Plintir // Actionable intelligence // Interface visuals use synthetic data

Plintir / Products / AUGUR

Plintir AUGUR

AI Decision Intelligence

AI that proposes. People that decide.

Large models are useful in intelligence work exactly to the degree that you can trust what they retrieved and constrain what they can do. AUGUR is built around that constraint: retrieval is authorised before generation, every claim carries a citation, and no action reaches the world without a named person approving it.

PROPOSED ACTIONHUMAN AUTHORITY AUTHORISED RETRIEVAL

3–8s

Typical time to first token

0

Actions executed without human approval

100%

Answers carrying source citations

On-prem

Private model hosting supported

Capabilities

What AUGUR does.

Authorised retrieval, not filtered answers

The retriever applies the caller's clearance and need-to-know before any document reaches the model. Nothing is retrieved and then hidden — it is never retrieved at all.

Caller-scoped retrievalCompartment awareNeed-to-know enforcedNo post-hoc filtering

Cited, confidence-bearing output

Every assertion links to the observation or report behind it. Source and inference are visibly distinguished so analysts can tell what the model read from what the model concluded.

Inline citationsConfidence bandsSource vs inferenceContradiction flagging
Plintir · AUGUR · Mission copilotPrivate on-premise model · domain-authorised Synthetic data
Summarise what changed in AO GRANITE over the last 12 hours, and flag anything that contradicts the 0400 assessment.

Advisory output · retrieval scoped to caller

Three material changes in the last 12 hours.

1 · Track TK-4471 was associated to ENT-8890 at 0912Z on correlated signals and imagery, confidence 0.87 OBS-2291.

2 · Vehicle count at FAC-0093 rose from 4 to 11 IMG-7714.

3 · CONTRADICTION — the 0400 assessment ASM-0088 placed the same entity 240 km south, citing one report whose source reliability was downgraded at 1120Z. Both cannot hold. I have not resolved this; an analyst should adjudicate.

▲ Proposed action · requires human authorisation

Create collection request CR-2291 against gap G-14 and route to the collection manager.

Policy check · PASSED at execution time
Authority required · Collection manager or above

Authorise Decline

Audit trail · this session

14:22:41identity

Query received · caller a.reyes · clearance attributes evaluated

14:22:41retrieval

Scoped to caller — 2,104 of 8,880 candidates authorised

14:22:42routing

Routed to private on-premise model, domain-authorised

14:22:51output

7 citations attached · sensitivity inherited from sources

14:22:52gate

Action proposed — awaiting human authorisation

The gate is architectural. The copilot can propose a collection request; it cannot create one. Authorisation is checked when the action executes, never inherited from the model's earlier reasoning.

Human authorisation on every action

Agents may propose collection requests, task assignments, escalations and updates. Execution requires an authorised identity, an execution-time policy check and an immutable audit record.

Approval gatesExecution-time policyNamed authorityImmutable audit

Model choice without lock-in

Route between private on-premise models, accredited services and specialised models by data handling level, with continuous evaluation and red-team testing before and after deployment.

Model gatewayDomain-bound routingContinuous evalsInjection defences
Plintir · AUGUR · Model routing & assurance6 registered models · continuous evaluation Synthetic data
ModelHostingAuthorised toAccuracyRefusal qualityStatus
private-70bOn-premiseCOMPARTMENTED
0.94
0.97
LIVE
private-8b-edgeEdge nodeU//FOUO
0.88
0.95
LIVE
vision-imageryOn-premiseU//FOUO
0.91
0.93
LIVE
transcribe-multiSovereign cloudCONTROLLED
0.86
0.90
LIVE
summarise-fastSovereign cloudPUBLIC
0.79
0.84
CANARY
external-api-xCommercialPUBLIC ONLY
0.92
0.71
BLOCKED HIGH-SIDE

Capability does not override handling. The commercial endpoint scores well and is still blocked from classified traffic, because routing is decided by data handling level rather than benchmark position.

Deploys where you work

One platform, every environment.

AUGUR runs identically in commercial cloud, sovereign cloud, on-premises, high-side and fully air-gapped estates, and degrades predictably at the tactical edge.

Sovereign cloudOn-premisesHigh-side Air-gappedTactical edgeCoalition workspace Zero trustAttribute-based accessImmutable audit

Next step

See AUGUR against your own mission thread.

We run briefings on a real mission problem you bring, not a scripted demonstration. Bring the question your analysts cannot currently answer.