Relevant ≠ Applicable
A fact can match the topic and still be wrong for the current object, place, time window, or operating condition.
- Not more context.
-
-
- Spatiotemporal Task Context Engine for AI Agents
-Not more context.
The context this task actually needs.
- GeoTask constructs spatiotemporal context that is relevant, applicable, resolution-adequate, and explicitly sufficient, then reassesses only the parts that are actually affected when reality changes.
-Task Sufficiency at Minimum Context Cost — minimize carried context while keeping critical context misses visible.
-
- Task-relativeContext for the task, not “the whole world”
Provider-neutralGIS / API / Sensor / WorldState
Explicit SufficiencySufficiency and gaps stay observable
Minimum ContextLower cost without hiding critical misses
Problem
The context problem is not how much an agent can carry. It is what is sufficient.
Long context windows, RAG, databases, and tools can expose more information. They do not automatically prove that information applies to the current task.
Available ≠ Adequate
A map, forecast, inventory value, or sensor reading may exist while its spatial, temporal, precision, or semantic resolution is still inadequate.
Large ≠ Sufficient
A huge payload can still miss one critical requirement; optional context can also add token, network, and human recovery cost without helping the task.
Open spatiotemporal foundations for AI agents
From world state
to the context this task actually needs.
WorldState represents reality as traceable, replayable state with evidence, validity, unknowns, and conflicts. GeoTask constructs the context the current task actually needs from that state and other providers.
Not more context: make world state explicit, then provide the minimum sufficient context for the task.
Task → Context, not World → Prompt
GeoTask starts from task requirements, then assesses candidate information. Relevance, applicability, resolution, and sufficiency remain separate so the final TaskContext and its gaps are explicit.
Task→Requirements→Candidates→Relevance→Applicability→Resolution→Sufficiency→Minimum TaskContext
Core concepts include TaskFrame, ContextRequirement, ContextCandidate, ContextAssessment, ContextGap, SufficiencyAssessment, TaskContext, ContextConstructionTrace, plus Minimum Context and Temporal Reassessment contracts.
One public story: Reality → WorldState → GeoTask → Agent
The projects are tightly related because they form a continuous information chain. They remain independent foundations with separate semantic ownership, repositories, roadmaps, and benchmarks.
Realitythe physical world→WorldStatewhat is true, unknown, conflicted or stale?→GeoTaskwhat does this task need to know?→Agentreason and act
One public story does not mean one repository.
Boundary
GeoTask does not own world truth and does not replace an agent runtime.
Its independent value is task-relative context. Upstream systems provide candidate reality; downstream systems keep reasoning, domain decisions, authorization, and execution.
UpstreamWorld / Data Providers
WorldState, GIS, APIs, sensors, databases, or other providers expose candidate facts, provenance, and state.
GeoTaskTask Context
Determines what the task needs and whether candidates are relevant, applicable, resolution-adequate, and sufficient.
DownstreamAgent / Domain System
The harness runs reasoning; domain systems continue to own professional judgment, authorization, execution, and responsibility.
Context Sufficient ≠ Domain Decision ≠ Action Authorization
Two foundations
World truth semantics and task-context semantics stay separate.
WorldState
What is true about the world?
WorldState is an open, lightweight, domain-neutral foundation for evidence-grounded world state. It preserves provenance, temporal validity, uncertainty, unknowns, conflicts, and history instead of silently resolving them away.
- Entity / Observation / Evidence / Provenance
- StateAssertion / Relation / Validity
- Unknown / Conflict / History / StateDelta
- North Star: Truth Fidelity
GeoTask
What does this task need to know?
GeoTask is a Spatiotemporal Task Context Engine for AI agents. It evaluates candidate information by relevance, applicability, resolution adequacy, and explicit sufficiency, then seeks a minimum sufficient TaskContext.
- TaskFrame / ContextRequirement / ContextCandidate
- Relevance / Applicability / Resolution Adequacy
- SufficiencyAssessment / TaskContext / ContextGap
- North Star: Task Sufficiency at Minimum Context Cost
Current Public Proof
An independent consumer now proves the model outside its original domain.
The public Core includes Task Context contracts, provider candidates, relevance / applicability / resolution, sufficiency composition, minimum context, and temporal continuity, with a non-low-altitude consumer.
Warehouse Robot Picking
Indoor GIS, an inventory API, and an aisle-clearance sensor provide ContextCandidates. GeoTask derives requirements, evaluates relevance, applicability, and resolution separately, composes sufficiency, builds minimum context, and refreshes only the affected requirement after a sensor change.
Indoor GIS / Inventory API / Aisle Sensor
- ↓
-TaskFrame → ContextRequirement[] → ContextCandidate[]
- ↓
-Relevance / Applicability / Resolution Adequacy
- ↓
-Sufficiency → Minimum Sufficient TaskContext
- ↓
-Sensor Change → Bounded Temporal Reassessment
Counterexample by design: even when the measured aisle is narrower than the robot, GeoTask may correctly conclude that the context is sufficient if that measurement is relevant, applicable, fresh, and resolution-adequate. It still does not decide that the robot may traverse the aisle.
Open the complete example →Boundary
Tightly integrated, not tightly coupled.
GeoTask can consume WorldState, but it can also consume GIS, APIs, sensors, databases, or other world models. WorldState can serve GIS, digital-twin, analytics, and other consumers without GeoTask.
WorldState does not know the task
It owns state, evidence, validity, provenance, unknowns, conflicts, history, and change.
GeoTask does not own world truth
It owns task-relative context, applicability, resolution adequacy, sufficiency, gaps, and context construction.
Context sufficient ≠ decision ≠ authorization
A sufficient TaskContext does not itself decide the domain outcome or authorize real-world action.
World → State is the center of WorldState. Task → Context is the center of GeoTask.
Measure
The objective is not context reduction by itself. It is minimum cost under sufficiency.
Every positive “reduce context” metric needs a counter-metric so the system cannot look efficient by silently dropping critical information.
Critical Requirement Coverage ↑Counter: Critical Context Miss Rate
Sufficiency Accuracy ↑Counter: False Sufficiency Rate
Context Reduction ↑Counter: Critical Context Miss Rate
Applicability Accuracy ↑Counter: Irrelevant / Inapplicable Context Rate
Context Rebuild Locality ↑Counter: Unnecessary Context Rebuild
Independent proof
Each foundation must still work without the other.
GeoTask: Warehouse Robot Picking
Indoor GIS, an inventory API, and an aisle sensor provide candidates. GeoTask derives requirements, assesses relevance / applicability / resolution, composes sufficiency, builds minimum context, and refreshes only affected requirements.
TaskFrame → ContextRequirement[] → ContextCandidate[]
+→ Relevance / Applicability / Resolution Adequacy
+→ Sufficiency → Minimum Sufficient TaskContext
+→ Bounded Temporal Reassessment
Open the GeoTask proof →WorldState: Cold-chain State
The cold-chain consumer demonstrates that evidence, validity, unknown/conflict preservation, history, and state transitions remain useful without GeoTask or a low-altitude domain product.
Observation → Evidence → StateAssertion
+→ Validity / Provenance
+→ Unknown / Conflict Preservation
+→ WorldStateSnapshot
Open the WorldState proof →Research Roadmap
The next frontier is the Task Context method itself, not more numbered examples.
GeoTask evolves as an independent foundation with its own problems, benchmarks, and cross-domain evidence.
Requirement Derivation
Move from manually supplied requirements toward stable Task → Requirement methods with explicit lineage.
Applicability & Resolution
Prove that the same fact can have different applicability across tasks while making spatial, temporal, precision, and semantic adequacy testable.
Minimum Context Cost
Reduce carried bytes, tokens, provider latency, and recovery cost without increasing critical misses.
Temporal Reassessment
Map reality changes to affected requirements and perform bounded reassessment plus only the rebuild that is actually needed.
Independent Consumers
Validate the Core in additional domains so no single product or data model shapes GeoTask semantics.
Open Method & Protocol
The durable public asset is a Task Context Method, Engine, Benchmark, and open contracts — not a closed domain platform.
About the previous positioning: early Verifiable World Model / World-State Cycle / Verification assets remain public and maintained for compatibility and traceability. They no longer define long-term semantic ownership. The current positioning is Task Context Engine.
Move from “give the model more information” to “prove this task has enough information.”
GeoTask Core is MIT licensed. Start with the independent consumer, the Python API, or the existing public examples, then connect your own GIS, API, sensor, WorldState, or other provider.
Understand the shared story, then use the foundation you need.
Use WorldState when you need traceable world state with evidence and validity. Use GeoTask when you need task-relative, explicitly sufficient context for an AI agent. Use both when reality changes and the task context must be reassessed.