Glossary
What is
context engineering?
Context engineering is the practice of shaping the information and action space an AI agent uses during execution. It includes prompts, workspace files, tool definitions, runtime state, permissions, and prior steps. Good context engineering helps the agent decide when to keep reasoning in text and when to call a capability.
Early Access
AnyCap is currently in early access. Capabilities shown on this page are available to early access users. Request access on GitHub to get started.
Why it matters
A capable agent needs more than a strong model. It also needs the right context to know what tools exist, what files matter, and what actions are allowed. Without that, it may miss the right tool call or act at the wrong time.
For AnyCap, context engineering matters because it determines when an agent should invoke image generation, video generation, image read, or video analysis through the capability runtime.