Aetheria Systemsthe space between systems

How it works

Exactly what happens on a call — start to finish. This describes the demo as it's built today: a conversational voice line where Amazon Connect and the AI meet live Salesforce data.

Architecture — how it's built

One inbound call flows left to right through the stack. Telephony and the AI live in AWS; the customer data lives in Salesforce.

Telephony

Caller

An inbound phone call.

AWS

Amazon Connect

Contact flow + voice (Polly generative, Matthew). Answers, identifies the caller, plays the greeting, streams the conversation.

AWS · AI

Amazon Q in Connect

Self-service AI orchestrator. Understands natural speech and decides which tool to call — no menus.

AWS · code

Lambda tools

Deterministic functions. Pull the data, compose the exact spoken answer, apply policy. The AI never invents a fact.

Data

Salesforce + KB

System of record — contacts, prescriptions, cases — plus the policy knowledge base and a shipment-tracking feed.

Outcome

Answer & routing

Spoken back word-for-word; the call routes to the right queue on fixed rules.

Inside Salesforce, agents see all of it in one screen: the Amazon Connect softphone is embedded in the Service Console via SCC-AC (Salesforce Contact Center for Amazon Connect).

How it's configured

Telephony & voiceAn Amazon Connect contact flow handles the call; the spoken voice is Amazon Polly generative (Matthew).
ConversationAn Amazon Q in Connect self-service AI agent (the orchestrator) drives the natural-language dialogue and calls tools — there is no press-1 menu.
ToolsAWS Lambda functions, exposed to the agent through an AgentCore gateway. They own every fact and judgment; the model only decides which tool to call.
DataSalesforce over secure API (identity, prescriptions, orders, cases), a Q in Connect knowledge base (policy), and a stand-in carrier API for tracking.
Agent desktopSalesforce Service Console with the Amazon Connect softphone embedded via SCC-AC — one screen for the human agent.

What happens the moment a call connects

  1. The caller is looked up before they hear anything

    We take the calling number and search Salesforce for a Contact whose phone matches — so the line can greet a known customer by name.

  2. The line greets a known customer by name

    If recognized, the greeting is personalized from their Salesforce record: "Thank you for calling Companion Pet Pharmacy. Welcome back Sarah. How can I help you today?"

  3. The caller says what they need, in their own words

    No press-1 menu. The caller speaks naturally and an Amazon Q in Connect AI agent handles the conversation — understanding the request, looking up real data, and answering.

  4. The AI hands the call to a person on the right team

    When the conversation is done or needs a human, the AI reports who the caller is and what they want, and fixed rules choose the queue. The AI never picks a queue itself — routing is deterministic.

The one rule that beats everything: if the caller asks for an agent, a representative, a human, or a person — at any point, even mid-sentence — the call transfers to a human immediately, no questions, no self-serve first.

Who the caller is (identification)

We match the calling number against the Salesforce Contact phone field:

ResultWhat the IVR does
Exactly one matchRecognized. Greet by name and continue.
More than one matchTwo records share the number — we never guess. The caller is not identified and goes to a person.
No Contact matchFall back to an Account phone match; if still nothing, identify by voice (ask role, then an account number, read back and confirmed, up to three tries).

What the caller can get answered

Every answer is built in code from real Salesforce data and spoken back word-for-word, so the AI can't rephrase a fact, get vague, or flip a judgment.

Order & delivery status

Real status, location, expected delivery, and — for a refrigerated medication — whether the cold chain held.

Caller: "Where is Bailey's insulin order?"
IVR: "Bailey's Vetsulin insulin shipped on August 30th. It's out for delivery in Atlanta, expected today by 7 PM. The cold chain is normal, so it's been kept at the right temperature."
On track vs. late — judged in code

For an order still in processing, the system compares the order date to the standard window (~5 business days) in code. Within it, it reassures; past it, it hands the caller to a person. Never a guess.

A cold-chain safety problem

If a refrigerated shipment's temperature indicator tripped in transit, the IVR leads with a safety warning and arranges a replacement through a person — it does not just read a status.

Refills, existing cases, prescriber questions

Refills: it knows how many are left and whether AutoRefill is on; zero refills needs vet authorization. Cases: it surfaces the caller's open Salesforce case by subject. Clinical/controlled: it never improvises — it consults policy and routes to the right team.

Where the call ends up (routing)

The AI establishes the facts; the phone system chooses the destination from fixed rules — predictable and auditable.

If the caller is…They go to…
Asking for a personStraight to a human — immediately, no questions
A prescriberPrescriber queue
A pet ownerSupport queue
Unidentified, ambiguous, or unclearSupport queue — a person always gets it
The conversation causes the retrieval; the code makes the judgments. Speaking naturally is enough to pull a caller's real Salesforce records — no account numbers, no menu. And every decision that matters is computed in code from live data, then spoken back word-for-word. The AI drives a natural conversation; it does not invent facts or make the business calls.

See it live on the Try it page, or the exact records behind it on Data & sources.