Meet us at RSAC 2026 to explore runtime security for agentic workloads.
Solutions

Visibility &
Observability

See what every agent is doing, who it's talking to, and what was allowed or denied — captured automatically, streamed to your existing stack.

Your CISO Asked "What Are Our Agents Doing?"

"Not a vague answer — nothing. Your APM shows service-level traffic. Your logs show what the agent framework decided to log. But when the CISO asks 'which agents accessed customer data last Tuesday, and on whose authority?' — you're guessing."

— VP Engineering, AI-native startup

No agent-level visibility

APM tools show pod-to-pod traffic. They can't tell you which agent process made which request, or distinguish one agent from another on the same host.

No audit trail

When an agent calls an external API, there's no immutable record of which agent, which identity, which policy allowed it. Agent-side logs can be suppressed, modified, or simply not implemented.

No behavioral baseline

Agents exhibit dynamic behavior — they decide at runtime which tools to call. Without a kernel-level baseline, you can't detect when an agent starts doing something it's never done before.

No incident investigation path

A prompt injection happened. Which agent? What did it try to reach? Was it blocked? How long was it active? Without agent-aware telemetry, your SOC team is blind.

No cost attribution

LLM API bills arrive as a single line item. When costs spike, you can't tell which agent, which user, or which workflow is responsible.

Sound familiar?

If you lead security or AppSec This is the visibility gap that makes agent deployments a compliance risk. You can't prove controls you can't observe.
If you lead AI/ML platform engineering This is what your security team needs before they'll approve production. Give them this, and agents ship.

Identity-Aware Observability

Every agent connection captured automatically at the kernel level. Every event tied to the agent's SPIFFE identity. Streamed to your existing observability stack. No agent code changes.

2

Identity on every event

Each connection is tagged with the agent's identity, the policy that was evaluated, the decision (allow/deny), and which credential was used. Your SIEM receives structured events, not raw logs.

3

Stream to your existing stack

Connection events stream to your observability pipeline: OpenTelemetry, Datadog, Splunk, Elastic, or any SIEM. Native integrations, standard formats. No new dashboard to adopt.

4

Real-time alerting

Alerts fire when agents exhibit unexpected behavior — new destinations, traffic volume spikes, off-hours activity, sudden deny patterns.

What Changes for You

Answer the CISO's question in minutes

Which agents accessed what, when, and under which policy. Cryptographic identity on every event — not pod IPs, not container names.

Agents can't hide their activity

Telemetry is captured at the kernel, below the application layer. Agents can't suppress, modify, or omit their connection logs. What the kernel sees is what your SIEM receives.

Policy decisions, not just connections

You don't just see that a connection happened. You see the policy rule that allowed or denied it, and the full evaluation context. This is the audit trail compliance requires.

No agent code changes

No logging SDK to integrate, no OpenTelemetry instrumentation in agent code. Works with LangChain, CrewAI, AutoGen, LangGraph, and any framework. The kernel module captures everything automatically.

Why not just...

Application-layer logging or an AI gateway?

Application-layer logging depends on the agent framework logging correctly — and on the agent not being compromised in a way that suppresses its own logs. AI gateways see traffic that flows through them, but agents can make direct connections that bypass the gateway. Kernel-level capture is comprehensive and tamper-proof: every TCP connection from the agent process is captured regardless of framework, configuration, or compromise state.

Where to Start

The Fastest Win

Deploy in Observe Mode — Value in Hours

Deploy Riptides on the cluster where your agents run. Before enforcing any policies, you immediately get full visibility: every connection every agent makes, tied to its identity, streamed to your SIEM.

This is the deployment that answers the CISO's question — and unblocks the production approval conversation.

ALLOW research-agent → api.openai.com:443
ALLOW research-agent → db.internal:5432
DENY  research-agent → evil.exfil.com:443
DENY  research-agent → evil.exfil.com:8443
Then Expand

Establish behavioral baselines

Let agents run under observation. Build per-agent profiles of normal behavior: which destinations, what frequency, what patterns.

Enable anomaly alerting

Flag when agents deviate from their baseline — new destinations, unusual volumes, off-hours activity.

Add enforcement

Once you see what's happening, lock it down with egress policies and credential injection.

Application Logging vs. AI Gateway vs. Riptides

Application-Layer Logging AI Gateway Riptides
Identity granularity Service or pod level Request-level (if routed through gateway) Per-agent SPIFFE identity
What's captured What the framework logs Traffic through the gateway Every connection at the kernel
Agent can suppress logs Yes Can bypass gateway No — kernel captures independently
Covers direct connections Only if instrumented No — only proxied traffic Yes — all TCP connections
Policy context None Gateway rules Full policy evaluation: rule, decision, reason
Credential exposure API keys in HTTP logs API keys visible to gateway Credential name only (never the secret)
Code changes Logging SDK, instrumentation Route traffic through proxy None
Audit posture "We log what the framework provides" "We log what flows through the gateway" "Every agent connection is captured with SPIFFE identity"

Ready to secure your
workloads?

Kernel-level identity and enforcement. No code changes. Deploy in minutes.