For technical teams

How we build it.

This page is for the person who gets asked "is this legit?" It covers the architecture, the models, how data is handled, how we test, what we monitor, and what the client owns. No marketing language. If something you need isn't here, ask and we'll answer in writing.

What we build, in one paragraph

Each client gets a custom system with three layers: a knowledge layer built from their documents, systems and conversation history; a model layer that uses current frontier language models through their business APIs; and an action layer that connects to the client's existing software so the AI can do things, not just answer. On top of that sit the channels the client actually uses: a web application, internal tools, and voice, chat and text agents. We design it, build it, test it with the client, run it and keep it current as models and the client's business change.

Architecture

1. KnowledgeYour informationDocuments, product and pricing data, policies, CRM records, call and email history, website content. Indexed and kept in sync with the sources.
2. ModelsFrontier models via APIBusiness-tier access to current models from the major providers. The model is chosen per task and swapped when something better ships.
3. ActionsYour systemsConnections to CRM, calendar, inventory, accounting, phone and email through their APIs. Scoped permissions. Approval gates on anything that matters.
4. ChannelsWhere people use itWeb app, internal tools, voice calls, SMS, website chat. Same brain behind every channel.

Knowledge layer

Answers are grounded in retrieved source material (retrieval-augmented generation) rather than the model's general knowledge. Sources are chunked, embedded and indexed; each answer can cite the document or record it came from. Sources are re-indexed on a schedule or on change, so the system reflects current prices, policies and records rather than a snapshot.

Model layer

We use current frontier models from the major providers through their business APIs, selected per task for quality, latency and cost. We don't train or fine-tune public models on client data. When a provider ships a better model, we evaluate it against the client's test suite and roll it in as part of the managed service. The client doesn't need to know or care which model is running.

Action layer

Integrations use the target system's official API, webhooks or OAuth where available. Each connection is scoped to the minimum access needed (read first, write only where the workflow requires it). Actions that change records, send money, commit to customers or alter bookings run through an approval step by a named person unless the client explicitly decides otherwise for a specific low-risk action.

Voice, chat and text agents

Conversational agents run on a telephony and messaging platform connected to the same knowledge layer. They identify themselves as AI at the start of every conversation, hand off to a person on request or on defined triggers (upset customer, out-of-scope question, high-value decision), and log every conversation. Call recording follows the client's state consent requirements.

What a call leaves behind

Every conversation is logged with what the agent did and why. A sample record, so you can see the shape before you ask for the real thing.

Call record Tue 4:12 PM1 min 52 s
Caller"Hi, we just bought a lot in Linden Hill and we're looking for a builder."
AI"Congratulations. I'm the AI agent here. We've built four homes in Linden Hill. Are you hoping to start this year or next?"
Caller"This spring, if we can."
AI"That works. Daniel, our lead builder, can walk the lot with you Thursday at 10:00 AM. Does that work?"
Caller"Yes, perfect. Thank you."
AI"You're booked. You'll get a text with the details in a minute. If anything changes, just reply to it."
What got logged and why
Caller
New contact createdName and number added to your customer records.
Request
Tagged: new build, Linden Hill, spring start"Bought a lot" matched your new-build rule.
Action
Booked Thu 10:00 AM, site visit with DanielWritten to your calendar. Site visits are on your pre-approved list, so no sign-off needed.
Handoff
Not triggeredNo pricing commitment, no upset caller, no out-of-scope question.
Message
Confirmation text sentFrom your number, with the lot address and Daniel's name.
Recording
Kept 90 daysYour retention setting. Deleted on request.
Sent to
Your customer records and calendar. Nothing else.

Data handling and security

Not used to train public models

We use business and API tiers whose terms exclude training on customer data. Client data is used only to serve that client's system.

Encrypted in transit and at rest

TLS for every connection. Encrypted storage for indexed knowledge, logs and recordings.

Scoped access

Per-user and per-role permissions. A team member, a customer and an owner each see only what they're allowed to. Integration credentials are stored in a secrets manager, never in code or prompts.

Retention you set

Conversation logs and recordings are kept for the period the client chooses and deleted on request. Full export on exit.

Isolation

Each client's knowledge base, credentials and logs are separate. No shared index between clients.

Audit trail

Every action the AI takes against a client system is logged with what it did, on whose behalf, and what it was based on.

Specific providers, regions, retention defaults and compliance requirements (for example HIPAA or industry rules) are confirmed per client in writing before build.

Accuracy, testing and guardrails

Delivery

StageWhat happensWhat we need from you
DiscoveryMap the workflow, the systems involved, the data sources, the risks and the approval points. Scope and price in writing.Time with the owner and the people who do the work today. Read-only access to the relevant systems.
Interactive demoA clickable, working demo of the actual workflow on the client's own data where possible, usually within about two weeks of receiving what we need.Documents, sample conversations, a point person for questions.
Build and testFull build, integrations, test suite from real scenarios, review sessions with the client's team.Write access where the workflow needs it, test participants, sign-off on approval rules.
Launch and runGo-live, monitoring, model upgrades, security updates, source re-indexing, changes as the business changes.A contact for questions. That's about it.

What the client owns, and what happens on exit

Due diligence checklist

Things we're happy to provide or walk through on a call:

Data flow diagram

Where each type of data lives, moves and is stored, per client.

Provider terms

The specific model and platform providers used for your build and their data-use terms.

Access plan

Which systems we connect to, with what scope, and how credentials are stored and rotated.

Test suite sample

What the scenario tests look like and how pass/fail is judged.

Incident process

Who you call, how fast we respond, and how a bad answer or failed action is handled and prevented from recurring.

Exit package

Exactly what an export contains and the format it comes in.

Questions this page didn't answer?
Send them over. You'll get a written reply from the person who builds it.

Ask a technical question