Hash-Chained Audit Logs: Tamper-Evident Compliance for AI Decisions
A hash-chained audit log records every decision in a way that makes tampering detectable: each entry includes a cryptographic hash of the…
Meet DeepintShield at Bengaluru Tech Summit 2026, 17 to 19 November, BIEC Hall 1, booth H1A106. Book 20 minutes
Platform · Observability & Audit
LLM observability shows what your AI systems are doing: requests, tokens, cost, latency, agent runs, tool calls and policy verdicts. DeepintShield records them on the request path, exports metrics and traces through OpenTelemetry and Prometheus, and keeps agent decisions in a hash-chained ledger you can verify.

Cost, latency and guardrail results sit in different tools, so nobody sees one request from end to end.
One agent task spans many model and tool calls, and plain application logs do not link them.
Ordinary logs can be changed without anyone noticing, which weakens them as audit evidence.
Telemetry is captured where the traffic already flows: at the gateway that every model and tool call passes through. See how DeepintShield works.
Requests, responses, tokens, cost and latency are logged to SQLite by default or PostgreSQL.
Agent decisions are written to an append-only, hash-chained ledger before the call proceeds.
OpenTelemetry, Prometheus, scheduled log exports and durable webhooks feed the tools you already run.
Verify chain, in the console or through the API, recomputes the hashes and exposes any break.
OTLP over HTTP or gRPC with GenAI conventions. Documented setups for Grafana Cloud, Datadog, New Relic, Honeycomb and Langfuse.
Cost, cache hits, time to first token and inter-token latency, labelled by key, team, customer and routing rule.
Runs, Decisions, Trends and Audit views, with each decision tagged against the OWASP Agentic Top 10.
Workspace-scoped and append-only. Production requires an HMAC key, so a database writer cannot quietly rebuild the chain.
Daily, weekly or monthly exports to S3, Google Cloud Storage, Azure Blob, Snowflake, Redshift or BigQuery, including MCP tool logs.
At-least-once, HMAC-signed delivery of control-plane events, with idempotency keys, a dead-letter queue and replay.
Agentic observability covers agent decisions, which need Agentic Security on the Business plan and above.
Total requests, success rate, average latency, tokens and cost, a request-volume chart and the request list on one screen.
Tap to enlarge(opens the full-size image in a new tab)Send traces to any OpenTelemetry collector and expose metrics to Prometheus from Integrations › Observability. Turn on Disable Content Logging to keep prompt and response text out of the store.
Tap to enlarge(opens the full-size image in a new tab)One request's timings, provider, model, virtual key, tokens, cost, input and response in a single panel, ready to share with a reviewer.
Tap to enlarge(opens the full-size image in a new tab)Each ledger record holds the hash of the record before it, so a change anywhere breaks the chain. The audit log is on by default and uses the CADF format with a SHA-256 hash chain. Tool arguments in agent decisions are stored as a cryptographic digest, and evidence is kept for 730 days by default. For framework mapping and auditor workflows, see AI Compliance.
The telemetry plugin is on by default and serves Prometheus metrics at /metrics; clusters can push to a Push Gateway instead. OpenTelemetry export uses OTLP over gRPC or HTTP, with a push interval of 15 seconds by default. Add your own Prometheus labels per request with x-deepintshield-prom-* headers.
# Prometheus scrape target
deepintshield-host:8080/metrics
# OpenTelemetry (OTLP)
4317 gRPC
4318 HTTP
# Example metrics
deepintshield_cost_total
deepintshield_cache_hits_totalMapped to
Audit logging supports SOC 2, GDPR, HIPAA and ISO 27001 evidence collection. Mapping supports your own assessment; it does not replace it.
A hash-chained audit log records every decision in a way that makes tampering detectable: each entry includes a cryptographic hash of the…
DeepintShield team · · 4 min read

EU AI Act Readiness: Practical Controls for GenAI EU AI Act readiness begins with a clear account of what a system does…
DeepintShield team · · 5 min read

Self-Hosted vs SaaS AI Security: Compare Data Flows Choosing where to run an AI security gateway is also a choice about who…
DeepintShield team · · 5 min read
LLM observability is the practice of recording and measuring what language-model applications do, from tokens and cost to tool calls and policy decisions. It lets platform, security and finance teams answer their questions from one set of data.
Logs are stored in SQLite by default, or in PostgreSQL, inside the deployment that serves your traffic. In hybrid and self-hosted modes, no data leaves your environment. Compare the deployment options.
Any OpenTelemetry backend over OTLP, with documented setups for Grafana Cloud, Datadog, New Relic, Honeycomb, Langfuse and self-hosted collectors, plus Prometheus. Scheduled log exports go to S3, Google Cloud Storage, Azure Blob, Snowflake, Redshift and BigQuery.
Each record includes the hash of the record before it, so editing or deleting one breaks every later link. Verify chain recomputes the chain, and in production an HMAC key stops anyone with database access from rebuilding it unnoticed. Read the agentic observability docs.
Agent decision evidence is kept for 730 days by default, and you can change the retention period. Durable webhook deliveries are retained for 720 hours.
Map controls and evidence to NIST AI RMF, ISO/IEC 42001, the EU AI Act and OWASP.
Explore AI compliance
Allow, Deny or Require approval for every agent tool call, with each decision on the ledger.
Explore agentic security
Turn cost and cache-hit metrics into savings with caching, routing and prompt compression.
Explore cost optimization
Start free and send your first requests through the gateway, or book a demo to walk through the audit trail.