Case study · AI modernization

From keyword search to an AI assistant that finds the answer

A global hotel company with thousands of hotels and millions of guest interactions a year answered chat questions with Amazon Kendra. Guests got document links and snippets instead of answers, results changed with phrasing, and every new topic meant more synonym and relevance tuning. We replaced it with generative AI on Amazon Bedrock. Claude models search the company’s own knowledge by meaning, and AI tools identify the hotel and look up its amenities. Everything answers inside Amazon Connect chat, with a live agent one step away.

88–92%
first answers correct, up from ~70%
15–20%
agent-efficiency improvement
9 months
from discovery to full rollout
Zero
manual synonym tuning
01For you

One chat, from both sides

On the left, the guest’s chat. On the right, what the AI does: it works out the hotel, retrieves the right knowledge, writes the answer on Amazon Bedrock, or hands over to a person. Pick a question to see each path.

Hotel chatAssistant · online
    Amazon Connect chat
    Behind the chatHow the AI finds the answer (Amazon Bedrock)
    Live
    1. Question
    2. Which hotel?
    3. Search knowledge
    4. Write answer
    5. Done
    What the AI knows so far
    Hotel
    —
    Topic
    —
    How sure it is
    —
    What it looked up
    • Waiting for a question
    Messages
    0
    Sources used
    0
    Lookups
    0
    Agent needed
    …

    Illustrative chats. The hotel, guests and amenities are fictional; the flow follows the production design: a hotel identification agent, semantic retrieval, answers generated on Amazon Bedrock, and a live agent when confidence is low.

    02For you

    The challenge

    Guests ask about reservations, amenities, loyalty and policies, and they expect an answer, not a list of documents. Kendra was good at finding documents, but it could not understand intent, summarize, or follow a conversation over several turns.

    So guests got links and partial snippets, asked again, and ended up with a live agent. Answers depended on how a question was phrased. Every new use case, such as hotel-specific FAQs or a policy change, meant more manual tuning of indexes, synonyms and relevance rules.

    The company wanted conversational answers, more chats resolved without an agent, less tuning, and a foundation for voice bots, agent assist and multilingual chat later.

    03For you

    What made this modernization different

    Swapping one AWS service for another is easy. Getting a generative AI assistant to answer reliably, at enterprise scale, is the work.

    • 88–92%

      of first answers correct, up from about 70%.

      Measured by reviewing samples of real production chats, against a target of 85%.

    • When the hotel isn’t clear, the assistant asks before it answers.

      “What about breakfast?” depends on the hotel. The identification agent asks a clarifying question instead of guessing, and keeps the hotel for the rest of the chat.

    • Content cleaned up and organized before the new model went live.

      Answers are only as good as the content. We set chunking and metadata standards and validate content before it is embedded.

    • Every AI change released gradually, and easy to switch off.

      Prompts are versioned and released in phases behind feature flags and canaries, so a change can be rolled back in minutes.

    • Answer quality measured, not just whether the servers are up.

      We log prompt versions and outcomes, and review transcripts regularly, so quality is measured, not assumed.

    04For you

    What changed

    • AnswersBefore: Document links and partial snippetsAfter: A conversational answer, grounded in retrieved knowledge (RAG)
    • First answer rightBefore: About 70% of the timeAfter: 88–92%, from sampled production chats
    • ConversationBefore: Each message on its ownAfter: Multi-turn, with session context and history
    • Which hotelBefore: Results for every hotelAfter: A hotel identification agent finds the right hotel, and asks if it is not clear
    • TuningBefore: Manual synonyms, indexes and relevance rulesAfter: Semantic retrieval; prompts versioned and released behind feature flags
    • KnowledgeBefore: Documents written for a search indexAfter: Chunked, tagged by topic and hotel, validated before embedding
    • EscalationBefore: Repeat questions ended with an agentAfter: Low-confidence answers hand over to a live agent with the full conversation
    • ControlBefore: Changes needed engineersAfter: An admin console for prompts, agents and feature flags, with role-based access
    • SecurityBefore: Search with broad accessAfter: Least privilege, KMS encryption, TLS, private subnets, AWS WAF at the edge
    • ObservabilityBefore: Infrastructure metrics onlyAfter: Prompt versions, response outcomes and AI quality metrics in CloudWatch

    Hover or tap a tile to see what it replaced.

    05For you

    The right answer, the first time.

    Two KPIs were agreed with the business: how often the first AI answer is right without rephrasing or escalation, and how many chats are resolved without an agent. Both were compared against the Kendra-based search.

    • First answer correctBefore~70%After88–92%
    • Agent efficiencyBeforeBaselineAfter+15–20%
    • Relevance tuningBeforeManual, ongoingAfterPrompts and tools in code

    First-response accuracy sampled and reviewed across production chat transcripts (target 85%). Agent-efficiency improvement as documented for the engagement.

    06For you

    How a guest question gets answered now

    The guest asks in their own words. The assistant works out the hotel, finds the knowledge, writes the answer, and hands over to a person when it is not sure.

    1. 01 · AskGuest types a questionIn Amazon Connect chat. Lambda adds the session context and conversation so far.
    2. 02 · ContextWhich hotel?If the hotel is not clear, the hotel identification agent asks first instead of guessing.
    3. 03 · RetrieveSemantic searchEmbeddings find the most relevant knowledge chunks for that hotel.
    4. 04 · AnswerAmazon Bedrock writes itClaude generates a conversational answer from the retrieved knowledge, calling tools such as amenity lookup when needed.
      • Answered in chat
      • Live agent
    5. 05 · EscalateOnly if neededLow-confidence or unresolved chats go to a live agent, with the full conversation.
    Running around every contact
    GuardrailsStandard prompt templates, tone and length controls, confidence thresholds.
    Admin consolePrompts, agents and feature flags managed with role-based access.
    AI observabilityPrompt versions, outcomes, fallback rate and escalations, plus transcript reviews.
    ResilientTwo Availability Zones and private subnets; falls back to a live agent if AI or retrieval is unavailable.
    07For you

    How we ran it

    1. 1Discover and designWorkshops with business, application, security and operations; target architecture; Dev and UAT environments; baseline KPIs.
    2. 2Core frameworkLambda orchestration, Amazon Connect chat integration, the first Bedrock calls, request and session schemas, logging and retries.
    3. 3Understand and retrieveQuery reformatting, chunking and metadata, the embedding pipeline, semantic retrieval, compared against the old keyword results.
    4. 4Optimize answersPrompt templates, guardrails on tone and length, confidence thresholds, fallback and clarification logic.
    5. 5Agentic AIThe hotel identification agent: when to ask, structured lookup tools, context kept across the conversation.
    6. 6Admin, security and readinessAdmin console with role-based access, IAM hardening, KMS and TLS checks, dashboards, runbooks and an operational readiness review.
    7. 7UAT and go-liveFormal UAT, deployment through CI/CD and infrastructure as code, phased traffic with feature flags and canaries, then hypercare.
    08For you

    The outcome

    • Guest chat search moved from Amazon Kendra to generative AI on Amazon Bedrock
    • First-response accuracy up from about 70% to 88–92%
    • 15–20% improvement in agent efficiency
    • Agentic tools for hotel identification and amenity lookup, with clarifying questions when context is missing
    • Multi-turn conversations, with handoff to a live agent carrying the full history
    • An admin console for prompts, agents and feature flags
    • Phased production rollout with feature flags and canary releases
    • No manual synonym or relevance tuning
    What it runs on
    AI
    • Amazon Bedrock
    • Claude models
    • Retrieval-augmented generation
    • Tool calling
    Agents
    • Hotel identification
    • Amenity lookup
    Knowledge
    • Embeddings
    • Vector store (Amazon OpenSearch)
    • Amazon S3 knowledge base
    Contact center
    • Amazon Connect chat
    • Live agent handoff
    Compute and edge
    • AWS Lambda
    • Amazon CloudFront
    • AWS WAF
    Security and operations
    • AWS IAM
    • AWS KMS
    • Amazon CloudWatch
    • Dynatrace
    Delivery
    • Terraform
    • Bamboo CI/CD
    • AWS CDK
    What we learned
    Five lessons shaped how we build generative AI for contact centers now. Answers need prompt governance, or tone and length drift. Quality depends on the content and how it is chunked as much as on the model. Vague questions need a clarify-first agent, not a guess. AI needs its own observability. And it should reach customers in phases, behind feature flags.
    For you
    Why Digiclarity

    A partner AWS has validated, on exactly this kind of work.

    AWS partner credentials
    • AWS Advanced Tier Services PartnerRecognized by AWS for proven delivery, certified people and customer outcomes.
    • AWS Migration Services CompetencyValidated by AWS for moving and modernizing workloads on AWS at scale.
    • Amazon Connect Delivery PartnerValidated by AWS to deliver Amazon Connect, including migrations from Avaya, Genesys, Cisco and other platforms.
    • AWS AI Services CompetencyValidated by AWS for building AI into real products, including the contact center.
    • AWS Experience-Based Acceleration (EBA) partnerWe run EBA engagements with AWS to speed up migrations with hands-on, time-boxed sprints.
    Security and compliance
    • ISO/IEC 27001 certifiedOur information security management system is independently certified to the international standard.
    • SOC 2 Type IIIndependent auditors have tested our security controls over time, not just at a single point.
    Start here

    Have a project like this?

    Tell us what you run today and what needs to change. You will hear back within a week.

    • AWS Advanced Tier Services Partner
    • AWS Migration Services Competency
    • Amazon Connect Delivery Partner
    • AWS AI Services Competency
    • AWS Experience-Based Acceleration (EBA) partner
    • ISO/IEC 27001 certified
    • SOC 2 Type II
    Certified supplierMWDBE certifiedTexas HUB certifiedNCTRCA certified
    +1 (214) 550-14936275 West Plano Parkway, Suite 500, Plano, Texas 75093