Yair Weinberger

Production agent evaluation must account for changing policies, task-specific outputs, and workflows that can modify external systems. Reindeer evaluates candidate agent revisions against criteria ...

Uncertainty in an agent workflow is not a single confidence score. It appears across a sequence of plans, tool calls, observations, retries, and state-changing actions. Reindeer treats uncertainty ...

Reindeer notifications send workspace events to an outbound webhook destination. The only supported notification event today is run_completion, which fires when an agent run completes. A notificati...

This article explains how Reindeer stores, protects, retains, and deletes customer data, including personal data (PII). For how data is used with large language models, see Data Privacy, Isolation,...

Reindeer webhook connectors receive events from external systems over HTTPS and turn each accepted payload into a record artifact that can trigger an agent workflow. The public receive endpoint is:...

Overview This article summarizes common ways to connect Reindeer to systems that run in an on-premises or customer-managed network. It is intended for infrastructure, network, and security teams ev...

Reindeer API Reference This is a placeholder for the generated Reindeer API reference. Status The API reference content will be generated from the Reindeer API Gateway template. The generated vers...

Data Privacy, Isolation, and LLM Provider Controls This article summarizes how Reindeer protects customer data when agents use large language models, enterprise tools, and customer-specific workflo...

Building and Deploying Agents on Reindeer Reindeer provides a secure runtime and builder harness for enterprise agents. Teams bring the agent logic, workflow policy, prompts, and tools they want to...