Build your agent
Strict Knowledge Mode
Strict Knowledge Mode is a per-agent guarantee: the agent answers only from your own knowledge. When a visitor asks something your knowledge base can't ground, the agent returns a fixed fallback message instead of letting the language model answer from its general training — which is where invented, off-brand "facts" come from.
How to enable
Open the agent's settings page (/app/agents/{id}/settings),
find the Strict Knowledge Mode section, and toggle
Only answer from my knowledge. The change takes effect
immediately — there's no separate publish step.
Strict mode is on by default: every agent that existed when this shipped was switched on, and the "create agent" form defaults the toggle on for new agents. You can turn it off per agent at any time.
When the agent defers
On every turn, retrieval runs first and keeps only the chunks that clear the agent's confidence threshold. Strict mode returns the fallback message when, and only when, both of these are true:
- No retrieved chunk cleared the threshold (zero grounded sources), and
- There's no live page snapshot for the visitor's current page.
The second condition matters: if the widget sent a snapshot of the page the visitor is on, that counts as grounding and the agent answers from it normally. Curated answers, workflows, and the "talk to a human" shortcut all run before strict mode, so none of them are blocked by it.
The fallback message
You can set a custom fallback per agent in the settings field. When it's left blank, the agent resolves a default in this order:
- The agent's own
strict_fallback_message, if set. - A built-in default in the agent's default language (e.g. Dutch for a
nlagent). - The global English default: "I can't confirm that based on the available information. Please contact the company for more information."
Keep it warm and forward-looking — point the visitor at a contact route (email, phone, or the "talk to a human" button) so a deferral still moves the conversation forward.
Deferrals feed the self-improvement loop
Every strict-mode deferral is recorded as a content gap — the visitor's exact question, clustered and counted. The most frequently deferred questions rise to the top of the gaps list, so strict mode doubles as a backlog of the knowledge your agent is missing. Answer a gap once and that question stops deferring.