aminobots kbot · standalone product

search and reason over all your company knowledge.

Knowledge engine with RBAC-scoped search across structured + unstructured company data. Multi-agent research, report generation, background indexing. RLHF-tuned with external memory; background agents keep it current.

01 · capabilities
what's inside
  • Background indexingContinuously indexes Confluence, Notion, GDrive, GitHub/GitLab, Jira, Zendesk, ServiceNow, CW logs.
  • Hybrid retrievalBM25 + dense vector + graph traversal. Re-ranker over candidate set.
  • RBAC + tenant isolationPer-team CMK · row/col ACLs · SSO + identity center. Every query scoped to the user's permissions.
  • External memoryMem0-style long-horizon memory across sessions and tools. Per-user, per-team, per-domain memory layers.
  • RLHF feedback loopUser feedback → reward model → SLM fine-tuning. Closed-loop continuous improvement per team.
  • Per-team distilled SLMSmall fine-tuned model per team or domain — $0.10/Mtok class, served on Inferentia.
  • Agentic deep-researchMulti-step research subagent. Semantic search · SQL · code search · report generation tools.
02 · architecture
all sources in. one searchable corpus out.

Background agents continuously index every source. Pipeline runs through NER + semantic chunking. Indexed into semantic + lexical + graph search. RBAC + per-team CMK applied at query time. External memory layer remembers prior conversations. Agentic query orchestrator dispatches the right tool per question.

confluence · github · jira · drive · cw logs
  ↓ background indexing
semantic + lexical + graph search
  ↓
rbac · external memory · rlhf loop
  ↓
agentic query · search · sql · code · report
03 · lighthouse
live in production
live deployment

core-banking client · l1/l2/l3 support

L1, L2, L3 engineers use KBot to resolve tickets faster, generate root-cause reports, and accelerate runbook authoring. Every query RBAC-scoped; nothing leaves the client VPC.

ready to evaluate

start with a diagnose.

Two to three weeks. Five to ten lakh. A written scorecard with topology recommendation, cost ranges, and remediation plan. No commitment to build.

request diagnose
DPDP-ready by design AWS · Azure · GCP blueprint · patent pending India residency · on-prem option