Skip to main content

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

Use non-alarming, actionable language focused on user next steps.
Ground responses in authorized data and active product context.
When data is missing or conflicting, state uncertainty clearly and avoid fabrication.
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

https://mintcdn.com/narrative-b13c445c/qi6sqKB_OLTe8ty2/SVG/prompt-guardrails.svg?fit=max&auto=format&n=qi6sqKB_OLTe8ty2&q=85&s=1b80d39c7fb42726d26b571a39bbd617

Prompt + routing guardrails

Detect high-risk or out-of-scope requests and route to restricted handling paths.
https://mintcdn.com/narrative-b13c445c/qi6sqKB_OLTe8ty2/SVG/runtime-disclaimers.svg?fit=max&auto=format&n=qi6sqKB_OLTe8ty2&q=85&s=528dc3cfb668922d4248e7b47e88464c

Runtime disclaimers

Show explicit user-facing disclaimers for known uncertainty or processing states.
https://mintcdn.com/narrative-b13c445c/qi6sqKB_OLTe8ty2/SVG/refusal-behavior.svg?fit=max&auto=format&n=qi6sqKB_OLTe8ty2&q=85&s=7f2e9e92249aa3eb1c27b298f31fd56f

Refusal behaviour

Refuse disallowed requests with clear rationale and safe alternatives.
https://mintcdn.com/narrative-b13c445c/qi6sqKB_OLTe8ty2/SVG/validation-suites.svg?fit=max&auto=format&n=qi6sqKB_OLTe8ty2&q=85&s=cd7d6a89b3789817982e6c08d58a997e

Validation suites

Test tone, scope, and trigger behaviour to catch regressions before release.

Escalation model

1

State limitation

Explain confidence gaps or missing context explicitly.
2

Constrain recommendation

Avoid prescriptive advice in regulated or high-risk scenarios.
3

Escalate to human channel

Route users to approved human support workflows when needed.