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.
Telemetria SDK-first
Govern existing frameworks with SDKs and OpenTelemetry.
API di esecuzione
Insert approval checkpoints and intercept risky actions at runtime.
Esportazione evidenze
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
Guida rapida
Da zero strumentazione a esecuzione governata ed esportazione delle evidenze.
1. Installate un SDK di telemetria
Usate i nostri SDK OpenTelemetry per emettere span GenAI automaticamente. Scegliete il vostro runtime:
# Node.js pnpm add @kla-digital/otel-node # Python pip install kla-otel-python
L'SDK rileva automaticamente i principali framework (Express, FastAPI, LangChain, OpenAI).
2. Puntate OTLP verso KLA
Configurate il vostro exporter OTLP per inviare le tracce al collector del vostro tenant. Otterrete l'endpoint e il token API nella Console.
OTEL_SERVICE_NAME=claims-service OTEL_EXPORTER_OTLP_ENDPOINT=https://<your-collector-endpoint> KLA_TENANT_ID=<your-tenant-id> KLA_PII_MASK=true
Impostate `KLA_PII_MASK` per mascherare di default i valori sensibili nelle tracce.
3. Registrate un agente
Gli agenti vengono dichiarati come manifest. Createne uno tramite l'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"]
}'La risposta include un `agentId` stabile e un `manifestHash` immutabile.
4. Avviate un'esecuzione
Le esecuzioni sono workflow durabili con budget e controlli di policy.
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 }
}'Seguite l'avanzamento in streaming via WebSocket su `wss://api.kla.local/execution/ws`.
5. Esportate le evidenze (Annex IV, SOC2)
La CLI estrae i log di audit a prova di manomissione e genera bundle firmati pronti per regolatori e auditor.
# 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
SDK ufficiali
OpenTelemetry nativo per linguaggio con convenzioni semantiche GenAI.
SDK Node.js
Auto-strumentazione zero-config per Express, tRPC, LangChain, OpenAI e altro.
import '@kla-digital/otel-node';
SDK Python
Middleware drop-in per FastAPI e auto-strumentazione LangChain, con mascheramento PII e tracciamento dei costi integrati.
import kla_otel_python