Coach guide

Integration guidance for Coach conversations, streaming responses, and follow-up workflows.

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 v1.5.11

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 tool, model call, context assembly step, or data source 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

1. Initialize or restore a session

Load current conversation context and prior history when the user opens Coach.

2. Stream responses for each user message

Render assistant output incrementally so users see progress instead of waiting for one final payload.

3. Separate content and control handling

Handle text chunks, completion signals, and runtime errors as different event types in the UI.

4. Explain limitations explicitly

When data or tools are unavailable, show a specific limitation and a safe next step rather than a generic failure message.

5. Run follow-up workflows after completion

After each completed answer, enable feedback capture and optional guided next-question suggestions.

6. Capture journey goals and follow-through

Record specific goals, challenges, and action-status updates from confirmed Coach interactions so journey progress reflects real user intent.

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.

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.