Atlas Intelligence
Atlas is the decision layer behind Argus. It classifies what a node hears and feels, says how confident it is, shows the evidence behind the call, and puts the result in front of an operator in the tools they already use. It runs entirely offline.
Atlas converts raw sensor data into decisions.
Acoustic, seismic and magnetic signatures are classified on the node and fused across the network into a single picture. Every detection arrives with a confidence figure and a provenance trail, then flows straight into ATAK or a standards-based feed. No cloud round-trip, no bandwidth dependency, and nothing that stops working when the link goes down.
Core Capabilities
Classification
Threat identification from raw sensor data. Acoustic signatures: gunshots, explosions, vehicles, drones, rotorcraft. Seismic and magnetic confirmation. Runs on the node itself, not in the cloud.
Fusion
Multi-source correlation. Acoustic, seismic and magnetic detections combined into one picture, so a signature that is ambiguous on one channel gets resolved by another. Fewer false alarms, and a clear reason behind every call.
Calibrated confidence
Every detection carries a confidence figure that means something, and the system is built to abstain when the evidence is thin rather than guess. An alert from Atlas is one worth acting on.
Integration
Atlas publishes Cursor-on-Target to ATAK and WinTAK today, alongside a SAPIENT-aligned feed following BSI Flex 335 v2:2024 and a plain JSON stream for everything else. It drops into a command chain that already exists rather than asking anyone to replace one.
Technical Architecture
Edge Processing
Intelligence generated at the source. No cloud round-trip. No bandwidth dependency. Operates in contested, denied, and disconnected environments.
Distributed Computation
No single point of failure. Nodes operate autonomously and share processing load. Network degrades gracefully under attack.
Sensor Fusion
Integrates heterogeneous inputs: acoustic arrays, seismic and magnetic sensors, into a single operational picture. Correlates signals across time and space so one node’s uncertainty becomes the network’s certainty.
Built for the real world
Trained on real field recordings, not only clean laboratory audio, and evaluated against conditions it has not seen before. The hard part of sensing is the day it rains, and that is what we test against.
Human in the loop
Atlas recommends, a person decides. Every output is built to be reviewed: what was detected, how confident the system is, and the evidence behind it. Built for operators who are accountable for the call they make.
Evidence Provenance
Every output traces back to its source data. Extraction method, confidence score and relationship chain are all recorded. Built for environments where an output has to survive scrutiny: military command, procurement review, regulatory bodies.
Applications
Force Protection
Early warning around forward positions and temporary sites. Passive, battery-powered and quiet enough to leave in place. Detections publish as Cursor-on-Target straight into ATAK, so they land in the tools operators already run.
Border Security
Continuous coverage of long, sparsely manned lines. Intrusion detection and classification in places where persistent manning is impractical and mains power does not reach.
Critical Infrastructure Protection
Perimeter awareness for power grids, pipelines, ports, transportation networks. Physical intrusion detection. Anomaly identification. Integration with facility security systems.
Why Atlas
Most detection systems answer with a label and a number that does not mean anything. The number is the whole problem: an operator who cannot tell a confident detection from a guess ends up treating every alert the same way, and then ignoring all of them.
Atlas is built the other way round. It reports what it is confident about, abstains when it is not, and shows its evidence either way. That is less dramatic than promising to replace the operator, and considerably more useful to one.
Development Status
The command-and-control layer is built, tested and running: it classifies, calibrates, and publishes Cursor-on-Target to ATAK today. Argus hardware is in development, with first articles the next milestone.