Skip to main content
Coach is the in-product conversational assistant your users talk to when they need clarity on what is happening in their business and what to do next. In the current app experience, users ask free-form questions, get guided answers in chat, open linked detail views, and continue with follow-up prompts that turn insight into concrete next steps.

What’s new in v1.8

v1.8 makes Coach entry, Daily Briefing, action history, and public-search context steadier.
  • The current Daily Briefing can remain visible above the selected conversation when users open Coach, select New, or switch chat history.
  • Starting from a Daily Briefing item creates or reuses a chat only after Narrative checks the current briefing version.
  • Existing Coach Action results restore more reliably across refreshes and conversation switching, with durable storage for generated report results in configured environments.
  • Unavailable Coach Actions remain visible but disabled, and the slash launcher stays hidden when no action can run.
  • Search-backed answers use account country, region, and currency context where available and ask for clarification instead of inventing a missing location.

What’s new in v1.5.14

v1.5.14 makes Coach new conversations, Coach Actions, and generated answers more useful.
  • Selecting New in Coach can show the current day’s Daily Briefing instead of a blank chat page.
  • The New action keeps the conversation clean: previous messages are not shown, and an empty session is not created until the user sends a message or chooses an action that needs one.
  • Competitor intelligence is more local and owner-aware, with nearest-first discovery, better fallback search when local sources return no useful places, and advice that respects the owner’s stated constraints.
  • Supported Coach Action forms can use stored business profile context to avoid asking for details the user has already provided.
  • Free-form Coach answers have stronger natural-writing guidance while preserving safety, compliance, citation, source-attribution, and structured-answer rules.

What’s new in v1.5.13

v1.5.13 adds QuickBooks-aware accounting answers, Coach Action context, and clearer journey-aware first-visit behaviour.
  • Coach can answer a QuickBooks-first set of accounting questions, including overdue invoices, customer balances, vendor bills, top vendors, and accounting expense categories.
  • Coach keeps bank cash movement and accounting facts separate, and explains when connected-source data is missing, stale, partial, or unsafe to combine.
  • Coach Actions receive company background by default, while transaction context is loaded only for transaction-related actions.
  • The first visit is Coach-led: welcome, goal bridge, and quick-win cards open in Coach while still linking to relevant Money action details.
  • Journey goal-setting prompts now ask for the user’s own goal and challenge before completing the milestone.

What’s new in v1.5.12

v1.5.12 makes Coach faster for common questions and account-aware for same-currency multi-account users.
  • Coach can reason over multiple connected same-currency bank accounts.
  • Internal transfers between connected accounts are not treated as business income or spending.
  • Common question types use a faster response path while preserving answer quality for deeper transaction analysis.
  • Streaming responses, saved history, citations, follow-up questions, and product-surface handoffs remain compatible.
  • Users can expand collapsed progress details to understand what Coach is checking without seeing internal operational detail.

What’s new in v1.5.11

v1.5.11 connects Coach to journey progress and follow-through.
  • Coach includes a “Help me set clear goals” entry point until the user has shared specific goals and challenges.
  • Briefings lead with Money actions before Growth opportunities so users can build the financial picture first.
  • Coach can ask about bookmarked action status to help users return to priorities they already chose.
  • Journey-related Coach copy uses guidance language and avoids regulated financial recommendation framing.
  • Goal and challenge capture for journey progress is distinct from broad onboarding direction.

What’s new in v1.5.8

v1.5.8 improves Coach reliability, spending explanations, and reporting readiness.
  • Coach gives clearer spending breakdowns by category.
  • Coach handles partial failures more clearly when a data source or answer-preparation step is unavailable.
  • Error responses are more specific and are designed to avoid fabrication while offering a next-best action.
  • Transaction-level behavioural signals and sector context can improve the grounding available to Coach where tenant configuration and data availability support it.

Functional flow

Load current conversation context and prior history when the user opens Coach.
Render assistant output incrementally so users see progress instead of waiting for one final payload.
Handle text chunks, completion signals, and runtime errors as different event types in the UI.
When data or tools are unavailable, show a specific limitation and a safe next step rather than a generic failure message.
After each completed answer, enable feedback capture and optional guided next-question suggestions.
Record specific goals, challenges, and action-status updates from confirmed Coach interactions so journey progress reflects real user intent.
Keep Coach answers grounded in the connected same-currency account set and avoid treating internal transfers as income or spending.
When accounting data is connected, allow Coach to answer supported accounting questions from that source and state limitations when source data is unavailable or partial.
Give supported actions prepared context so the client does not need to assemble source-specific details.
When the user selects New, show the current Daily Briefing where available while preserving a clean conversation context.
Use stored business profile context to prefill or hide supported Coach Action fields when the answer is already known.
Keep free-form answers concise and practical without weakening truthfulness, source-grounding, or compliance constraints.

Integration considerations

Session model

Keep conversation state bound to authenticated user context so resumes and restores remain coherent.

Streaming lifecycle

Design the UI around in-progress, completed, interrupted, and degraded answer states.

Context binding

Attach conversations to relevant product entities so follow-up guidance stays grounded.

Connected account context

Preserve account-aware context when users ask about cash movement, transfers, spending, or income across connected accounts.

Connected-source answers

Keep accounting answers tied to connected-source availability and show limitations instead of inventing unavailable data.

Action context

Pass company background and only the required optional context into Coach Actions.

Daily Briefing entry point

Let New conversations surface the latest Daily Briefing without persisting an empty session.

Action form context

Reuse trusted profile context so supported forms ask only for genuinely missing information.

Feedback loop

Capture explicit user sentiment after messages complete to improve assistant relevance over time.

Common risk patterns

  • Session restore drift after account or context switches.
  • Duplicate client rendering when stream completion is not handled idempotently.
  • Feedback double-submission when retries are not deduplicated.
  • Generic error states that hide whether data is unavailable, still processing, or outside the current product scope.