Vellum

The Agent Node documents tool calling with automatic function-calling schema generation and loop logic, with tools drawn from custom code, subworkflows and API calls, a dedicated page on function calling with chat models, and a worked example of parallelised function calls. The API Node makes authenticated HTTP requests to any endpoint and the Code Execution Node runs custom Python or TypeScript, and a Zapier and Airtable example and a Datadog export are documented. Documented custom tool support that lets an agent act in outside systems is Full.

Sourcedocs.vellum.ai Agent Node, API Node, Code Execution Node and function-calling pages, 31 August read, re-gradedread 2026-09-29

Fifteen documented node types cover an Agent Node with automatic schema handling and loop logic, prompt and prompt-deployment nodes, templating, a search node, an API node, a code execution node running Python or TypeScript, subworkflow, map, guardrail, conditional, merge, final output, error and note nodes. Node adornments apply retry and try semantics to existing nodes.

Advanced documentation covers long-running workflows and batching executions. Multi-agent composition appears through subworkflows and worked examples including multi-agent content creation and LLMs debating each other, and six common architectures are documented covering RAG, escalation to a human, prompt retry, PDF summarization and fallback models.

Sourcedocs.vellum.ai workflows nodes overview and per-node pages, node-adornments, advanced long-running-workflows and batching-executions, common-architectures and examples pagesread 2026-08-31

A Documents section documents uploading documents into a Document Index, integrating with a Search API, and metadata filtering for scoped retrieval. A dedicated Search Node searches against a Document Index and is described by the vendor as suited to RAG.

A RAG system appears as one of the documented common architectures, with worked examples covering a basic RAG chatbot, a RAG chatbot with Cohere rerank, and a building-a-RAG-chatbot tutorial. Evaluating RAG pipelines has its own documentation page under Evaluation and Test Suites. Documents persist as an index between runs rather than being assembled per request.

Sourcedocs.vellum.ai documents section, workflows nodes search-node, common-architectures rag-system, workflow examples and evaluation/evaluating-rag-pipelines pagesread 2026-08-31

The platform documentation offers a Guardrail Node that runs an inline evaluation against a pre-defined Metric inside a workflow, Error and Conditional nodes that stop or branch execution, Retry and Try adornments, release reviews before a change is promoted to a live deployment, role-based access control, and an Escalation to a Human architecture that automatically routes sensitive or complex messages to human operators.

Those are runtime constraints, a design-time release step and workflow-initiated escalation. The documentation index shows no approval node or pause for a person to approve an agent's action before it executes.

Sourcedocs.vellum.ai documentation index, Escalation to a Human, Guardrail Node and release reviews pagesread 2026-09-29

The vendor's data privacy and storage page states that Vellum maintains SOC 2 Type 2 compliance and is HIPAA compliant, with security practices regularly audited to meet industry standards and healthcare data protection requirements. All data stored in Vellum, including documents in Document Indexes, is encrypted with AES-256 GCM in transit and at rest.

The vendor states it does not send interactions or feedback to LLM providers for training, and that Completion Actuals submitted through the feedback API are stored for the customer's own quality monitoring rather than used to train or fine-tune models. Documented controls include role-based access control, HMAC authentication for verifying request origin, static IPs for customer-side allowlisting, organization access management and configurable data retention policies.

Sourcedocs.vellum.ai security section covering data-privacy-and-storage, rbac-permissions, hmac-authentication and static-ips, and organizations manage-access and pagesread 2026-08-31

Observability in production is documented as its own capability, alongside monitoring of production trends, tracking of workflow execution costs, and execution URLs addressing individual runs. A Datadog integration and a webhook integration export execution data to the customer's own monitoring and alerting systems. Online evaluations score production traffic on defined metrics. Deployment lifecycle management, environments and release tags tie each execution to a specific released version. Data retention policies are documented separately at organization level.

Sourcedocs.vellum.ai deployments observability and deployment-lifecycle-management, monitoring section covering production-trends, execution-cost-tracking, datadog, webhooks and execution-urls, evaluation online-evaluations, and organizations pagesread 2026-08-31

A Document Index persists uploaded material between runs and is queryable through a Search Node or Search API. Long-running workflows are documented for executions that extend beyond a single request, and deployment lifecycle management, environments and release tags persist configuration and version history across releases. No memory module, conversation store, session identity or cross-execution context capability appears anywhere in the Product documentation navigation, and workflows are documented as invoked per execution through the deployed API.

Sourcedocs.vellum.ai workflows advanced long-running-workflows, documents section, deployments section and Product navigation indexread 2026-08-31

Self-hosting is a top-level documentation section alongside Home, Product and Developers, with its own getting-started introduction. Static IPs are documented under both Security and advanced workflow behavior, providing fixed egress addresses for customer-side allowlisting. Data retention policies are configurable at organization level, and a data privacy and storage page documents how data is held. Managed deployment covers deployment lifecycle management, environments and release tags for promoting versions.

Sourcedocs.vellum.ai self-hosting introduction, security static-ips and data-privacy-and-storage, workflows advanced static-ips, organizations and deployments pagesread 2026-08-31

Twelve named workflow examples are documented covering prompt chaining, basic RAG chatbot, RAG with Cohere rerank, customer support bot, PDF to CSV, summarizing images of websites, parallelized function calls, conference attendee lookup, multi-agent content creation, LLMs debating each other, a Zapier and Airtable integration and automating PR reviews.

Six common architectures cover RAG systems, escalation to a human, prompt retry logic, PDF content summarization and fallback models. Out-of-the-box metrics are supplied by the vendor and reusable across test suites, and subworkflows let customers make their own work reusable. Whether examples are importable into a workspace in one action, rather than followed as documentation, is not stated.

Sourcedocs.vellum.ai workflow examples overview, common-architectures, metrics out-of-the-box-metrics and reusing-metrics, and workflows nodes subworkflow-node pagesread 2026-08-31

Workflows are invoked programmatically through a deployed API, with a dedicated integrating page covering calling them from application code, plus batching executions for volume and long-running workflows for extended jobs. The webhook integration documented under Monitoring pushes execution data outward to customer systems rather than accepting inbound events to start a workflow. No scheduled, cron, event-driven or chat-channel trigger appears anywhere in the Product documentation navigation.

Sourcedocs.vellum.ai workflows api-integration, advanced batching-executions and long-running-workflows, monitoring webhooks and execution-urls pages, and Product navigation indexread 2026-08-31

A Custom Models page documents bringing models beyond the built-in roster, and prompt engineering documentation covers comparing prompts across models. Fallback models are documented as one of Vellum's common workflow architectures. Prompt caching and multimodality have their own pages under Prompts.

Model choice is coupled to measurement through test suites and metrics, so switching providers can be evaluated quantitatively rather than by inspection. Prompt deployment nodes execute deployed prompts within workflows, and release tags and environments govern which prompt version, and therefore which model configuration, is live.

Sourcedocs.vellum.ai prompts custom-models, prompt-engineering, prompt-caching and multimodality, workflows common-architectures fallback-models, and deployments pagesread 2026-08-31

A Developers section sits at the top level of the documentation covering SDKs, APIs and developer tools. Workflows deploy to an API with a dedicated page on integrating them into application code, and a Search API reaches the Document Index independently of workflows. Webhook integration exports execution data, and execution URLs address individual runs. A Code Execution Node runs customer Python or TypeScript within a workflow, and HMAC authentication verifies request origin for callbacks.

Sourcedocs.vellum.ai developers overview, workflows api-integration, documents api-integration, monitoring webhooks and execution-urls, workflows nodes code-execution-node and security hmac-authentication pagesread 2026-08-31

Quantitative evaluation is documented through Test Suites and Metrics, with the vendor stating that prompt changes, parameter adjustments and model switches make regression likely and that quantitative evaluation is the answer. Metrics are documented as out-of-the-box, custom, and reusable across test suites.

Online evaluations extend scoring to production, and evaluating RAG pipelines is documented separately. A Guardrail Node runs an inline evaluation using a pre-defined Metric within a workflow. Experimentation and a prompt playground support side-by-side comparison across models, and Retry and Try node adornments handle failure paths during development.

Sourcedocs.vellum.ai evaluation section covering quantitative-evaluation, online-evaluations and evaluating-rag-pipelines, metrics section, and workflows nodes guardrail-node and node-adornments pagesread 2026-08-31

The Product documentation enumerates fifteen node types and none provides browser, desktop or computer-use capability: the external-action nodes are an API Node making HTTP requests to an endpoint, a Code Execution Node running custom Python or TypeScript, and a Search Node querying a Document Index, with tool calling handled by the Agent Node through automatic schema generation.

The nearest example, summarizing images of websites, applies retrieval and vision to fetched material rather than navigating or operating a site. No browser automation, session control, form filling or screen interaction appears anywhere in the Product documentation navigation.

Sourcedocs.vellum.ai workflows nodes overview and per-node pages, workflow examples summarize-images-of-websites, and Product navigation indexread 2026-08-31