Ground its answers

Choose what happens when knowledge has no answer

Decide whether answers must come from your knowledge library.

Captured from the product Demo workspace

Choose whether the agent should stop or use general knowledge when your knowledge library has no answer.

What this changes for your team.

In strict mode, the agent is instructed to say when your knowledge does not support an answer. If you allow general knowledge, it can continue but must tell the reader that it used information outside your library.

How it works in practice.

01
Choose strict abstention for agents that must stay within approved material.
02
Allow general knowledge if the agent may answer beyond your library, with that source clearly stated.
03
Review the answer’s sources to see whether it used your knowledge, tools, general knowledge, or no recorded source.

What you can plan around.

What to expect, including limits that matter to your team.

Your choice is saved when you publish the agent.

Answer summaries distinguish general knowledge from information found in your library.

Strict abstention is enforced around the model's output rather than requested inside the prompt, and each turn records which source class it landed on - so the policy is auditable after the fact, not only asserted before it.

Complete the operating path

View all capabilities

Ground its answersLink answers back to their sources

Let readers move from an agent's response back to the organization material that informed it.

Ground its answersKeep answers grounded as knowledge grows

Let Yekar.AI adapt retrieval automatically as the selected knowledge grows.

Build the agentBuild agents with AI

Turn a working brief into a reviewable agent draft without starting from a blank setup.

Bring one real process