The agentic knowledge platform that reads your documents, answers with cited sources, and takes the next action — no human required to close the loop.
Built by EFFOMA, an applied-AI studio. Sage productizes a RAG + multi-agent pipeline reused across 5+ enterprise engagements since 2023.
Six components, six explicit trade-offs. This is what we tell clients when they ask "why this and not that" — no "let the team decide later."
S3 → EventBridge → Step Functions. The state machine runs Textract (with OCR for scanned pages), chunks by semantic boundary, then embeds before writing vectors to the store.
Default: OpenSearch Serverless. Aurora pgvector for small-scale or already-on-Postgres teams. Kendra when enterprise-connector ACLs matter more than retrieval flexibility. S3 Vectors for a cold archival tier.
Default: Bedrock AgentCore — managed memory and guardrails remove a lot of undifferentiated plumbing. LangGraph on Lambda/ECS when portability across models or infra matters more than managed convenience.
Supervisor (default): one orchestrator routes to specialist agents — Extract, Compare, Risk, Summary. Hierarchical once you pass ~8 specialists. Swarm rejected for enterprise use.
A 100–200 pair golden dataset drives two metric layers: retrieval (recall@k, MRR/nDCG) and generation (faithfulness via RAGAS / Bedrock Evaluations).
Cognito issues group claims, enforced as retrieval-time ACL metadata filters. KMS encryption, VPC endpoints, and CloudTrail wrap the rest.
This calls real deployed endpoints — not a mock. Ask a question against the live RAG pipeline, or run the golden-set evaluation suite and watch the metrics come back.
Runs the golden-set retrieval + faithfulness benchmark used to gate every release.
Sage shipped as a named, versioned internal platform starting 2024, with incremental releases through today.
AgentCore migration
Evaluation & caching
Agentic layer
Multi-tenant
Initial release