High-performance customer service AI powered by RAG

PolyAI integrated SurrealDB as an external RAG provider for Agent Studio, delivering 30ms vector search latency while giving enterprises full control over their knowledge base.

IndustryArtificial intelligence

OutcomeLow-latency, customer-controlled knowledge base powering voice AI RAG integration

01 |KEY CHALLENGES

What they needed to solve

The technical and operational hurdles the team faced before adopting SurrealDB.

Avoiding vendor lock-in

Enterprises wanted to use their own knowledge bases inside Agent Studio rather than migrating sensitive content into a vendor-specific ecosystem.

Data ownership requirements

Organisations needed full ownership over where knowledge was stored and queried, particularly for sensitive or regulated information.

Real-time latency constraints

Even small increases in latency can interrupt spoken dialogue. Response times needed to stay well below the 1-1.5 second perceptible threshold.

Proving external RAG viability

PolyAI needed to demonstrate that an external knowledge base could power retrieval and reasoning without compromising conversational quality.

02 |SOLUTIONS

How SurrealDB helped

The architecture decisions and SurrealDB capabilities that addressed each challenge.

External RAG via Agent Studio

Connected SurrealDB as an external RAG provider through Agent Studio's function-calling runtime for vector similarity search.

Zero-change integration

No architecture changes, no specialised plugin development, and no data migration required. SurrealDB slotted directly into the pipeline.

Customer-controlled deployment

SurrealDB runs entirely within an organisation's own infrastructure, preserving full data ownership and control.

Multi-model data foundation

Supports documents, relational, graph, and vector data in one system, ready for future expansion to new data modalities.

03 |RESULTS

The impact

Measurable outcomes delivered after moving to SurrealDB.

~30ms

Near-zero latency

Vector lookup latency matched PolyAI's internal stack performance of ~31ms.

OWNED

Full data ownership

All knowledge stays under enterprise control with no need to migrate into PolyAI's environment.

SEAMLESS

Zero-change architecture

No architecture changes, plugin development, or data migration needed for integration.

MULTI-MODEL

Future-ready foundation

Ready to expand to graph and new data modalities as PolyAI evolves Agent Studio.

MORE CASE STUDIES

See what other teams have shipped

From knowledge graphs to AI assistants - how enterprise teams are building on the context layer.

Samsung

Unlocking insights with knowledge graphs

Samsung Ads uses SurrealDB to build dynamic, real-time knowledge graphs for smarter campaign execution - collapsing three legacy data stores into one.

Read case study

Verizon

AI assistant empowering 10,000 technicians

Verizon uses SurrealDB to power a generative AI assistant for 10,000 field technicians, delivering instant access to documentation, outage updates, and workflows.

Read case study

Tencent