"Why is it that your existing employees initially outperform the new rockstar you've just hired? And why do you have a period of onboarding before a new hire gets up to speed? Institutional knowledge. The new rockstar knows how to do the job. That's why you hired them. But they need time to understand the company culture, processes, approaches, applications, their team, and customers and partners."
"So let's look at the different types of context, its source, and whether it's structured or unstructured -- all of which will determine how it is presented to the AI agent. Also: More workers are using AI than ever - they're also trusting it less: Inside the frustration gap You keep hearing about models having a large context window. Claude has a 1-million-token context window; ChatGPT 5.2 has a 400,000-token window. But this is not sufficient to handle everything about the company."
AI agents require contextual information equivalent to institutional knowledge to perform well. Context engineering prepares data, metadata, process flow, and related artifacts for agentic use. Context can be structured or unstructured and must be presented appropriately to the agent based on role and task. Large model context windows help but are insufficient for entire organizational configurations, so selective provisioning of context is necessary. Examples show model token limits and large codebases can exceed available context. Faster onboarding of agents is possible when contextual data is organized, accessible, and aligned with business processes and roles.
Read at ZDNET
Unable to calculate read time
Collection
[
|
...
]