    "name": "Test plan",
    "contains": "How to score the model per class, on new places and by eye, with the pass line."
   },
   {
    "name": "Deployment plan",
    "contains": "The steps from image tiles to clean map layers, and how to watch for drift."
   },
   {
    "name": "Failure modes",
    "contains": "Cloud, shadow, season and other conditions that break the model, with a test for each."
   }
  ]
 },
 "output_shape": "TARGET AND ASSUMPTIONS\n  <what to find> | <accuracy needed> | <use of the result> | <assumptions>\n\nIMAGERY AND DATA CHECK\n  <imagery> | <pixel size, bands, dates> | <labelled data found or missing> | <ready-made model to try>\n\nMODEL PLAN\n  <model type> | <why> | <tile size and overlap> | <train, validation, test split> | <training steps>\n\nTEST PLAN\n  <metric per class> | <test on new geography> | <visual spot-check> | <pass line to agree with you>\n\nDEPLOYMENT PLAN\n  <export> | <tile, predict, merge> | <clean-up> | <map layer output> | <drift watch>\n\nFAILURE MODES\n  <condition> | <what goes wrong> | <how to test it>\n\nCHECKS LEFT AND NEXT STEP\n  <what you must run> | <next action>",
 "how_to_use": [
  "Download the pack and add it to your AI as a skill. If you cannot, paste SKILL.md and then references/source-agent.md into a new chat.",
  "Describe what you want to find and attach notes on your imagery. A sample image helps.",
  "Type \"Plan the model and tell me what data I am missing.\" Your AI asks once for anything missing.",
  "Read the data check first. If labelled examples are too few, fix that before anything else.",
  "Run the tests it lists on your own computer or cloud account. It cannot train or score a model for you.",
  "Have a GIS specialist review the plan before a decision that affects people or money relies on the map."
 ],
 "checks": [
  "The result addresses your actual task and cites the evidence used.",
  "Examples, role-play experience and targets are kept separate from verified results.",
  "Claims of tests, memory, tool access or completed actions match what actually happened."
 ],
 "next": [
  {
   "name": "Data system design reviewer",
   "url": "https://useaiblocks.com/skills/data-system-designer",
   "why": "Build it"
  }
 ],
 "source": {
  "by": "Michael Sitarzewski and Agency Agents contributors",
  "repo": "msitarzewski/agency-agents",
  "url": "https://github.com/msitarzewski/agency-agents/blob/b37b5bb33b78f2c1d6567d98e25ca818e3259219/gis/gis-geoai-ml-engineer.md",
  "licence": "MIT",
  "original_name": "GeoAI/ML Engineer",
  "commit": "b37b5bb33b78f2c1d6567d98e25ca818e3259219"
 },
 "credits": [
  {
   "title": "GeoAI/ML Engineer",
   "by": "Michael Sitarzewski and Agency Agents contributors",
   "url": "https://github.com/msitarzewski/agency-agents/blob/b37b5bb33b78f2c1d6567d98e25ca818e3259219/gis/gis-geoai-ml-engineer.md",
   "used": "Original agent profile, preserved in references/source-agent.md; AI Blocks adds setup and review instructions."
  }
 ],
 "files": [
  "LICENSE",
  "references/source-agent.md",
  "SETUP.md",
  "source.json"
 ],
 "links": {
  "page": "https://useaiblocks.com/agents/agency-gis-geoai-ml-engineer",
  "markdown": "https://useaiblocks.com/agents/agency-gis-geoai-ml-engineer.md",
  "json": "https://useaiblocks.com/agents/agency-gis-geoai-ml-engineer.json",
  "instructions": "https://useaiblocks.com/skills/agency-gis-geoai-ml-engineer/SKILL.md",
  "download": "https://useaiblocks.com/skills/agency-gis-geoai-ml-engineer.zip",
  "api_item": "https://useaiblocks.com/api/v1/items/agency-gis-geoai-ml-engineer",
  "api_document": "https://useaiblocks.com/api/v1/documents/agent/agency-gis-geoai-ml-engineer",
  "mcp": "https://useaiblocks.com/mcp"
 }
}