Products

Two shipping, one in development. The rest we call research.

Status here means what it says. Production is people outside the company on real data. Internal is production on our own operations only — we are the tenant. Development is being built: the interface stands and the engine behind it runs, but nobody outside uses it yet. Research is a line we work on without promising a date — listing it as a product would be the easy lie, so we do not.

ARE5 Technologies
01

Shipping

Products on infrastructure we operate. Two of them serve users today; the third is in development and its card says so.

02

What they share

Three different markets on one engine. That is the point of building the engine first — a new product is a configuration, not a rewrite. It inherits the graph, the control layer, memory, the voice channel, billing and the infrastructure; what it adds is its own tools, its own knowledge base and its own interface. That is why the work left on any one of them is specific enough to list rather than an open question.

SHARED

The same agent graph

Routing, extraction, conversation and tool execution are the same nodes in every product. What changes is the set of tools an agent is allowed to call.

SHARED

The same control layer

Whether the action is issuing an invoice or publishing a site, it passes the same gate and leaves the same kind of record. One place to review, one place to change the rules.

SHARED

The same isolation model

Customer data, memory and retrieved knowledge are separated per organization by design, not by a filter applied afterwards. Nothing crosses between customers.

03

Research

Lines we work on that are not products. They are listed because they explain where the engine is going, not because they are for sale.

Ruby
Vertical research
A voice-first concierge for real estate: the client calls, the agent works out what they are looking for, searches available property and books the viewing. The distinction that matters is that a search portal returns listings, while this would carry the errand. It is designed down to pricing and distribution, and the engine it would run on is already deployed — but the build has not started, and it waits behind the products with users.
Paused · design only
Athena
Workspace research
A single environment for work done with an agent — code, writing, design and review in one place instead of five tabs. Paused while the products with users take priority.
Paused
Voice
Channel research
Speech-to-speech as a first-class channel rather than a transcription bolt-on: the agent hears, reasons, calls the same tools and answers, without dropping to text in between.
In progress
04

Questions about the line

What people ask before deciding which of these is relevant to them.

Which of the three can I use today?
Crafty publishes sites for people outside this company. AIO runs in production on our own operations, where we are its first tenant — which is how the rough edges get found before a customer meets them. X-Zero is in development: its interface is finished and the engine behind it is deployed, so what remains is joining the two and the parts that belong to a person rather than a company.
Why does one engine serve three different products?
The agent graph, the control layer and the isolation model are shared. Each product is configuration on top of them rather than a separate codebase, so a correction in the engine reaches all three at once instead of being ported three times.
What separates a shipping product from research here?
Whether it serves somebody outside this company. Research means the engine works but the product around it has no users yet. We name that plainly instead of listing it as available and explaining later.
Does taking one product commit me to the others?
No. Memory, documents and retrieved knowledge are isolated per organization, and each product stands on its own. Nothing crosses between them or between customers.