Convergence of latent representations, deterministic engineering, and spatial computing.
We design and build systems where data and models are not black boxes, but structured semantic geometries: representations that can be measured, audited, and explained.
Rancagua, Región de O'Higgins.Semantic Geometry did not start in a funded laboratory or inside a tech corporation. It started with an intuition its author held through decades of self-taught development: that an idea, a feeling, or a physical law can be located exactly in space.
Human meaning, then, would not be a static definition in an alphabetical dictionary, but a mathematical position in a continuous space of coordinates. If Earth has latitude, longitude, and altitude to locate any object on its surface, thought should have its own Cartesian axes: a GPS of knowledge.
Years later, reviewing the formal literature, that intuition turned out to converge with the lineage of classical psychometrics: Louis Thurstone's measurement of attitudes and Charles Osgood's semantic differential. It was not an orphan idea; it was an idea arriving late to its own scientific tradition.
That is where the technical stance that defines the company comes from. Against models that get it right most of the time without being able to explain why, that cannot tell what they know from what they invent, and that depend on enormous servers, Semantic Geometry was built on the opposite principle: the model proposes, but the graph and the cube verify.
Recomputable from the IEEE 754 specification. The 1022 exponents that give |x| < 1, plus the one that gives exactly ±1 with zero mantissa, across both signs.
Two ways of answering when you don’t know
Generative model
Always answers. If the data is not there, it builds something plausible: fluency and truthfulness come from the same mechanism, so from the outside there is no way to tell them apart.
→
Deterministic verifier
Allowed to stay silent. Geometry guides inference, but only graph evidence certifies it. When there is none, the system says so: refusal is an answer, not a failure.
The difference is not who gets it right more often. It is that one can be wrong without knowing it, and the other cannot assert without evidence.
02 — Verticals
The engine is the foundation; the verticals, the product
On top of the deterministic verification core we build regulated verticals: domains where a hallucination costs money, a verdict, or a fine. Each one states its stage honestly, without hype.
01
Fleet operations
SG-Fleet
Geofences, telemetry, and fleet control in C++23
Header-only C++23 engine with REST + TCP tracker, multi-tenant isolation, and hardware telemetry. Designed to operate 100% offline, at the edge.
REST API with multi-tenant isolation and RBAC
TCP tracker (Wialon IPS / CSV) with high-density batching
Geofences, alerts, and operations dashboard
Zero dependencies: runs where there is no cloud
Self-contained slices (~7 MB) for radio links and micro-devices
C++23SQLiteRESTTCP
Operational engine
02
Accounting & tax · Chile
SG-Tax
Payroll, RLI, and deterministic tax balance
Chilean regulatory calculation without heuristics: Previred settlements, ProPyme RLI, and financial vs. tax balance. Every result is auditable against the law.
Previred settlements (105-field file)
RLI ProPyme 14-D3 / 14-D8 and Semi-Integrated 14-A
IFRS vs. SII tax balance with reconciliation
Deterministic calculation: zero black boxes
C++23SQLiteSIIPrevired
In development
03
Credit & banking · Chile
SG-Fintech
Credit simulation with traceable amortization
Credit simulations and amortization schedules with full audit: every payment decision is backed by the engine, ready for inspection.
Credit simulation with amortization schedule
Market indicator calculation (UF, rate, CPI)
Audit trail per operation
Determinism for regulated decisions
NestJSSQLiteFinancial calculation
In development
04
Labor law · Chile
SG-Legal
Ontological grounding of labor regulation
Applying the verification engine to law: labor claims validated against the graph and the regulation, with a formal lineage traceable to the law.
Deterministic verification of labor claims
Traceability of the regulation underlying the answer
No vertical competes with an LLM at text generation: it competes in what an LLM cannot promise: an answer that knows when to stay silent and can show the regulation behind it. And where an LLM cannot reach —no connectivity, standard silicon, at the edge— the engine can.
03 — Pillars
Three capabilities, one discipline of representation
We do not sell hours of generic development. Each pillar solves a different kind of problem, under the same criteria: explicit structure, measurable performance, and results that hold over time.
01
Data Engineering & High-Performance Backends
We build the plumbing where data arrives intact and on time. Fault-tolerant ETL pipelines, flow optimization, and robust microservices, sized for real production volume.
ETL/ELT pipelines and massive ingestion orchestration
Query, index, and memory-footprint optimization
High-performance microservices and backends
Observability, idempotency, and failure recovery
C++23Embedded SQL / SQLitePythonREST APIs
02
Deterministic AI & Latent Spaces
We model knowledge as geometry, not as a black box. Interpretable vector spaces and a verifier that can refuse to assert when the graph does not support it.
Geometric modeling of knowledge in latent spaces
Interpretable, traceable vector representations
Deterministic verification of what a generative model proposes
Evidence-based grounding: no assertion without graph support
EmbeddingsDirected graphsVerificationEthical AI
03
Spatial Computing & Optimization
Analytic algorithms for problems that do not admit approximations. Combinatorial, geospatial, and financial optimization applied to industrial operations and regulated decision-making.
Combinatorial optimization and metaheuristics
Geospatial analysis and network topology
Risk models and auditable regulatory calculation
Simulation and operational decision support
Offline edge: ~15W on standard silicon, no GPU, no cloud
OptimizationGeospatialFinancial modelsSimulation
Current status
Semantic Geometry is not finished. It is built not to lie while it is not.
Being calibratedGrows through audited ingestion. What cannot be measured is purged.
Domain coverage
UnevenAnd the engine declares it: where the graph has no evidence, it answers with silence.
A model with incomplete coverage that fills the gaps is riskier than one with the same coverage that stays silent. For industrial operations and regulated decisions, that difference is not a detail: it is the product.
04 — Identity & Contact
Let's talk about the problem, not the pitch
Tell us what system you need to build, what pipeline is failing, or what decision you cannot back today. We respond with a technical diagnosis, not a brochure.