Serve your agents fresh data at Redis speed.

Learn how
Redis IrisRedis Iris
Platform
Platform
Redis IrisReal-time context for agents Redis LangCacheSave on tokens for common questionsRedis Context RetrieverLeverage context from anywhereRedis Agent MemoryAgentic memory for consistent experiencesRedis Data IntegrationCDC across your structured data Redis FlexMore data, more speed, less costCachingSub-ms read/write at scaleStreamingEvent-driven messaging & data pipelinesSession managementFast, persistent storage for sessions SearchSearch & query for structured dataFeature storeReal-time ML feature pipeline for apps & agents
Get RedisDownloads
Deploy
Deploy
Redis CloudFully managed, fully flexibleRedis SoftwareOn-premRedis open source frameworkRedis 8.8PricingLet’s talk numbersRedis on AWSBuy with cloud commitsAzure Managed RedisMicrosoft-supported RedisRedis on Google CloudRedis from the marketplace
Tools
Redis InsightUI to visualize, query, & debugRIOTGet data into Redis from anywhereClient librariesPython, Node, Java, Go, .Net, & moreSDKsConnect Redis to your apps
Get RedisDownloads
Solutions
AI & ML Apps
Scale agent & agentic systems Everything you need to be successful RAGUnderstand how Redis powers RAGSemantic searchRight answers, right nowMLLeverage your features, fastToken optimizationAll the AI without all the cost
Core Workloads
Fraud detectionStop fraud, protect customersReal-time decisionsAct on data in real timeCaching & performanceOur bread & butter Real-time messagingStreams at the speed of thoughtSession managementConsistent experiences everywhereLeaderboardsKnow who’s winning
Industries
Financial servicesE-commerce & retailGamingHealthcareTelco
Get RedisDownloads
Devs
Docs
Redis CloudThe nitty grittyWelcome to the communityJoin the largest open source community in cacheDev HubAll the tools to build
Training
UniversityBecome a Redis expertTutorialsHow-to for whatever you’re trying to doQuick startsGo 0 to 1: Redis fastKnowledge baseGet support
Learning
BlogAll the wordsResource centerEverything you need, in one placeDemo centerAnything & everything, in actionReference architecturesNo guessing, just deploy
Resources
Customers
Resource Center
Events
Virtual & live eventsCome say hello
Partners
Find a partnerAWSGoogleMicrosoft
Learn how to BuildVisit our dev hub
Try RedisBook a meeting
Resource Center
Events & webinarsBlogVideosGlossaryResourcesArchitecture DiagramsDemo Center
Resource Center
Events & webinarsBlogVideosGlossaryResourcesArchitecture DiagramsDemo Center
Back

In-person

Redis and AWS logos

Redis & AWS Workshop PH

Aug 06, 20261:00 PM – 5:00 PM PHT
Amazon Web Services OfficeManila, PH
Register now

Build faster AI apps on AWS with Redis Iris

Join Redis & AWS for a technical workshop where you will build an AI banking chatbot using Redis Iris, Redis's unified context engine for agents.

Through hands-on labs building your own retail banking chatbot, you will learn how to use Context Retriever, Agent Memory, and LangCache to give your agents real-time data access, persistent personalization, and token-efficient caching. Leave with a fully working chatbot that grounds every response in live customer data without sacrificing speed or cost.

You’ll learn how to:

  1. Build a production-ready agent using Redis Iris and Amazon Bedrock
  2. Ground AI agents in real-time business data so they respond accurately and stay up to date
  3. Give AI agents persistent memory to deliver personalized, context-aware experiences across sessions.
  4. Reduce LLM costs and response latency without sacrificing answer quality
  5. Why Redis Iris is the context layer enterprises trust to make AI agents reliable and production-ready at scale

Whether you’re an architect, developer, data engineer, or AI practitioner, you’ll leave with practical skills and real-world insights you can immediately apply to your own AI projects.

Seats are limited. Register today to see how Redis and AWS can help fast-track your AI journey.

Agenda

  • 1:00 PM
    Registration

  • 1:30 PM
    Intro to Redis Iris

    Overview of Redis AI capabilities and positioning in modern AI architectures, and key use cases

  • Hands-on lab

    Environment Setup, Provision a Redis Cloud database, Clone and configure the lab repository

  • Lab 1: Vector Search

    Build a Retrieval-Augmented Generation (RAG) pipeline for policy document search and question answering

  • Lab 2: Semantic Router

    Implement AI guardrails to identify and block off-topic or unsupported queries

  • 3:30 PM
    Tea Break

  • 4:00 PM
    Lab 3: LangCache

    Accelerate LLM applications with semantic caching for near-instant responses

  • Lab 4: Context Retriever

    Generate MCP tools automatically for real-time data access and retrieval

  • Lab 5: Agent Memory

    Implement session memory and long-term user preference management for AI agents

  • 5:00 PM
    End

Register to attend

Get started with Redis today

Speak to a Redis expert and learn more about enterprise-grade Redis today.

Try for freeTalk to sales