Skip to content
Vellum → EvalGuard

Bring your executions. Get security with your evals. 

Vellum runs your prompt and workflow executions. EvalGuard imports that run history and adds red team (300+ plugins), an LLM firewall, and a BYOK gateway alongside prompt and eval tooling — one workspace, one bill.

SOC 2 evidence engineISO 42001 mappedEU AI ActGDPR

Prompts + evals were the start

What you keep — and what you gain

Keep
  • Prompt- + workflow-execution history
  • Model + provider per execution
  • Inputs + outputs (variables and completion blocks)
  • Token usage — prompt / completion / total
  • Cost + latency per run
  • Execution state + model parameters
Gain
  • + Real-time LLM firewall (input + output)
  • + 300+ red-team plugins with threat-feed sync
  • + 200+ eval scorers (LLM-as-judge, pairwise, rubric)
  • + Prompt IDE + optimizer across 90+ providers
  • + Managed BYOK gateway with semantic caching
  • + 50 compliance frameworks + tamper-evident audit log

Backfill your history

Bring your Vellum executions along

Export your executions from Vellum (the /v1/workflow-executions or /v1/prompt-executions API), then convert them with the EvalGuard CLI. Both shapes are accepted, no record is dropped, and re-running the same import never double-counts, because spans use a stable content hash.

# Convert your Vellum export to neutral-shape spans:
npx @evalguard/cli import:traces --from vellum vellum-export.json --output spans.json

Prints an import summary (spans imported / duplicates skipped / parse errors) and writes the neutral spans to spans.json. This is an execution-history import — it moves your run logs, not your Vellum prompt deployments or workflow definitions.

What importsWhere it lands
Workflow + prompt executionsOne EvalGuard span each, grouped by trace id
Model + providerspan.model / span.provider
Inputs / outputsspan.input / span.output
Token usage (prompt / completion / total)span.promptTokens / completionTokens / totalTokens
Costspan.costUsd
Latencyspan.durationMs (latency_ms, or start / end)
Execution state + model params + metadataspan.attributes (vellum.* namespace)

Failed executions (state: FAILED) are imported with status: error so your failure history survives the move. Everything else the importer recognizes is preserved verbatim under span.attributes.

One platform, one bill

Ship prompts. Secure, eval, optimize — everywhere.

Prompt tooling is the hook. The platform is why you stay.

Start free