Documentation Index
Fetch the complete documentation index at: https://docs.narrativebanking.com/llms.txt
Use this file to discover all available pages before exploring further.
Assistant outputs are intended for decision support. They do not replace legal, tax, or regulated professional advice.
Core principles
Ground responses in authorized data and active product context.
Respect tenant and user access boundaries for every generated response.
Do not provide regulated legal, tax, or financial advice; provide guidance and escalation paths instead.
v1.5.7 safety updates
v1.5.7 strengthens how assistant surfaces handle guidance, uncertainty, and partner context.
- Coach distinguishes more clearly between general business guidance and regulated advice.
- Regulated or high-risk topics are handled with clearer boundaries and escalation paths.
- Responses are expected to be evidence-led, helping users understand the reasoning instead of receiving a blunt verdict.
- Source sections are only shown when useful sources are available.
- Partner product questions can be routed toward approved partner support or product channels.
- The assistant avoids saying it has completed an action when that action is not actually available.
Safety controls in practice
Prompt + routing guardrails
Detect high-risk or out-of-scope requests and route to restricted handling paths.
Runtime disclaimers
Show explicit user-facing disclaimers for known uncertainty or processing states.
Refusal behaviour
Refuse disallowed requests with clear rationale and safe alternatives.
Validation suites
Test tone, scope, and trigger behaviour to catch regressions before release.