Trust: data, failures, streaming, and deployment

This page answers the questions reviewers ask before they route traffic through ValGuard. Where does data go? What happens when something fails? What does streaming cost? How do you evaluate without a local runtime? Where a limit exists, we state it.

Last reviewed: 2026-10-02.

Related: Security · Privacy · DPA · SLA · Self-host docs

What ValGuard is

ValGuard is a runtime validation and policy-enforcement layer for LLM calls and agent steps. Deterministic rules run on every completion before the next model, tool, or customer-facing action. It includes a lightweight step graph so rules apply at handoffs. It is not a general workflow engine, connector platform, or durable-execution system.

Data flow

  1. Your app or agent SDK sends an OpenAI-compatible chat request to ValGuard.
  2. Optional input validators run on the prompt.
  3. ValGuard forwards the request to the provider you configured, or to a custom endpoint in Provider Vault.
  4. Output validators run on the completion, or on the assembled stream for streaming calls.
  5. The response returns to your app with validation headers such as X-VG-Validation-Status.

What we store. By default, request metadata for billing, limits, and observability. We do not write prompt or completion text unless you turn on payload logging for an agent.

If you enable payload logging. Content is kept for the period you set, up to your plan's cap. The caps are 7 days on Free and Developer, 30 on Growth, 90 on Production, and 365 on Enterprise. A daily job removes expired payloads.

Provider keys. Keys in Provider Vault are encrypted at rest with AES-256-GCM. We use them only to call the providers you configure.

Self-host license checks. On Enterprise self-host, a heartbeat sends license status to ValGuard cloud. It carries no customer AI payloads.

Evaluating without a local runtime

There is no public Docker image or open-source hosted runtime. The open-source ValGuard CLI runs local fixture tests against validator rules; the full OpenAI-compatible gateway and playbook path are evaluated on hosted shadow mode or licensed Enterprise self-host.

Hosted shadow mode is not local or offline evaluation. Requests still pass through ValGuard and the configured model provider, even when payload logging is off. Start with synthetic or sanitized test cases if your data policy permits hosted processing.

If your policy prohibits that processing, hosted shadow mode does not satisfy it. Review the licensed Enterprise self-host option with your security team before sending sensitive data.

In shadow mode enabled rules run on the traffic you send. Failures are logged. Nothing is blocked by those rules. Shadow mode is available on every plan, including Free.

Review the would-block rate, tune the rules, then turn enforcement on. The shadow mode rollout tutorial walks through it, and the blog post on validating before you enforce explains why.

One caveat applies to playbooks. Shadow mode is a per-agent setting. If an agent is a step in a playbook, a failure on that step does not trigger block routing while shadow is on. Turn it off on any step you want to gate before the playbook goes live.

Streaming

If any enabled rule can block or re-ask, ValGuard buffers the full reply before it sends a token. The user waits for model completion and validation before seeing output. A re-ask adds another model attempt to that wait.

Warn, log, and shadow mode can pass tokens through, but they do not stop a violating reply from reaching the user. Choose buffering when an output must pass checks before release. Do not relax a required blocking policy just to preserve streaming.

Measure time to first visible token and time to a complete accepted reply separately. Engine microseconds and mocked HTTP latency do not measure this UX cost. See benchmark methodology.

Failure modes

A rule fails. You choose the action per rule: block, reask, warn, or log. A block returns a block envelope instead of the model's text. A re-ask sends the request to the model again, within your plan's re-ask limit.

ValGuard is unreachable. The request fails. ValGuard does not skip rules and pass the call through. If your feature must survive an outage, build the fallback in your client: call the provider directly, queue the work, or degrade the feature. That choice stays with you, and it should be explicit.

ValGuard is an additional availability dependency on the model request path. An SLA is a service commitment, not a client recovery mechanism. Test your outage behavior before enforcing rules in production.

Client response to an outageConsequenceOwner
Fail the request or return a fixed safe responseNo unvalidated model output is released; the feature is unavailable or reducedYour application
Queue work for laterProcessing is delayed; retries and side-effect deduplication need explicit handlingYour application
Call the provider directlyValGuard rules and its validation audit are bypassed for that requestYour application and risk owner

Do not treat a direct-provider fallback as equivalent protection. For an action that requires validation, stop or defer it until the required checks can run.

The provider fails. Provider errors and open circuit breakers affect the model call. Validators do not invent a completion when the provider returns nothing.

Availability

PlanCommitment
Free, Developer, GrowthBest effort. No financial uptime credits.
Production99.5% monthly uptime. See the SLA.
EnterpriseUp to 99.99%, as set in the order form.

Current service status is on the status page.

Evidence for review

The linked security, privacy, and DPA pages describe controls and contractual terms. They are not independent attestations.

The benchmarks are ValGuard's own measurements. The methodology explains the mocked upstreams and reproduction limits; it is not an independent performance assessment.

This page does not provide a public pentest summary, SOC 2 report, ISO 27001 certificate, or independently verified customer error-reduction study. Do not infer those assurances from product descriptions or blog examples.

Per-request guardrail evidence (product): Growth+ request Proof panels can download an HMAC-signed envelope with policy snapshot hash, ordered validator verdicts, and SHA-256 digests of request/response. Digests only — the envelope does not store raw prompts. Verify in the UI or with valguard-cli verify-proof. That is execution evidence for this deployment, not absolute non-repudiation and not a customer compliance certification. Details: how to prove AI guardrails actually executed.

For procurement, ask our team which assessment artifacts are available for your review. Check their scope, date, assessor, and outstanding findings before treating them as evidence. Availability must be confirmed, not assumed.

Deployment

Default: hosted SaaS.

Enterprise self-host: the same web app, Go engine, Postgres, and Redis in your VPC or on-prem, under a license. It is not a free or open-source runtime. See the self-host docs and pricing.

Portability

Playbooks export as JSON (valguard-playbook-template/1). The file holds agents and, optionally, their validator rules. The same format imports through a validate-then-apply flow. Per-agent validator lists and audit export are also available through the API.

Export works per playbook and per agent today. A single org-wide policy file is on the roadmap. Until it ships, do not plan around a full org export.

What this page does not claim

Passing configured rules does not establish that an answer is true, complete, or useful. For example, a reply can match a JSON schema and contain no PII while giving the wrong refund deadline.

Grounding overlap is a bounded check, not proof that a source supports every claim. Use domain-specific evaluation cases and human review where meaning matters. A model judge can supplement those checks, but its verdict also needs evaluation.

  • ValGuard does not prevent every hallucination. It catches structural, policy, numeric, and grounding-overlap failures that you encode as rules.
  • ValGuard does not evaluate model quality. Evals measure the model. Validation enforces a contract at runtime.
  • ValGuard does not replace n8n, Temporal, or LangGraph when you need connectors, schedules, or durable execution.