Intrinsec AI Become a design partner

Intrinsec AI · Products

Securing the foundation of the inference stack.

  • KV cache first
  • We never see the prompt
Tessera Plato

Where they sit

Inference engine vLLM · SGLang
KV management layer LMCache
Plato Acts on what doesn't fit. Integrates at the inference engine. Tessera KV cache discovery layer. Integrates at the KV management layer.

KV cache

Tessera.
Surfaces unusual KV pages, wherever they live.

Watch the KV you already keep. Unusual computations surface themselves. Batteries included, and customizable.

  • LMCache
  • vLLM Production Stack
  • Dynamo
  • llm-d
lmcache server --l2-adapter '{
  "type": "plugin",
  "module_path": "tessera.taps.lmcache_l2",
  "class_name": "TesseraL2Adapter"
}'

Design partners

Plato.
Acts on what doesn't fit your inference traffic.

One extra flag on the engine you already run. Off the request path.

  1. 01

    Learn

    The shape of your traffic.

  2. 02

    Surface

    What doesn't fit, classified.

  3. 03

    Act

    We build this with you.

  • Model-agnostic
  • Tags and classes
  • Real-time
Become a design partner Watch the 2-minute demo

2-minute demo · anomalies surfacing against an inference baseline

How Plato attaches

One extra flag.

Off the request path. Your baseline, from your traffic.

  • vLLM
  • SGLang
  • Inference gateways
  • On-prem or cloud
vllm serve $MODEL --kv-transfer-config '{
  "kv_connector": "PlatonicKVConnector",
  "kv_connector_module_path": "platonic_tap.engines.vllm_connector",
  "kv_role": "kv_both",
  "kv_connector_extra_config": {
    "endpoint": "https://api.intrinsec.ai",
    "api_key": "pk_ingest_...",
    "model_id": "$MODEL"
  }
}'

The operator view

What operators see.

Traffic view: detections scored per KV page, with no prompt or response text.
Scores and labels. No prompt content.

What it covers

One baseline.

Attacks and ordinary breakage look the same from the outside. Both are deviations from how your workload normally computes.

  • Prompt injection, jailbreaks, advanced adversarial attacks
  • Sensitive-data exposure
  • Rogue and broken tool calls
  • Hallucination, drift, image, audio, video

Against guardrails

Different signal. Not a bake-off.

Guardrails Plato
Reads Prompt and response text Computation
Sees the prompt? Yes Never
Per tenant Point-in-time Own baseline from the traffic
Surfaces A new rule per modality and failure One baseline

Design partners

A small number of design partners.

You bring a workload; we sit with your team until it proves itself, or doesn't.

Become a design partner