Examples you can run, not just slide decks

Compare latency and responses across models through a single gateway endpoint.

Same prompt POSTed once to the compare route

Knowledge Q&A using Azure OpenAI and Azure AI Search over seeded policy documents.

Question sent to searchKnowledge (AI Search or local seed fallback)

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

Question enriched with seed context snippets

Extract initiative risks, stakeholders, and systems from unstructured text using schema-constrained generation.

Discovery notes POSTed as plain text

A pay-per-invocation durable workflow that orchestrates a multi-step transformation intake pipeline.

POST starts a workflow run with start()

A governed orchestration pipeline: retrieve context, generate a grounded answer, then safety-score the output.

Retrieve top-k policy chunks (Search or seed fallback)

Uses Bedrock Agent Runtime when configured, otherwise runs a multi-step orchestration (context → intent → answer) via Converse.

If agent env is set: invoke Agent Runtime and stream completion

Keyword retrieval over in-app policy seeds, then grounded answers via the Vercel AI SDK.

Question triggers keyword search over SEED_DOCUMENTS

Agent proposes CRM writes and refunds; supervisors approve or reject before anything executes.

Scenario analysed with generateObject for action proposal

Structured telemetry on every request: trace id, latency breakdown, tokens, retrieval hits, and cost estimate.

Optional seed retrieval timed separately from model call