Blekline
v0.3.0GitHub

Integrations

Eval and Safety Partners

L3 eval and post-model safety integrations complementary to Blekline.

View as Markdown

Blekline operates before model and tool execution. These partners operate after or alongside for quality and output validation.

Positioning

ProductLayerRole
BleklineL4Mask, enforce, audit at MCP ingress
LangSmithL3Eval, traces, datasets — consumes audit metadata
Guardrails AIL3/L4Post-model output validation — optional second layer

Data flow

Agent → Blekline (allow/block) → Model/Tools → Guardrails (optional output check) → User
                ↓
           LangSmith (eval traces, metadata only)

LangSmith is not a SIEM. For compliance export see Enterprise telemetry.


Next steps: Trust boundaries · Telemetry spec · AI Enablement Stack · Open workspace