Products/Intelligence
hybrid3 platforms4 source families
Reason over the physical world

AI & Location

AI/ML APIs, vision, location-aware agents, ranking, and natural-language spatial workflows.

Start building Get credentials

Combine Mappls data and platform operations with models that classify imagery, understand spatial intent, rank places, and orchestrate tools. AI integrations should ground every answer in a typed Mappls operation and expose provenance rather than allowing the model to invent locations or operational state.

Open the SkyDNN vision evidence guide

Keep synchronous inference, model provenance, geometry validation, policy, independent review, retention, and redaction in their correct ownership boundaries.

Open guide

Capabilities

Vision and imagery analysisProduction guidance, platform support, examples, and operational considerations included.01
Location-aware retrieval and rankingProduction guidance, platform support, examples, and operational considerations included.02
Natural-language map operationsProduction guidance, platform support, examples, and operational considerations included.03
Typed tools for AI agentsProduction guidance, platform support, examples, and operational considerations included.04
Spatial workflow orchestrationProduction guidance, platform support, examples, and operational considerations included.05
Evaluation and grounding patternsProduction guidance, platform support, examples, and operational considerations included.06

Available platforms

Keep business identifiers and server-side policy portable; use the native surface where device integration or long-lived state matters.

Underlying product credential, held by the tool server

Never place keys or tokens in model context. Use the exact current or legacy authentication generation required by each underlying product, execute typed policy-checked tools on a trusted server, and redact precise coordinates and credential-bearing URLs from logs.

  • Use separate projects for development, staging, and production.
  • Apply the narrowest domain, IP, platform, product, and resource scopes available.
  • Never ship a server secret in a browser bundle, mobile binary, prompt, or public repository.

Quickstart

Replace placeholders with credentials from the developer console. Examples include the lifecycle and failure-handling context that short snippets usually omit.

AI & Location quickstart
const nearbyPlacesTool = {
  name: "mappls_search_nearby",
  description: "Find real places near a validated Mappls Pin or coordinate.",
  inputSchema: {
    type: "object",
    required: ["location", "category"],
    properties: {
      location: { type: "string", description: "Mappls Pin or 'lat,lng'." },
      category: { type: "string" },
      radiusMeters: { type: "integer", minimum: 50, maximum: 10_000 }
    }
  }
};
Before productionRestrict and rotate credentialsHandle timeouts and typed errorsAdd tracing without logging secretsTest quota and degraded-mode behavior

Operate the complete lifecycle

These blueprints name every state, actor, command, event, invariant, durable record, retry boundary, failure recovery, source contract, and operational signal.

Browse all stateful journey blueprints

Source repositories

Reference content is reconciled against these public and private source families. Version, authentication generation, and maturity are recorded before content is promoted.

Browse all 3 related integration guides