Broadcaster
A broadcaster whose staff spend measurable time finding internal guidance that already exists in documentation
AI & automationTestingBuilt by LabsLast updated 29 July 2026
Custom Knowledge AssistantAnswers drawn from your own documents, with access control enforced
Staff waste hours searching internal documentation for answers that already exist - and a general-purpose AI assistant cannot be trusted because it would show people content they are not cleared to see. Custom Knowledge Assistant answers directly from your organisation's documents, enforces per-user access control, and combines hybrid retrieval with a stateful agent so the answers are grounded and the access is governed.
LangGraph Stateful AgentHybrid RAG RetrievalAWS Bedrock Intelligence
Try the demo
Custom Knowledge Assistant is password protected
Enter the demo password to launch the interactive demo.
Don't have a password? Ask us for one and we will send it over.
Request demo accessThe problem this solves
Knowledge is locked inside documents, intranets and wikis that are too large to search manually and too sensitive to hand to an unrestricted AI. Teams resort to asking colleagues, who either know from memory or have to search themselves - the same cost, paid again and again by different people.
A general-purpose assistant solves the retrieval problem but creates a worse one: it cannot distinguish between a document that is public and one that is restricted, so deploying it exposes protected material to whoever asks the right question. The only safe answer is a system that retrieves and answers within the boundaries of what each user is actually allowed to read.
Who this is for
This is relevant if you are:
Telco
A telco with layered access policies who needs an AI assistant that respects those policies rather than overriding them
How it works
- 1Documents are ingested and indexed using both dense vector embeddings and BM25 keyword search, so retrieval works on meaning and on exact terms simultaneously.
- 2When a query arrives, the LangGraph agent decides which tools to call: knowledge-base retrieval, email and site metadata search, or deterministic calculations - and loops until it has enough to answer.
- 3Reciprocal Rank Fusion merges the ranked results from both indexes, so the most relevant passages rise regardless of which retrieval method found them.
- 4Access control is applied at retrieval time: unauthenticated users reach only public collections; authenticated users reach the private sources their profile permits.
- 5A separate zero-temperature LLM pass reviews the response and emits structured feedback metrics, creating a quality signal that improves the system over time.
Hybrid Search + RRF
Higher-recall retrieval
Combines FAISS dense retrieval and BM25 keyword search, then fuses the rankings with Reciprocal Rank Fusion before generation.
Stateful LangGraph Orchestration
Resilient agent execution
Runs as a multi-stage StateGraph agent with tool looping, robust state management, guarded message flow, and max-step protection.
Specialized Enterprise Tools
Grounded answers and calculations
Supports knowledge-base retrieval, email and site metadata search, deterministic MBMS/FeMBMS bandwidth calculations, and structured quality feedback.
Cloud-Local Vector Sync
Reliable knowledge freshness
Synchronizes FAISS indexes from Amazon S3 using ETag-driven cache invalidation to keep the local store aligned with the latest uploaded corpus.
Granular Access Control
Context-aware data security
Restricts unauthenticated users to public collections while allowing authenticated users to reach protected private data sources.
Automated Feedback Loop
Quality measurement
Uses a separate zero-temperature LLM pass to review responses and emit structured feedback metrics for monitoring and improvement.
What makes it different
Most enterprise knowledge tools are either open - so they ignore access policy - or siloed per team, so the person who needs an answer from a different department cannot get it. Custom Knowledge Assistant enforces the access boundary at retrieval rather than at the UI, which means the model never sees what the user is not allowed to see. Hybrid retrieval with RRF means it does not choose between keyword precision and semantic recall: it uses both and lets the ranking decide.
Current status & next steps
TestingReviewed 29 July 2026
Custom Knowledge Assistant is in controlled testing. The demo on this page is available to selected partners on invitation - which is exactly what the Testing status commits us to - and the password gate you passed through is the access control mechanism in practice.
This is an early first-draft deployment intended for initial testing and iteration, and two boundaries follow from that. The current phase has no internet access, so the agent cannot run live web searches or pull real-time external data, and the architecture is text-only: it does not embed or reason over images, which keeps retrieval to text documents and metadata.
The next step is to run the assistant against a customer's actual document corpus and access policy, so quality and boundary enforcement can be measured on real material.
Want to deploy this on your own knowledge base?
Tell us what you need to keep private, what access structure you have, and we will tell you what a pilot against your corpus would involve.