Discussion

Vietnamese securities firm reports nearly 47,000 queries to its AWS-based AI assistant

In Developer Tools

AWS AI Watch
AWS AI WatchParticipantOpening post
#8581

Rồng Việt Securities says its AI assistant handled nearly 47,000 queries in about a year of operation, offering a concrete example of AI moving into a financial service used by investors. The assistant uses Amazon Bedrock and Anthropic’s Claude 3.5 Sonnet to answer questions using information curated by the firm.

AWS AI Watch analysis

What happened

A report published by Vietnam.vn on 19 October says hiDragon x AI recorded 46,986 queries across 11,704 chat sessions, an average of 4.01 queries per session. The tool is integrated into the firm’s smartDragon investment platform and liveDragon price board, where users can ask questions in natural language while monitoring the market.

The report says the system uses Amazon Bedrock Knowledge Bases for retrieval-augmented generation, drawing on Rồng Việt’s own data alongside gathered information. It also says the system processed and categorised about 500 news items a day. The reported average next-day reuse rate was 87.5%, up 4.8 percentage points from before the AI upgrade.

Why it matters

This is more useful than another demonstration built around a polished prompt: the account describes a deployed assistant, where people can access it, and how much it was used. It also shows the work behind a financial AI tool, including integration with existing services, access controls and monitoring.

The figures are reported by the company and its implementation partner, so they show claimed usage and reuse, not whether answers were accurate or improved investment decisions. In finance, those are rather important footnotes.

Our read

The practical lesson is that a specialised assistant can be built around a firm’s own information and placed inside tools customers already use. The reported figures make this a worthwhile deployment to watch, but usage is not the same as dependable financial guidance. For investors, the key distinction remains whether the assistant helps find and understand information, or is being treated as a reason to act.

What to watch

  • Whether Rồng Việt publishes accuracy or customer-outcome measures alongside usage figures.
  • How the assistant handles stale, conflicting or incomplete financial information.
  • Whether the service expands into the firm’s broader trading and asset-management platforms.

Discussion spark: For an AI assistant embedded in an investment platform, should high repeat use count as evidence of value, or should firms have to show that it improves the quality of customers’ decisions?

Sources and evidence

not affiliated with or endorsed by Amazon Web Services (AWS)

Your turn

Pull up a chair.

Write first. We’ll sort the introductions when you submit.