Targeting & Engagement Agent
D3A / F2T2EA workflows with deterministic, authenticated ROE policy checks.
- Doctrine alignment
- NATO AJP-3.9 Joint Targeting; D3A and F2T2EA workflows.
- Deployment
- Always paired with human-in-the-loop authority gates.
- Underlying products
- CipherLayer™CyberFort Blockchain™PQ-STRAT™
Purpose
Targeting decisions carry legal, political and strategic consequences, so decision support must be transparent, deterministic and always subordinate to human authority. SC-TGT-01 provides decision support across the full targeting cycle. It runs D3A and F2T2EA workflows as explicit state machines, applies deterministic ROE compliance checks against authenticated, version-pinned rule sets, and requires recorded human-in-the-loop authorisation at every irreversible gate, signed with ML-DSA in assured deployments. There is no configuration that removes the human gate, and every compliance check leaves a proof that can be inspected after the event.
Architecture
Target nominations enter through a STANAG-aligned adapter and are normalised into the mesh schema. The core runs D3A and F2T2EA workflows as explicit state machines with collateral modelling at each stage. ROE compliance is not a model output. It is a deterministic check against an authenticated, version-pinned rule set, and the result is a proof, not an opinion. Every irreversible gate requires an explicit human-in-the-loop authorisation, enforced by the engine rather than by a prompt and recorded in the decision chain, with ML-DSA signatures applied in assured deployments. CipherLayer™ protects the workflow in transit, PQ-STRAT™ provides post-quantum signatures, and the entire chain from nomination to effects assessment is sealed to CyberFort Blockchain™.
Hover or focus a band to see what it guarantees.
Inputs and outputs
- IN-01Target nominations
- IN-02ROE policy
- IN-03Collateral models
- OUT-01Engagement options with ROE compliance proofs
- OUT-02Effects assessments
Position in the mesh
- Consumes
- Publishes
- CommanderNLCommand interface
- SC-ATO-01Air Tasking Agent
What it does not do
It never authorises an engagement. There is no configuration in which the human gate can be removed.
The same four gates as every agent
An unregistered or unapproved model tag is refused before inference, not flagged afterwards.
Every action is scoped to a declared role. Scope is checked at the engine, not in the prompt.
New or changed models run under supervision until their evaluation evidence is accepted.
Irreversible decisions require a signed human authorisation recorded with the decision.
The agents differ in what they reason about. They do not differ in what they are allowed to do.
Deployment
In-country, accredited cloud, under your jurisdiction and operational control.
Designed for deployment up to NATO SECRET. Accreditation is per deployment.
Runs disconnected. Inference, agents and the decision record are all local.
Ready to see SynapseCommand® in action?
Briefings available under NDA. Classified briefings arranged through cleared channels.