Orq.ai's Video Library

In this walkthrough, you'll learn how to invoke a Deployment in Orq.ai and read the logs and evaluator results that come back. Call your Deployment through the SDK or API, inspect each request and response in the Logs view, and review evaluator scores to track quality over time.

In this walkthrough, you'll learn how to manage Deployments in Orq.ai using version control, SDK snippets, and PII filtering. Roll back to previous versions, copy ready-to-use SDK code for your language, and configure PII filters to strip sensitive data from prompts and responses. Use this to ship LLM apps that are safe to run in production and easy to maintain over time.

In this walkthrough, you'll learn how to build and configure a Knowledge Base in Orq.ai. Upload documents, set chunking and embedding parameters, and connect your Knowledge Base to any Agent or Deployment. Use this to ground LLM responses in your own data without managing a vector database or retrieval pipeline yourself.

In this walkthrough, you'll learn how to use variables and fallback models in Orq.ai Deployments. Pass dynamic values into your prompts at runtime, and route to a backup model automatically if the primary one fails. Keep production LLM apps resilient and personalized without touching your integration code.

In this walkthrough, you'll learn how to use Playgrounds in Orq.ai to test prompts across models, tune parameters, and compare outputs side by side. Use it to iterate on prompts before shipping, benchmark new models against your current production setup, and catch regressions when you update a prompt or swap providers.

In this quick walkthrough, you'll learn how to use Orq.ai's Experiments module to compare AI models, configure prompts, and evaluate results. Ideal for A/B testing prompts and running regression tests on your AI workflows.

In this session, Bauke Brenninkmeijer (AI Research Engineer at Orq.ai) walks through what red teaming actually means for LLM agents, why it's different from regular evaluation, and how to run automated adversarial testing on your own agents.

Welcome to Orq.ai, your control center for building, testing, and deploying LLM-powered software.

In this webinar, Kyra Dresen (orq.ai) walks through a practical, end-to-end approach to AI model evaluation using orq.ai's Experiments module - from planning your success metrics to running live experiment comparisons in the UI.

This step-by-step tutorial walks you through the complete Orq.ai platform. You'll learn how to manage prompts, run experiments, set up evaluations, deploy to production, build Agents and monitor then using Traces.

𝗘𝘃𝗮𝗹𝘂𝗮𝘁𝗼𝗿𝗾 is a Python evaluation framework designed for running multiple experiments in parallel and measure AI performance directly from your Python code.

𝗠𝗲𝗺𝗼𝗿𝘆 𝗦𝘁𝗼𝗿𝗲𝘀 are persistent storage for agent memories, allowing your agents to maintain context and recall information across conversations Check out a short build to learn when to use Memory Stores and when to go for a Knowledge Base.

Learn how to build your first agent in Agent Studio

Learn how to set up Orq.ai MCP Server in your CLI

Find out how to leverage human feedback to improve system performance

Learn how to use historical data to build curated datasets in Orq.ai.

Learn how to easily import test data and use it as part of an evaluation workflow in Orq.ai.

Find out how you can create a knowledge base in Orq.ai in less than 2 minutes.

Learn how to enable models from OpenAI, Anthropic, and more for your GenAI use case.

Learn how to set up your first deployment and publish prompt and model changes.

Learn how to use our platform to iterate safely on prompt configurations.

Discover how to do A/B tests, carry out canary releases, and do contextualized routing.

Use logs and traces in to gain full visibility into your LLM app’s behavior.

Discover how to compare AI models, configure prompts, and evaluate results.

Discover how to interpret outputs from experiment to derive actionable insights.

Find out how to add a second model to an existing experiment.

Learn how Tidalflow delivers LLM-based features using Orq.ai.