Finance
Internal Knowledge Search and Report Q&A
RAG over LLMs for frontline staff and financial reports.
Named Models
The research names no model for this use case.
Where this comes from
Models the research names for this use case. Research, with sources on each model record.
Who Runs It
production, 3planned, 2
Citi Indonesia (Citibank N.A. Indonesia)Country: IndonesiaCiti Stylus Workspaces (document processing, chat, summaries, conversational search) and Citi Assist (internal policy and procedure assistant)Vendor: Citi (in-house)productionDate11 Jun 2026Available to about 180,000 Citi staff in 87 countries and jurisdictionsEvidence: company statementConfidence: lowSource: selular.id, keuangan.kontan.co.id
PT Bank Syariah Indonesia Tbk (BSI)Country: IndonesiaMicrosoft 365 Copilot (Copilot Chat) for drafting, reports, analysis and internal communicationVendor: MicrosoftproductionDate4 Jun 2026Qualitative only; user numbers not disclosedEvidence: company statementConfidence: lowSource: news.microsoft.com
Bank Rakyat Indonesia (BRI)Country: IndonesiaWISE generative AI knowledge search for frontliners (model not stated)Vendor: In-house BRIBRAINproductionDate9 Jun 2024Developed and implemented per releaseEvidence: company statementConfidence: lowSource: industry.co.id
Bank Negara Indonesia (BNI)Country: IndonesiaCloudera AI Inference on NVIDIA NIM with open-source LLMs (names not stated), on-premVendor: Cloudera; NVIDIAplannedDate7 Aug 2025Full deployment expected by end of 2025Evidence: company statementConfidence: lowSource: aap.com.au
Bank Rakyat Indonesia (BRI)Country: IndonesiaHi Bravo! (RAG over LLM, planned)Vendor: In-houseplannedDate–Planned, not confirmed liveEvidence: company statementConfidence: lowSource: cloudera.com
Where this comes from
Documented uses by named organisations. The evidence column says who made the claim.
Candidate Models
SEA-HELM leaderboard, 58 models, SEA average
A general benchmark for this model class, not a test on this use case. SEA average and per-language (incl. Indonesian) scores for open-weight models. Higher is better. Showing 10 of 11.
Qwen3.6-35B-A3BAlibaba (Qwen) maintainer-run73.86Qwen3.5-35B-A3BAlibaba (Qwen) maintainer-run73.55
gemma-3-27b-itGoogle maintainer-run64.54
Gemma-SEA-LION-v4-27B-ITAI Singapore maintainer-run64.35
gpt-oss-20bOpenAI maintainer-run60.64
Llama-3.3-70B-InstructMeta maintainer-run60.44Qwen3-8BAlibaba (Qwen) maintainer-run60.33
GLM 4.7 FlashZ.ai (Zhipu) maintainer-run53.76Gemma-3-4B-itGoogle maintainer-run47.84
Nemotron 3 Nano 30B-A3BNVIDIA maintainer-run46.89050100
Nemotron-SEA-LION-v4.8-120B-A12BAI Singapore, LLMReleasedSep 2026open weightsIndonesian statedhas scoreslast 18 monthsNemotron-SEA-LION-v4.8-30B-A3BAI Singapore, LLMReleasedSep 2026open weightsIndonesian statedhas scoreslast 18 monthsQwen-SEA-LION-v4.5-27B-ITAI Singapore, LLMReleasedMay 2026open weightsIndonesian statedhas scoreslast 18 monthsQwen3.6-35B-A3BAlibaba (Qwen), LLMReleasedApr 2026open weightsruns on edgehas scoreslast 18 monthsNemotron 3 SuperNVIDIA, LLMReleased2026open weightsIndonesian statedhas scoreslast 18 monthsNemotron 3.5 Lightning 30B-A3BNVIDIA, LLMReleased2026open weightsIndonesian statedhas scoreslast 18 monthsgpt-oss-120bOpenAI, LLMReleasedAug 2025open weightsIndonesian statedhas scoreslast 18 months
Granite 4.2 8BIBM, LLMReleasedSep 2026open weightshas scoreslast 18 months
Hy4-previewTencent, LLMReleasedAug 2026open weightshas scoreslast 18 monthsGLM-5.3Z.ai (Zhipu), LLMReleasedAug 2026open weightshas scoreslast 18 monthsShowing 10 of 402. All models of this class
Where this comes from
Derived, not researched: models in the directory whose class matches a class this use case uses, excluding family records and models shut down or deprecated. Ranked by how many fit facts they meet, then by release date. Each fit fact is read from the model record.
Links
Modelsnone recorded
Deployments 5
Bank Negara Indonesia (BNI)Cloudera AI Inference on NVIDIA NIM with open-source LLMs (names not stated), on-prem, IndonesiaBank Rakyat Indonesia (BRI)Hi Bravo! (RAG over LLM, planned), IndonesiaBank Rakyat Indonesia (BRI)WISE generative AI knowledge search for frontliners (model not stated), IndonesiaCiti Indonesia (Citibank N.A. Indonesia)Citi Stylus Workspaces (document processing, chat, summaries, conversational search) and Citi Assist (internal policy and procedure assistant), IndonesiaPT Bank Syariah Indonesia Tbk (BSI)Microsoft 365 Copilot (Copilot Chat) for drafting, reports, analysis and internal communication, Indonesia
Sources
- PT Bank Rakyat Indonesia | Customers | Cloudera cloudera.com https://cloudera.com/customers/bank-bri.html
- BRI Kenalkan Conversational Banking hingga Robot Cash Management di Kick-Off BUMN AI Center of Excellence - Industry.co.id industry.co.id https://www.industry.co.id/read/133616/bri-kenalkan-conversational-banking-hingga-robot-cash-management-di-kick-off-bumn-ai-center-of-excellence
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Internal Knowledge Search and Report Q&A", https://aurion.semai.id/usecases/fin-internal-knowledge-qa/, records of October 2026.