ModelsParticula-Legal
Clauses and risk flags,privilege intact.
Particula-Legal pulls key clauses out of contracts and flags risk against your playbook, with a citation to the exact language on every flag. On-prem by design: no third party touches the document and privilege stays intact.
ON-PREM · PARTICULA-LEGAL
$ POST /v1/review · msa_draft_v3.pdf
→ particula-legal · privilege-safe
→ "clause": "liability_cap" · "risk": "high"
→ "missing": "indemnity carve-out"
✓ 200 · 62 ms · on-prem
ready
PARTICULA-LEGAL · ON-PREM · ZERO TELEMETRY
What it doesSee it on your data
Clause extractionLiability caps, indemnities, termination, assignment, and governing law from MSAs, NDAs, leases, and vendor paper.
Risk flags against your playbookEncode your standard positions once. The model flags deviations and missing carve-outs, not generic boilerplate warnings.
Privilege-safe by designRuns on-prem with no external calls, so review work product never touches a third party and privilege arguments stay clean.
A citation on every flagEach flag links to the exact clause language it came from. Counsel verifies in one click instead of re-reading the document.
Spec sheetCompare all six
Context window64K tokensA full MSA with schedules fits in one request.
Median latency62 ms medianBatch 1 on the reference single-GPU deployment. Our own measurement: the shipped harness reproduces it on your hardware.
InterfaceOpenAI-compatible RESTServed by vLLM, deployed with Docker Compose or Helm. Drop-in for existing OpenAI client code.
Hardware1× 48 GB GPUL40S or A6000 class, on-prem. Sizing reviewed before the pilot.
Fine-tuningLoRA on your dataTuning jobs are included with Enterprise. A few hundred labeled examples from your pipeline is usually enough to move the needle.
How deployment worksStart at step 01
01Discovery call
30 minutes, no slides. Your task, your data shape, and the security constraints around it. If this model is the wrong fit, we say so on the call.02Pilot install
Containerized deployment to staging in your VPC or on-prem, on the same stack as Lumen and Notetaker. The eval harness runs on your data and the numbers go into the pilot agreement.03Production rollout
Runbook handoff, operator training, and 90 days on call. After that it is yours to operate, no vendor dependency.More modelsAll six models
Request a demo
“Bring a hundred real examples from your pipeline. We run the model on them live, the harness scores the output in front of you, and you decide with numbers instead of a sales deck.”
Sebastian Mondragon, Founder of Particula Tech
Request a demo30 minutes · no sales deck