1
Stage 1
Record consented incident location
Capture intent and source evidence without inventing a more precise state than the inputs support.
Production solution blueprint
Evidence-led claims from incident to settlement
Capture location and imagery, use governed vision triage, dispatch assessors, and understand catastrophe exposure.
Business outcomeFaster, more consistent claims decisions with tamper-aware spatial evidence.
The operating situation
After a severe storm, a policyholder submits vehicle-damage images and location evidence. The insurer must guide capture, detect missing or contradictory context without overclaiming authenticity, run model-locked vision triage with human review, dispatch scarce assessors by eligibility and ETA, join hazard exposure, and retain explainable evidence through settlement and appeal.
PolicyholderClaims intakeAssessorFraud analystCatastrophe manager
Keep authority explicit across the stack
01Claims systemOwns policy, claimant, incident declaration, coverage, reserves, decisions, settlement and appeal.
02Consented capture and vision boundaryCollects guided media, device/location accuracy, timestamps, hashes, capture policy and disclosure; an entitled SkyDNN adapter locks model identity, validates bounded derived geometry and confidence, and never treats metadata or inference as proof by itself.
03Spatial enrichmentNormalizes incident place, joins versioned hazard/catastrophe layers and links every feature to its source and observation window.
04Assessment operationsRoutes incomplete, uncertain, sensitive, or high-risk claims to independent review and capable assessors, ranks eligible teams by network ETA and tracks field-task proof.
05Decision evidencePolicy engine and reviewer actions name exact submissions, enrichments, model fingerprints, rule versions and reasons; later evidence creates a revision and retention policy redacts derived detections without erasing audit.
From intent to reconciled outcome
2
Stage 2
Capture guided photo evidence
Advance through an idempotent boundary, preserve stable Mappls identity, and expose freshness and ownership.
3
Stage 3
Run model-locked vision triage with human review bands
Advance through an idempotent boundary, preserve stable Mappls identity, and expose freshness and ownership.
4
Stage 4
Dispatch an assessor when needed
Advance through an idempotent boundary, preserve stable Mappls identity, and expose freshness and ownership.
5
Stage 5
Overlay hazard and policy context
Advance through an idempotent boundary, preserve stable Mappls identity, and expose freshness and ownership.
6
Stage 6
Preserve decision lineage and redaction
Reconcile the terminal result to every authoritative system and retain attributable evidence.
Records that must survive restarts and retries
Claim ↔ declared incident place and policy coverage snapshot
Version, authorize, retain, observe, and reconcile this relationship explicitly; do not recover it later from display text or logs.
Evidence submission ↔ immutable media hashes, consent, times, accuracy, device/source
Version, authorize, retain, observe, and reconcile this relationship explicitly; do not recover it later from display text or logs.
Vision attempt ↔ model fingerprint, asset hash, bounded detections, confidence, review policy
Version, authorize, retain, observe, and reconcile this relationship explicitly; do not recover it later from display text or logs.
Hazard feature ↔ dataset/version, geometry relation, observation date
Version, authorize, retain, observe, and reconcile this relationship explicitly; do not recover it later from display text or logs.
Assessment decision ↔ evidence IDs, rule/model version, reviewer, settlement revision
Version, authorize, retain, observe, and reconcile this relationship explicitly; do not recover it later from display text or logs.
Design recovery before rollout
Media upload partially succeeds
Use per-object hashes and a submission manifest; keep the claim incomplete until all required evidence commits.
Vision result is uncertain or sensitive
Preserve model and input identities, route to an independent reviewer, and prohibit automatic settlement or fraud decisions.
Location metadata conflicts with declaration
Preserve both sources, lower automation confidence and route to review rather than silently choosing one.
Catastrophe data is revised
Publish a new dataset/version and derived claim revision without rewriting the evidence used in the original decision.
Products and evidence
Capture & FeedbackOn-demand location capture, camera evidence, map feedback, and update workflows.AI & LocationAI/ML APIs, vision, location-aware agents, ranking, and natural-language spatial workflows.WorkmateWorkforce automation for people, clients, tasks, attendance, proof, and live operations.GIS & AnalyticsSpatial data, analysis, maps, dashboards, and embeddable location intelligence.Routes & NavigationRoutes, matrices, optimization, map matching, predictive ETAs, and turn-by-turn navigation.
stateful
Field-service task lifecycle
Create, assign, accept, travel, prove, approve, and close a field job without losing actor, retry, or evidence history.
statefulCoordinated incident response
Resolve an incident location, select a capable available responder, route and observe the unit, adapt to hazards, establish arrival, resolve with evidence, and review every decision.
hybridRecoverable navigation session
Move from route intent through preview, guidance, reroute, arrival, and cleanup while surviving process, sensor, and network interruption.
hybridGoverned spatial analysis
Ingest versioned data, validate and publish it, execute reproducible analysis, review lineage, and share a governed decision layer.
Earn the right to automate
1
Rollout gate
Start with guided completeness checks only
2
Rollout gate
Add entitled fixture-first vision triage with model provenance and mandatory review bands
3
Rollout gate
Add spatial hazard enrichment with analyst-visible lineage
4
Rollout gate
Pilot assessor eligibility/ETA recommendations
5
Rollout gate
Introduce versioned triage rules with independent reviewer separation
6
Rollout gate
Scale after consent, fraud, model-risk, fairness, retention, catastrophe, and appeal audits
Measure the outcome
Tutorials and downloadable applications
Intermediate
Build a route preview with alternatives
Resolve endpoints, request alternatives, decode geometry, and explain toll/time trade-offs.
AdvancedTrack a delivery with a trustworthy ETA
Join asset telemetry, map matching, route progress, ETA refresh, and customer visibility.
AdvancedAutomate a complete Workmate task lifecycle
Provision workers, dispatch jobs, consume transitions, enforce proof, and reconcile closure.
AdvancedBuild a reproducible site-selection model
Publish layers, generate catchments, join signals, score candidates, and share results.
IntermediateGive an AI agent grounded Mappls tools
Run the MCP server, scope credentials, call search and routing tools, and inspect provenance.
AdvancedProvision and validate a remote MCP client
Approve exact authority, deliver a signed pre-registration event, inspect discovery, validate PKCE and resource binding, then revoke without transporting a token or secret.
Advanced · verified app
Grid Restoration Desk
Correlate an outage, govern independent switching approval, dispatch an assigned crew, preserve rework, and reconcile restoration from telemetry and customer-impact evidence.
Advanced · verified app
Care Transfer Desk
Confirm the correct receiving entrance, assign eligible transport, preserve courier custody, review condition exceptions, and reconcile receiver acceptance without retaining patient or clinical data.
Advanced · verified app
Airside Turnaround Desk
Coordinate a revision-safe aircraft turnaround, pause for airside exceptions, preserve four service milestones, and require independent airline, airport, and safety readiness decisions.