Add runtime controls
without re-platforming your stack
Start by governing the workflow you already run. KLA supports govern-in-place instrumentation for existing frameworks and a more managed run-through-KLA pattern when you want tighter operational control.
SDK-first Telemetrie
Govern existing frameworks with SDKs and OpenTelemetry.
Execution-API
Insert approval checkpoints and intercept risky actions at runtime.
Nachweis-Export
Generate execution lineage that trust and compliance teams can reuse later.
Deployment patterns
Technical evaluators need to know whether KLA forces a rewrite. It does not. Pick the control pattern that matches your stack and governance maturity.
Govern in place
Instrument the agents, APIs, and orchestration frameworks you already operate, then add checkpoints at the moments that matter.
- Best for existing LangChain, custom orchestration, and internal workflow stacks
- Low-friction path for platform teams avoiding re-platform fear
- KLA focuses on controls, approvals, and proof rather than replacing your app
Run through KLA
Route execution through a managed KLA surface when you want tighter standardisation and a faster path to controlled production.
- Best for greenfield governed workflows or fragmented estates
- Reduces local integration work when teams want one control surface
- Uses the same approval, policy, and lineage model as govern in place
Schnellstart
Von null Instrumentierung zu gesteuerter Ausführung und Nachweis-Export.
1. Telemetrie-SDK installieren
Nutzen Sie unsere OpenTelemetry-SDKs, um GenAI-Spans automatisch zu senden. Wählen Sie Ihre Runtime:
# Node.js pnpm add @kla-digital/otel-node # Python pip install kla-otel-python
Das SDK erkennt gängige Frameworks automatisch (Express, FastAPI, LangChain, OpenAI).
2. OTLP auf KLA verweisen
Konfigurieren Sie Ihren OTLP-Exporter, um Traces an den Collector Ihres Tenants zu senden. Sie erhalten den Endpunkt und API-Token in der Konsole.
OTEL_SERVICE_NAME=claims-service OTEL_EXPORTER_OTLP_ENDPOINT=https://<your-collector-endpoint> KLA_TENANT_ID=<your-tenant-id> KLA_PII_MASK=true
Setzen Sie `KLA_PII_MASK`, um standardmäßig sensible Werte in Traces zu vermeiden.
3. Agent registrieren
Agenten werden als Manifeste deklariert. Erstellen Sie einen über die Execution API:
curl -X POST https://api.kla.local/execution/v1/agents \
-H "Authorization: Bearer $KLA_TOKEN" \
-H "x-tenant-id: $KLA_TENANT_ID" \
-H "Content-Type: application/json" \
-d '{
"name": "claims-bot",
"description": "Triages inbound claims with human gates",
"model": "gpt-4o-mini",
"temperature": 0.2,
"tools": ["search_claims_db"]
}'Die Antwort enthält eine stabile `agentId` und einen unveränderlichen `manifestHash`.
4. Ausführung starten
Ausführungen sind dauerhafte Workflows mit Budgets und Policy-Checks.
curl -X POST https://api.kla.local/execution/v1/executions \
-H "Authorization: Bearer $KLA_TOKEN" \
-H "Content-Type: application/json" \
-d '{
"agentId": "<agentId from step 3>",
"input": { "prompt": "Summarise today\u0027s high-risk claims." },
"budgets": { "maxSteps": 50, "maxTokens": 20000, "maxCostUsd": 5 },
"flags": { "euOnly": true }
}'Streamen Sie den Fortschritt über WebSocket unter `wss://api.kla.local/execution/ws`.
5. Nachweise exportieren (Annex IV, SOC 2)
Das CLI lädt manipulationssichere Audit-Logs und generiert signierte Pakete, die für Regulierungsbehörden und Auditoren bereit sind.
# Last 30 days as PDF kla export evidence --tenant $KLA_TENANT_ID --days 30 --format pdf # Filter by framework or controls kla export evidence --tenant $KLA_TENANT_ID --frameworks "SOC 2 Type II" --format csv
Offizielle SDKs
Sprachnative OpenTelemetry mit GenAI-Semantic-Conventions.
Node.js
Zero-Config-Auto-Instrumentierung für Express, tRPC, LangChain, OpenAI und mehr.
import '@kla-digital/otel-node';
Python
Drop-in FastAPI-Middleware und LangChain-Auto-Instrumentierung mit integrierter PII-Maskierung und Cost-Tracking.
import kla_otel_python