Workshop Explainer · Foundation
The managed platform for building generative AI applications and agents at production scale. This explainer walks the four pillars — model choice, your data (RAG), guardrails, and agents — then maps them to the integration and deployment decisions you'll make for a real agentic use case. Framed for a technical audience with basic AWS experience; sample scenarios use AnyCompany, a fictional bank.
Bedrock is a fully managed, serverless service for building generative AI applications and agents. There are no servers to run and no models to host — you call an API, pick a model, and pay for what you use. Everything you need to go from prototype to production sits behind one unified API, secured by AWS IAM and kept inside your account.
High-performing foundation models from Amazon (Nova), Anthropic (Claude), OpenAI, Meta, Mistral and more — all through one API. Swap models without changing application code.
Ground responses in your own content with Knowledge Bases — a fully managed RAG pipeline (ingest, retrieve, augment) with automatic citations.
Configurable safeguards that filter harmful content, block prompt attacks, redact PII, and check groundedness — applied to any model, agent, or knowledge base.
Build, deploy, and operate agents at scale with any framework or model — runtime, memory, identity, gateway, and observability as managed building blocks.
The market moved from proofs-of-concept (2023) to production (2024) to business value (2025). The questions shifted from "what is GenAI?" to "how do I lower cost, stay compliant, and ship agents?"
Gartner projects 80%+ of enterprises will have used generative AI APIs or deployed GenAI-enabled apps by 2026.
Gartner projects 33% of enterprise apps will include agentic AI by 2028 (up from <1% in 2024), and 15% of day-to-day decisions made autonomously.
Work through the tabs in order — each maps to one pillar plus the deployment concerns around it:
Bedrock gives you a broad selection of fully managed foundation models through one API. You can pick from leading providers, evaluate models against your own data, import your own customized models, and reach 100+ more via Bedrock Marketplace. Because the API is unified, you can swap the underlying model without rewriting your application.
Fast, cost-effective reasoning model for everyday tasks. Generally available.
Nova's most intelligent model for complex AI workloads. Preview.
All-in-one model for multimodal reasoning and image generation. Preview.
State-of-the-art embeddings for semantic search and agentic RAG. Generally available.
Most agentic workloads land on Claude. The tradeoff is intelligence vs. cost vs. latency — pick the smallest model that clears your quality bar, then scale.
| Claude Opus | Claude Sonnet | Claude Haiku | |
|---|---|---|---|
| Best for | Hardest, most complex work needing peak intelligence & sustained autonomy | High-volume production; near-Opus intelligence at scale; agentic workflows | Latency-sensitive UX; high-volume; executing tasks planned by bigger models |
| Cost (In/Out per MTok) | $5.00 / $25.00 | $3.00 / $15.00 | $1.00 / $5.00 |
| Relative latency | Fast (~80 TPS) | Fast (~80 TPS) | Very fast (~109 TPS) |
| Context window | 1M (beta) | 1M (beta) | 200K |
| Max output | 128K tokens | 128K tokens | 64K tokens |
gpt-oss are available through the Bedrock API with native OpenAI SDK support — you can migrate with zero code changes.Priority, Standard, Flex, Batch, and Reserved — trade latency for cost depending on how time-sensitive the workload is.
In-Region for data-residency control, or Cross-Region inference for capacity and resilience (outputs still land in the home Region).
Prompt Caching (reuse repeated context), Intelligent Prompt Routing (send easy prompts to cheaper models), and Model Distillation.
Custom Model Import lets you run your own fine-tuned/customized model behind the same serverless Bedrock API, on-demand, and still use native features like Knowledge Bases, Guardrails, and Agents. Bedrock Marketplace adds 100+ specialized models (from Hugging Face, Stability, Writer, NVIDIA, and others) through a serverful deployment when you need something niche.
A base model knows the public internet up to its training cut-off. It does not know your products, your policies, or last night's transactions. Retrieval-Augmented Generation (RAG) closes that gap: fetch relevant snippets from your data at query time and add them to the prompt, so the model answers from your knowledge — with citations. Bedrock Knowledge Bases is the fully managed way to do this.
RAG on Bedrock is a spectrum from full control to full abstraction. Pick based on how much you need to tune vs. how fast you want to ship.
Full control over every component — choose your vector store, parsers, and connector workflow. You connect and retrieve data; you own the pipeline. Most control.
Connect data, retrieve data — infrastructure and scaling handled for you. You still choose embedding model and vector store, but skip the plumbing.
Connect data, users get answers — no RAG pipeline to build. Native AgentCore integration, agentic retrieval (retrieve → reason → re-rank), and native connectors. Most abstraction.
retrieve tool queries a Bedrock Knowledge Base exactly like step 2 above — this is the same RAG flow, wired into an agent.
For a bank, the model is only usable if it's safe and the data stays protected. Bedrock addresses both: Guardrails control what goes in and comes out of the model, and the platform's data-handling guarantees keep your prompts and responses inside your account and Region.
A configurable safety layer that works with any model, agent, or knowledge base — even models hosted outside Bedrock.
Detect and filter up to 88% of undesirable or harmful text and image content, with thresholds you configure per category.
Block jailbreaks, prompt injections, and prompt leakage before they reach the model.
Detect and redact personally identifiable and sensitive information in inputs and responses.
Define and disallow subjects with short natural-language descriptions — e.g. keep a support bot off investment advice.
Filter hallucinations by checking whether a response is grounded in the provided context and relevant to the query.
Verify responses against encoded rules with up to 99% accuracy to minimize factual errors on policy-critical answers.
① the input is checked against your policies · ② if it passes, the model runs · ③ the response is checked by the same policies · ④ if it passes, the final answer is returned — otherwise it's blocked, or the PII is masked. Click any policy in the guardrail box to explore it.
Amazon Bedrock Guardrails — the same policies screen both the input and the output
Your prompts, responses, and fine-tuned models are never used to train the base models and are never shared with model providers.
Customer model data is isolated per customer and stays in the AWS Region where it was created. (Cross-Region inference may process in a secondary Region, but outputs are stored in the home Region.)
Encrypted in transit (TLS 1.2+) and at rest (AES-256 via AWS KMS). Fine-tuned models can use your own KMS keys — only you can access them.
20+ standards including HIPAA eligibility, SOC 1/2/3, ISO, PCI, FedRAMP (Moderate & High), and GDPR. Monitor API activity with AWS CloudTrail.
ap-southeast-1 before committing an architecture to it, or plan a Cross-Region inference profile.
A working agent in a notebook is exciting — but getting it to production is where most projects stall. Agents run for long stretches, call many tools, need memory, need fine-grained identity, and need monitoring built for autonomous systems. Amazon Bedrock AgentCore is a set of modular managed services that supply exactly those pieces, so you don't rebuild the plumbing for every agent.
Build powerful agents without the infrastructure and operational headaches — the runtime, memory, and gateway are managed.
Use any framework and any model — Strands Agents, LangGraph, CrewAI, LlamaIndex, Google ADK, OpenAI Agents SDK. Protocols: MCP and A2A.
Deploy secure, scalable, reliable agents your organization can trust — with identity, policy, and observability built in.
Mix and match — you don't have to adopt all of them at once.
| Group | Service | What it gives your agent |
|---|---|---|
| Build tools & memory | Memory | Retain context across turns and sessions; learn from past interactions; personalize. |
Gateway | Turn existing APIs and services into agent-callable tools (MCP-ready). | |
Browser | Let the agent browse the web in a managed, sandboxed browser. | |
Code Interpreter | Execute code securely for calculation, data work, and file handling. | |
| Deploy securely at scale | Runtime | Serverless runtime purpose-built for long-running, multi-modal agents (auto-scaling, isolated sessions). |
Identity | Fine-grained identity and access control — the agent reaches only the systems and data it should. | |
Policy | Governance guardrails around what the agent is allowed to do. | |
| Operate gain insight | Observability | Trace and monitor agent behavior — the reasoning steps, tool calls, and outcomes. |
Evaluations | Measure agent quality over time so you can catch regressions. |
Visually design and accelerate GenAI workflows — chain prompts, models, knowledge bases, and logic.
Managed multi-step task execution over your systems and data: pick a model, give instructions, attach data sources, specify actions.
Here's how the pillars come together for a real agentic use case. The scenarios below use AnyCompany, a fictional bank — swap in your own workload and the architecture stays the same.
Uses: a model (Claude/Nova) + a Knowledge Base of product FAQs and policies + Guardrails to block off-topic or unsafe answers. Answers questions with citations, escalates when unsure.
Uses: an orchestrator agent routing to specialist sub-agents (fraud scoring, dispute evidence, compliance). AgentCore Identity scopes each agent's access; Observability traces every decision.
Uses: AgentCore Gateway to expose settlement, chargeback, and payout APIs as tools; Memory for multi-turn context; a Knowledge Base for merchant onboarding docs.
Uses: Bedrock Data Automation to extract structured fields from documents, a model to reason over them, and DynamoDB tools to record results.
Before the lab, sketch one agent for a workload you own. These five questions map directly onto the Bedrock building blocks:
retrieve, and deploy to AgentCore Runtime — the four pillars, hands-on.