AI Labs
All examples
AWS

AWS-Native Q&A with Amazon Bedrock

Conversational demo using Bedrock Converse API with optional Knowledge Base retrieval.

RAGEnterprise

Target outcomes

  • Keep data in-account; no cross-cloud model routing required
  • Pilot on one domain before enterprise KB rollout

Initiative playbook

Typical delivery arc for this pattern in enterprise programs.

  1. 1
    Discovery2 to 4 wks

    Identify S3/OpenSearch corpora and IAM boundaries for Bedrock Knowledge Bases.

  2. 2
    Pilot6 to 8 wks

    Converse + KB on one data domain; validate answer grounding with subject-matter experts.

  3. 3
    Scaleongoing

    Roll out per-account Bedrock guardrails, KB versioning, and cross-region DR patterns.

Business use case

Problem

AWS-centric organisations want gen AI without exporting data to another cloud’s model API. Teams need a path from pilot (Converse + context) to production (Knowledge Bases on S3/OpenSearch).

Who benefits

  • Data platform, Bedrock aligned with existing IAM and regions
  • Application teams, one Converse API across foundation models
  • Security, least-privilege IAM per workload

Success metrics

  • Pilot on one domain with subject-matter expert grounding review
  • IAM policy reviewed before any public-facing endpoint
  • Clear upgrade path from Converse-only to Knowledge Base retrieval

Solution

Invoke Amazon Bedrock Converse with optional seed context (portfolio demo) or Knowledge Base retrieve-and-generate when BEDROCK_KNOWLEDGE_BASE_ID is configured in your account.

Technical implementation

Stack

  • @aws-sdk/client-bedrock-runtime, ConverseCommand
  • BEDROCK_MODEL_ID, e.g. amazon.nova-lite-v1:0
  • Credentials via AWS_REGION + access keys or execution role on Vercel

Architecture

Bedrock Runtime in your account; Knowledge Base retrieval when configured, otherwise seeded snippets for local demos.

How it runs
Drawing the flow…

Implementation highlights

  • Seed snippets from lib/demos/seed-documents.ts when KB not wired
  • Response includes mode field (bedrock-converse vs KB-configured)
  • README documents least-privilege IAM for bedrock:InvokeModel

Outcomes and learnings

  • Converse unifies message format across models, simplifies app code
  • Knowledge Bases connect existing S3/OpenSearch without custom RAG in v1
  • Keep blast radius small with per-demo IAM roles on public portfolios

Where else this applies

Knowledge-grounded Q&A in AWS is for teams whose data residency and procurement already point to Bedrock, not for every workload, but for the ones that must stay in-account.

Internal developer portal

Answer questions about internal APIs and IaC standards from repos synced to a KB.

Energy and utilities ops

Technicians query equipment manuals indexed per region with strict account isolation.

Financial research assistants

Analysts ask questions over approved research corpus, not the open web.

Post-merger integration

Unified KB over legacy and acquirer policy PDFs while IAM stays account-scoped.

Using this stack elsewhere

Bedrock Knowledge Bases pair with S3/OpenSearch corpora; Converse gives a single API for multi-model trials inside the same IAM boundary.

Live demo

The demo is the same code path described above, not a simplified mock UI. Add keys in .env.local when you are ready; the narrative and diagrams stand on their own without them.

Business

Classic “keep data in our account” Q&A. Try a Bedrock/IAM question; note whether you are on KB or seed mode in the response.

Technical

Converse API with optional Knowledge Base; seed snippets when KB env is unset.

Amazon Bedrock Q&A

Bedrock-class model via AI Gateway with seed-document context.

Live