Telecom · home networking
WiFi log intelligence with RAG
Vague “my internet is slow” tickets become a ranked root cause, the log lines that prove it, and the next action.
Result: 7 analysis passes · 3 vector memories
View case studyService · Documents & language
We design and build AI agents and retrieval-augmented generation (RAG) systems that answer from your data (documents, tickets, logs, manuals) with citations, guardrails, and measurable accuracy.
Selected work
Working systems from our founding team. Open any project for the full workflow, the stack and the results it produced.
Telecom · home networking
Vague “my internet is slow” tickets become a ranked root cause, the log lines that prove it, and the next action.
Result: 7 analysis passes · 3 vector memories
View case studyInsurance · South Korea
Customers get answers from the insurer’s own policy documents, by chat or by phone, instead of generic chatbot guesses.
Result: Korean end to end · chat + phone
View case studyFinance · investment research
Eight AI agents draft first-pass company research, with every score traceable to its inputs. Data stays in-house.
Result: 8 agents · 50+ metrics per company
View case studyClient names are withheld unless public. References are available on request.
All case studiesWhat this covers
Chunking and indexing strategy, hybrid retrieval, reranking, citation-grounded answers over manuals, wikis, and archives in English and Korean.
Planner and worker architectures that decompose real business tasks: triage, investigation, report drafting, tool use against your internal APIs.
A golden-set harness with retrieval and answer metrics, so “it seems better” becomes a number your team can rerun after every change.
Your cloud or on-premise, with logging, cost controls, and fallbacks when the model is wrong or unavailable.
Support and operations teams answering from large document sets, engineering organizations mining logs and postmortems, and any workflow where staff spend hours finding what the company already knows. Bilingual Korean and English corpora are a specialty.
Common questions
A general chatbot does not know your documents, cannot cite them, and cannot be measured against your ground truth. A RAG system retrieves from your own indexed knowledge, answers with citations, and ships with an evaluation harness that proves accuracy on your data.
Yes. We deploy with open-weight models on your hardware when data cannot leave your network, and we are honest about the quality trade-offs versus hosted frontier models.
Typically two to six weeks after scoping, depending on data readiness. The prototype runs on your real documents, not a demo corpus.
Start a project
Send a few lines about your data and the outcome you want. We reply within 1 business day with a feasibility read and a proposed scoping plan.