A grounded knowledge assistant for a revenue platform
An illustrative example: a knowledge assistant that answers questions across a revenue platform's own content, with citations and permissions, so teams stop hunting through scattered sources.
Illustrative example. Named engagements are shared with client permission.
Context
A growing B2B SaaS company had knowledge spread across documentation, support tickets, and product data. Teams wasted time searching, and answers were inconsistent.
Challenge
Support and sales teams could not find answers across scattered docs, tickets, and product data.
Product approach
We treated retrieval quality as the core problem. Content was ingested into a hybrid retrieval layer, answers were grounded in sources with citations, and access controls were enforced at retrieval so users only saw what they were permitted to.
System architecture
Architecture layer details
- Frontend
- An assistant embedded in the existing product surface.
- Backend
- A retrieval API with permission enforcement and logging.
- AI
- Grounded answer generation with citation checking.
- Retrieval
- Hybrid graph and vector retrieval over ingested content.
- Integrations
- Documentation, ticketing, and product data sources.
- Infrastructure
- Cloud deployment with monitoring on retrieval quality.
AI and data components
- Grounded answer generation
- Citation and support checking
- Query understanding
- Provider-agnostic model orchestration
Backend and integrations
- Hybrid retrieval service
- Permission enforcement at retrieval
- Content ingestion pipelines
- Answer and source logging
Engineering decisions
Hybrid retrieval over pure vector search
Some questions needed relationships between entities, so we combined graph and vector retrieval instead of relying on similarity alone.
Permissions at retrieval, not display
Access was enforced when retrieving content, so restricted material never reached the model in the first place.
Responsible AI and safeguards
- Every answer carries citations to its sources
- Permissions enforced so users only see what they may access
- Answers checked for support against retrieved content
- Retrieval quality monitored in production
Outcome
- Faster answers for support and sales teams
- More consistent responses grounded in approved sources
- Less time lost searching across systems
Lessons
- Grounding and citations are what make an assistant trusted enough to use.
- Enforcing permissions at retrieval is simpler and safer than filtering later.
- Retrieval quality, not the model, was the lever that mattered most.
RAG and Knowledge Systems
For products that must retrieve and reason over private or domain-specific information with citations.
Explore capabilityBackend and Platform Engineering
For AI systems that need reliable, multi-tenant infrastructure behind them.
Explore capabilityAI Visibility
Visibility measurement and guidance for AI answer engines.
View productFacing a problem like this?
Tell us what you are building. We will show you how we would approach it, and reply within one business day.