# MAIA Analytics

> Every parcel, owner, and dataset in America, already loaded. Ask a question in plain language and get an answer you can act on, with sources attached.

MAIA is an agent platform purpose-built for the physical world. Every parcel, owner, and dataset in America is already loaded, so a market thesis becomes an answer you can act on, with sources attached.

## Product

- [Home](https://maia-analytics.com/): MAIA is the geospatial research engine that connects structured records, imagery, and the live web, so you can investigate the physical world at the speed of your ideas.
- [Product](https://maia-analytics.com/product): Search, enrich, resolve, and publish. All from one engine.
- [Interactive demo](https://maia-analytics.com/#interactive-demo): Prepared example runs of MAIA answering real siting questions on county records, with every value sourced.
- [Geospatial search](https://maia-analytics.com/product#site-selection): Gather the precise context your answer requires.
- [Multimodal enrichment](https://maia-analytics.com/product#enrichment): Ask what the database does not already know.
- [Bring your own data (BYOD)](https://maia-analytics.com/product#byod): Upload structured and unstructured context.
- [Entity resolution](https://maia-analytics.com/product#entity-resolution): Find the people behind the places.
- [Knowledge & Skills](https://maia-analytics.com/product#skills): Make every interaction compound.
- [Data sourcing](https://maia-analytics.com/data): Trust isn't optional, it's built in. At MAIA, we believe you should know both how our AI works and how your data is handled. Here's our commitment in plain language.
- [Pricing](https://maia-analytics.com/pricing): Every plan includes every dataset, every agent, and every enrichment. You pay for the research you run, not for the people who run it.
- [Book a demo](https://maia-analytics.com/demo): Pick a time below to walk through MAIA together. We'll show you the capabilities, where the data comes from, and if it fits the work you have in front of you.

## Documentation

- [MAIA documentation](https://maia-analytics.com/docs): MAIA is a geospatial research engine. You define a research objective, MAIA's agent builds a spatial database to answer it, and every value in that database names its source.
- [All docs as one Markdown file](https://maia-analytics.com/docs.md): Every page below, in reading order.
- [What is MAIA?](https://maia-analytics.com/docs/quickstart/what-is-maia.md): MAIA is a geospatial research engine. You define a research objective in plain language, MAIA's agent builds a spatial database to answer it, and every researched value in that database names its source.
- [Your first run](https://maia-analytics.com/docs/quickstart/first-run.md): A first run in MAIA is the same four steps as every run, once you have chosen a county: define the objective, dispatch it, review the result, and compound what worked. This page follows one run through all four.
- [Define](https://maia-analytics.com/docs/using-maia/define.md): To define a research objective for MAIA, name the thing, the place, and the conditions, with numbers wherever you have them. The objective says what you want, and MAIA's agent works out how to get it.
- [Dispatch](https://maia-analytics.com/docs/using-maia/dispatch.md): To dispatch an objective, you hand it to MAIA's agent and answer what it asks along the way. The agent shows what it is doing, and it stops for you only when a choice would change the result, spend credits you have not agreed to, or remove data.
- [Review](https://maia-analytics.com/docs/using-maia/review.md): To review a result in MAIA, you check the answer against the database the agent built. Every column header states where the column came from, and every researched value opens to its reasoning and its sources.
- [Compound](https://maia-analytics.com/docs/using-maia/compound.md): To compound your work in MAIA, you save the method as a skill, teach MAIA your context as knowledge, and run the same objective in the next county. Each run then starts from what the last one learned.
- [Capabilities overview](https://maia-analytics.com/docs/capabilities/overview.md): MAIA's capabilities fall into four layers: agents that do the work, data they can read, context they remember, and the workspace where the work lives. This page lists every capability, what it takes, and what it returns.
- [Agents](https://maia-analytics.com/docs/capabilities/agents.md): MAIA is a coordinated system of agents. One main agent takes your objective and directs the run. Sub-agents do the deep work on each row, in parallel, so the conversation never waits on the research.
- [Main agent](https://maia-analytics.com/docs/capabilities/main-agent.md): MAIA's main agent takes a research objective and returns layers on the map and in the table, with a written answer. It answers from the data first, researches only what the data cannot answer, and checks the result before it reports.
- [Sub-agents](https://maia-analytics.com/docs/capabilities/sub-agents.md): MAIA is a coordinated system of agents. The main agent runs the conversation, and when a question needs research on every row, it hands the tasks to a sub-agent. Hundreds run at once, in the background, and none of them holds up the main agent.
- [Data](https://maia-analytics.com/docs/capabilities/data.md): Data is what MAIA's agents can read. There are three kinds: the core data MAIA holds, the data you bring, and public data MAIA finds during a run. Every column built from them names where it came from.
- [Core data](https://maia-analytics.com/docs/capabilities/core-data.md): MAIA's core data takes a question about a county and returns rows from the datasets MAIA already holds: parcels, buildings, businesses, environmental records, census data, and more, joined on one spatial model.
- [Database sync](https://maia-analytics.com/docs/capabilities/database-sync.md): When enabled by MAIA staff for an Enterprise workspace, MAIA's database sync takes tables from your own database and returns them inside your workspace, matched to parcels and refreshed every day.
- [File upload](https://maia-analytics.com/docs/capabilities/file-upload.md): MAIA's file upload takes a spreadsheet or a map file and returns a layer matched to parcels, a layer of your own shapes, or a table.
- [Data discovery](https://maia-analytics.com/docs/capabilities/data-discovery.md): MAIA's data discovery takes a question that core data cannot answer and returns a public GIS layer, found during the run, clipped to the project's selected counties, and saved with its source and usage terms.
- [Context](https://maia-analytics.com/docs/capabilities/context.md): Context is what MAIA remembers between runs. Skills hold your method, and knowledge holds what MAIA should know about you and your work.
- [Skills](https://maia-analytics.com/docs/capabilities/skills.md): A MAIA skill takes a method you have worked out and returns a run you can repeat. It records the criteria, the steps, and the output format, and it runs in any county.
- [Knowledge](https://maia-analytics.com/docs/capabilities/knowledge.md): MAIA's knowledge takes what you tell it about your business and returns it as context on every turn. It is filled in automatically, open to inspection, and yours to edit.
- [Workspace](https://maia-analytics.com/docs/capabilities/workspace.md): A workspace is where work in MAIA lives. It holds your team, your projects, and what MAIA has learned about your business, and each project's owner decides who else can see it.
- [Shared workspaces](https://maia-analytics.com/docs/capabilities/shared-workspaces.md): A shared workspace in MAIA puts a team in the same projects, skills, and knowledge. Each project starts private, and its owner decides whether the workspace can view it or edit it.
- [Sharing and publishing](https://maia-analytics.com/docs/capabilities/sharing-and-publishing.md): MAIA's sharing takes a project and returns a link you can send to anyone, with or without a MAIA account. Export takes a layer and returns a spreadsheet.
- [Enrichments](https://maia-analytics.com/docs/enrichments/overview.md): An enrichment is a column MAIA fills by research, one row at a time. It takes a question and a set of rows and returns a value for every row, with the reasoning and the sources behind it.
- [Run an enrichment](https://maia-analytics.com/docs/enrichments/run-an-enrichment.md): An enrichment runs when MAIA's main agent starts it or when you do. The agent tests a new column on a few rows before it runs the rest. You choose the rows yourself, from one cell to the whole list.
- [Computer vision](https://maia-analytics.com/docs/enrichments/computer-vision.md): MAIA's computer vision takes a parcel, a building, or a point and returns a value read from overhead imagery, with the reasoning behind it.
- [Contacts](https://maia-analytics.com/docs/enrichments/contacts.md): MAIA's contacts enrichment resolves the entity behind a parcel, a building, or a business, then finds the persona you asked for inside it: the owner behind an LLC, or a specific role at the business. Each contact comes with contact details and the evidence for the match.
- [Mortgages and liens](https://maia-analytics.com/docs/enrichments/mortgages-and-liens.md): MAIA's mortgages and liens lookup takes a parcel and returns its debt profile: open loans with their due dates and lenders, involuntary liens, and foreclosure filings.
- [Property details](https://maia-analytics.com/docs/enrichments/property-details.md): MAIA's property details take a parcel, a building, or a place and return who uses it. They answer two questions for every row, whether the owner occupies the property and who the tenants are, each with its reasoning and sources.
- [Web research](https://maia-analytics.com/docs/enrichments/web-research.md): MAIA's web research takes a question the data cannot answer and returns an answer from the public web, with links to the pages it rests on.
- [Connect MAIA to Claude or ChatGPT](https://maia-analytics.com/docs/mcp/connect.md): MAIA's MCP connector is a remote MCP server that lets Claude, ChatGPT, and other MCP clients hand research to MAIA's agent. You connect once, sign in with your MAIA account, and dispatch work from the client you already use.
- [Upload a file from Claude or ChatGPT](https://maia-analytics.com/docs/mcp/upload-a-file.md): MAIA's MCP connector takes a file you attach in Claude, ChatGPT, or another MCP client, and brings its rows into a MAIA project. MAIA matches the rows to parcels or adds them as a map layer or a table, the same way an upload in the web app does.
- [MCP tools](https://maia-analytics.com/docs/mcp/tools.md): MAIA's MCP connector exposes twenty-two tools. With them an MCP client can find a place or a county, start a project, bring in a file, send a request to MAIA's agent, query a project's data, share a project, follow the run, answer its questions, ask you to approve its steps, and save skills and memory.
- [MCP prompts](https://maia-analytics.com/docs/mcp/prompts.md): MAIA's MCP connector ships five prompts, which are ready-made requests that tell your client which tools to call and in what order. In Claude Code they appear as slash commands.
- [Runs and approvals over MCP](https://maia-analytics.com/docs/mcp/runs-and-approvals.md): A run is one request worked by MAIA's agent. Over MCP, your client starts a run and gets back a run report, which holds progress while MAIA works, a question when MAIA needs your decision, and the answer with a link to the project at the end.
- [In-chat project view](https://maia-analytics.com/docs/mcp/project-view.md): MAIA's project view is a card that shows a project inside the chat of an MCP client. It shows the run, the answer, a map, and the first rows of the table, without leaving the conversation.
- [Plans](https://maia-analytics.com/docs/billing/plans.md): MAIA has three plans: Free, Pro, and Enterprise. A plan belongs to a workspace, not to a person. It sets the credits the workspace receives each month and the counties it can open.
- [Credits](https://maia-analytics.com/docs/billing/credits.md): Credits are a dollar balance that a MAIA workspace spends on research. A workspace can hold three kinds: monthly credits from its plan, promotional credits from MAIA, and credits it purchased.
- [What uses credits](https://maia-analytics.com/docs/billing/usage.md): Two kinds of work spend credits in MAIA: what the main agent does in chat, and enrichments. Both spend from the same workspace balance, and the amount follows the research done.
- [Buy credits and auto-reload](https://maia-analytics.com/docs/billing/buy-credits.md): Any MAIA workspace can buy credits, on any plan. Purchased credits never expire. Auto-reload buys credits for you when the balance drops below a threshold, up to a monthly limit you set.
- [Out of credits](https://maia-analytics.com/docs/billing/out-of-credits.md): A MAIA workspace is out of credits when its balance reaches $0. New work stops, running work finishes, and everything already built stays available. New work can start again once credits are added.
- [Manage your plan](https://maia-analytics.com/docs/billing/manage-your-plan.md): A MAIA workspace manages its plan from the Plan & credits tab of its account: upgrade to Pro, change a card, read receipts, recover from a failed payment, cancel, and reactivate. Any member can do so.
- [Limits](https://maia-analytics.com/docs/reference/limits.md): MAIA's limits in one place: how large a file, a layer, a sync, an enrichment batch, or an export can be, how long a query can run, and what MAIA does not do.
- [File formats](https://maia-analytics.com/docs/reference/file-formats.md): MAIA reads spreadsheets and map files on upload, reads a PDF attached to chat, and writes CSV and Excel on export. This page lists each format, what it holds, and the rules that apply to it.
- [Restricted uses](https://maia-analytics.com/docs/reference/restricted-uses.md): MAIA is for geospatial research. MAIA declines any request to use it for a decision about a person's credit, insurance, employment, tenant screening, or housing eligibility.
- [Data and privacy](https://maia-analytics.com/docs/reference/data-and-privacy.md): MAIA keeps each workspace's data separate, encrypts it in transit and at rest, and does not train its models on your inputs.
- [Frequently asked questions](https://maia-analytics.com/docs/reference/faq.md): Short answers about what MAIA covers, what data it includes, how it is priced, and how it handles your data. Each answer stands on its own.

## Solutions by industry

- [Solutions](https://maia-analytics.com/solutions): Find the land, properties, businesses, and market opportunities others miss.
- [Affordable housing](https://maia-analytics.com/solutions/lihtc): MAIA finds every parcel in a county inside a qualified census tract or difficult development area that clears your acreage and zoning, scores it against the state QAP, and resolves the owner behind it. Affordable housing developers use it to turn a county into a ranked list of sites, including the ones with a path to rezone. Sourcing starts from every eligible parcel, not from a broker's RFP.
- [Battery storage](https://maia-analytics.com/solutions/battery-storage): MAIA finds every parcel in a county within reach of a substation or transmission line that clears your acreage, zoning, environmental, and neighbor screens, then resolves the owner behind each one. Storage developers use it to turn a county's substation buffers into a ranked short list in an afternoon. Sourcing starts from every parcel in the buffer, not from a spreadsheet.
- [Commercial & industrial solar](https://maia-analytics.com/solutions/solar): MAIA finds every commercial building in a county with the roof, load, and incentives to support a solar deal, plus every array already built, then resolves the owner behind each one. Solar teams use it to build an outbound list, or to work outward from current customers where the installation next door is the social proof. Sourcing starts from every roof in the market, not from a lead list.
- [EV charging](https://maia-analytics.com/solutions/ev-charging): MAIA scores every parcel in a county for charging demand and keeps the ones with the size, road access, power nearby, and clean history to build on, then resolves the owner behind each one. Charging developers use it to turn a metro's industrial parcels into a ranked short list before anyone books a site visit. Sourcing starts from every parcel in the market, not from what's listed.
- [Industrial outdoor storage](https://maia-analytics.com/solutions/industrial-outdoor-storage): MAIA finds every industrial parcel in a county zoned for outdoor storage by right, with the low building coverage and usable acreage of a real yard, then resolves the owner behind each one. IOS investors use it to cut a county's industrial parcels to a few hundred true yards and reach the owners the listing databases can't. Sourcing starts from every parcel in the market, not from a broker's inbox.
- [Multifamily housing](https://maia-analytics.com/solutions/multifamily): MAIA finds every multifamily parcel in a county that fits your buy box, from a 12-unit building to a 15-acre assemblage, then resolves the person behind each owning LLC and where to mail them. Multifamily teams use it to turn a county into one owner list before the first letter goes out. Outbound starts from every owner in the market, not from the ones a broker already called.
- [Retail site selection](https://maia-analytics.com/solutions/retail): MAIA maps every store, competitor, and rooftop in a trade area, scores where demand can support another location, then finds the corners that can capture it and the owner behind each one. Retail developers use it to cut a county's commercial parcels to the prime corners and skip the ones a big-box developer already holds. Site selection starts from every parcel on the map, not from what's listed.
- [Case studies](https://maia-analytics.com/case-studies): One question, every parcel, and the records behind each answer. Each story names the question a team asked, what MAIA did with it, and what came back.
- [How Connected Companies Stays Ahead of the Competition with MAIA](https://maia-analytics.com/case-studies/connected-companies): 11,000 multifamily parcels across the San Gabriel Valley in one pull, filtered to 2 to 50 units, the year built, and no sale in the last two years
- [How Namaste Solar Finds Solar-Ready Buildings Using MAIA](https://maia-analytics.com/case-studies/namaste-solar): 48 nonprofit buildings in Denver County cleared every screen, out of 386 parcels
- [How a Columbus Solar Company Found Three Interested Property Owners](https://maia-analytics.com/case-studies/columbus-solar-outbound): 2,800 parcels screened down to the top 100 candidates by roof score and ESG signal
- [How Namaste Solar Identifies All the Solar O&M Opportunities with MAIA](https://maia-analytics.com/case-studies/namaste-solar-om): 169 solar arrays identified in Boulder County, each mapped by parcel with its module count, panel area, and an estimated capacity
- [How an EV Charging Company Found Sites Near Power and Highways](https://maia-analytics.com/case-studies/metro-ev-charging-sites): 657 parcels to 15 viable sites within half a mile of two target substations in one market, screened in one pass
- [Finding an Industrial Yard That Wasn't Listed for Sale and Reaching Its Owner](https://maia-analytics.com/case-studies/mid-atlantic-ios-owner-call): One call, one callback, and "bring me an offer": the owner's number MAIA returned was missing or stale in every database the firm pays for, and the owner shared the lease and asked for an offer
- [Where an Investor Found 332 Outdoor Storage Sites in Fulton County](https://maia-analytics.com/case-studies/fulton-county-ios-screen): 332 by-right IOS candidates in Fulton County from the first search, before a single owner was enriched
- [How Genesis Finds the Best Industrial Outdoor Storage Sites with MAIA](https://maia-analytics.com/case-studies/genesis): About 1,100 IOS parcels in a single New Jersey county from one prompt, each checked against the municipal zoning for outdoor storage, with usable acres and building coverage on every row
- [Mapping Buildable Apartment Sites in Manatee County, Florida](https://maia-analytics.com/case-studies/gulf-coast-multifamily-assemblages): 286 vacant parcels of 15 to 20 acres in Manatee County from the first saved search, with zoning, future land use, wetlands, and flood on every row
- [How a Broker Found Large Affordable Housing Sites Across 34 Counties](https://maia-analytics.com/case-studies/sunbelt-qct-dda-land): 3,800 vacant parcels to one 7.8-acre assemblage in the broker's home county: every vacant parcel inside a QCT or DDA, cut to 133 in multifamily districts, 19 at the acreage floor, and the two-parcel site worth the call
- [How ResiQ Finds the Apartment Owners Ready for Managed Wi-Fi With MAIA](https://maia-analytics.com/case-studies/resiq): 23 owners buying in Collin County, each with two or more apartment acquisitions in the last 24 months, found among 640 multifamily parcels
- [How a Housing Developer Found Land That Could Be Rezoned for Apartments](https://maia-analytics.com/case-studies/rezone-potential-qct): 63 rezone candidates inside one county's QCT and DDA tracts: parcels zoned single-family or commercial today that sit under a future land use allowing multifamily density, each with the ordinance cited
- [31 Pinellas County Churches with Land for Affordable Housing](https://maia-analytics.com/case-studies/pinellas-church-land-live-local): 107 church sites in Pinellas County found from assessor use codes in the first pass, before a single call was made
- [27 Large Retail Development Sites Found in Maricopa County](https://maia-analytics.com/case-studies/maricopa-hard-corners): 383 candidates, 79 true arterial corners, 55 prime corners from the first Maricopa County run, 27 of them commercially zoned
- [85 Potential Gym Expansion Sites Identified Around Phoenix](https://maia-analytics.com/case-studies/phoenix-gym-sites): 28 existing locations mapped from business records in the first minute, with a ten-mile radius drawn around each

## Use cases

- [Use cases](https://maia-analytics.com/use-cases): Find acquisition targets, forecast demand, build sales territories, and identify gaps in market coverage.
- [Acquisitions & roll-ups](https://maia-analytics.com/use-cases/acquisitions-and-roll-ups): MAIA runs your buy box across every parcel and every business in a market, groups what it finds into portfolios, and resolves the person behind each one. Acquisition teams use it to turn a county into an owner list, whether the target is a yard, a building, a tract of land, or an operator with eight locations. Outreach starts from the whole market, not from what's for sale.
- [Demand forecasting](https://maia-analytics.com/use-cases/demand-forecasting): MAIA joins traffic, jobs, households, destinations, and existing supply to every parcel in a market, weights them the way your model does, and returns a demand score at the parcel with the records behind it. Developers use it to see where demand is headed before they pick a site, and which of two lots on the same block ranks higher. Scoring starts at the parcel, not the census tract.
- [Target account sourcing](https://maia-analytics.com/use-cases/target-account-sourcing): MAIA reads the physical and business signals off every parcel in a market, from roof and load to owner occupancy and incentives, and turns them into an account list with the decision maker at each one. Sales teams use it to build a territory from buildings and owners rather than job titles. Sourcing starts from every building in the market, not from a contact database.
- [Whitespace analysis](https://maia-analytics.com/use-cases/whitespace-analysis): MAIA maps your locations and every competitor's, lays the demand signal over them, and finds the trade areas where demand is strong and coverage is thin, then the by-right sites inside each gap with the owner attached. Operators and developers use it to see where the next location belongs before a broker suggests one. Analysis starts from every operator and every parcel in the market, not from a competitor list.

## Blog

- [How do I find who owns a property — or every owner on a list of parcels?](https://maia-analytics.com/blog/how-to-find-who-owns-a-property-or-a-list-of-parcels): From one address to a whole county: the manual method, and the faster one
- [Can ChatGPT or Claude find development sites and property owners?](https://maia-analytics.com/blog/can-chatgpt-or-claude-find-sites-and-property-owners): What a general assistant gets right, where it breaks, and what it needs behind it
- [Buy intelligence, not data](https://maia-analytics.com/blog/buy-intelligence-not-data): The web taught us that access is not the product. The valuable layer indexes meaning and makes the corpus usable for reasoning.
- [Build vs. buy: what my sister's lemonade stand settled](https://maia-analytics.com/blog/build-vs-buy-site-selection-stack): One question about one place is a lookup. Ten ideas across a market are a search problem. The difference is the speed of the loop.
- [The IOS land grab is on. Here's how to find what isn't listed.](https://maia-analytics.com/blog/finding-off-market-industrial-sites): Capital is flooding into an asset class with frozen supply and fragmented ownership. The advantage belongs to whoever can search the land itself.

## Company

- [About](https://maia-analytics.com/about): The best ideas come from smart people who know what to ask. We built MAIA to help them go further.
- [Careers](https://maia-analytics.com/careers): If this sounds exciting, we'd love to hear from you.
- [Privacy policy](https://maia-analytics.com/privacy)
- [Terms of service](https://maia-analytics.com/terms)