DBT Assist: Building AI tools that balance innovation and trust

This is an extract from the team's blog post.

Please note that the Department for Business and Trade (DBT) is now the Department for Business, Innovation, Science and Trade (BIST). The change is ongoing and not all products have been renamed.

Introducing DBT Assist

BIST's suite of AI tools, DBT Assist, does what the name suggests. It assists with specific, high-value tasks where generic AI falls short.  Rather than a general-purpose chatbot, DBT Assist provides specialised capabilities for repeatable workflows from quality-checking ministerial submissions to extracting company intelligence from internal databases.

Building on proven foundations

Back in 2024, through joint workshops, employee secondment, and code-sharing with I.AI, we got Redbox running in one month. That foundation enabled rapid iteration based on user feedback.

Since then, we learned which capabilities matter most.  A Policy Advisor told us the Submissions Checker was "impressive" in how it "challenges the clarity of argument and evidence bases," acting as "an independent pair of eyes". It helps "avoid documents being returned for corrections, ultimately saving valuable time." These insights drove our evolution toward task-specific tools.

From generic chat to purpose-built tools

DBT Assist now features an improved interface built around what we are calling ‘Tools’. Instead of a blank chat, users choose from purpose-built capabilities for specific workflows like Submissions Checker for quality assurance and InvestLens for company intelligence. We are currently working on a Negotiation Planner for trade precedents.

This reflects a broader insight. The most valuable government AI applications aren't the most general ones. They are tools that understand specific professional contexts, integrate with departmental systems, and augment rather than replace human expertise.

A replicable pattern

The path from Redbox to DBT Assist demonstrates a pattern for government AI adoption:

1. Start with open-source collaboration to avoid duplication.
2. Engage users continuously to understand actual needs.
3. Build trust through transparency in architecture and interface.
4. Create new design patterns where existing ones don't serve conversational AI.
5. Measure carefully before claiming efficiency gains.
6. Scope tightly to high-value use cases.
7. Contribute back to accelerate cross-government adoption.

We publish our code openly and regularly collaborate with other departments. As government explores generative AI, the approach matters more than technical choices. It builds trust through transparency, creates reusable patterns, and focuses on problems where AI demonstrably adds value.

DBT Assist represents DBT's contribution to this collective learning. Our platform is built through collaboration, refined through user research, and designed to assist with the complex, sensitive work of modern government.

Innovation, collaboration and trust must go hand in hand in government. If your team is exploring what is possible with AI tools, we want to hear from you in the comments.