AI that actually
understands your business
Most AI guesses. Ours is grounded in a living model of your world — your language, your systems, your numbers. One platform: Envoy, the AI your team works with, and Envoy Warehouse, the governed data layer underneath that keeps every answer honest.
The idea
An ontology is just a clear model of how your world fits together.
Generic AI is fluent but rootless — it doesn't know your terms, your systems, or what your numbers really mean, so it improvises. We give it roots. We build a model of your business and put AI on top of it, so it speaks your language and answers from facts, not vibes.
The platform
Two products, one foundation
The surface your team talks to, and the governed data layer it stands on — joined by a shared model of your domain.
The surface · Envoy
The AI your team actually uses
A white-label assistant your people sign into — conversational, with your documents, agents, and skills tuned to how you work.
The foundation · Envoy Warehouse
The governed data layer underneath
Your data, modelled as typed objects and named metrics computed deterministically — and served to any AI through a locked-down MCP server. Trustworthy numbers, never raw rows.
AI that speaks your language
Envoy is a white-label AI product your team signs into — working from day one, then shaped to your domain. No toolkit to wire together, no model plumbing to maintain. It empowers your people; it doesn't replace them.
See Envoy in a demoquery_metric(activity, average · segment) · ~134 tokens · cited
Conversational workspace
A clean chat interface your team already knows how to use — no training required.
Your documents, retrieved
Upload to a workspace; Envoy retrieves and cites the right passages with hybrid search (RAG).
Agents, tools & skills
Ready-made agents out of the box, plus bespoke ones tuned to your terminology and workflows.
Workspaces
Spaces tailored to each team — each with its own documents, agents, and context.
Deep integrations
Connects to the systems you already run — CRM, accounting, storage, comms, data — via a real integration framework.
Admin console
Your team manages users, branding, agents, tools, and usage themselves. No black box.
Specialist agents
Agents built for the actual job
Not one generic chatbot, but focused agents — each tuned to a real task and powered by composable, portable skills. These run in Envoy today, and we build bespoke ones around your work.
Contract Review
Compares an AS 4902 contract against your organisation's preferred positions clause-by-clause, flags departures from your playbook and the standard's defaults, and renders a departures table right in the chat.
Tender Response
Draws on your past tender responses to draft consistent, well-supported answers — a single focused question, or a whole tender at once — ready to review and paste.
Commercial Contract Review
LegalReviews vendor agreements, MSAs, and SaaS subscriptions against your Legal Playbook — a deviation memo with severity, redlines, and approval routing.
Privacy / DPA Review
LegalReviews Data Processing Agreements term-by-term; detects processor vs controller direction and flags transfer mechanisms and sectoral overlays.
Employment Review
LegalReviews offer letters, employment and contractor agreements against your Legal Playbook, with jurisdiction-specific research.
NDA Triage
LegalFast GREEN / YELLOW / RED triage of inbound NDAs — so only the ones that genuinely need lawyer time get routed there.
IP Clause Review
LegalReviews IP clauses — assignment, licence, warranties, indemnities — against your playbook, with assignment-gap detection.
Accounting Review
FinanceReviews contracts for accounting implications — revenue recognition, leases, modifications — under IFRS, US GAAP, or AASB.
Research Analyst
GeneralCombines web research with your workspace documents to produce sourced, structured briefings.
Summariser
GeneralShort, medium, or detailed summaries of any document you upload.
Need something specific? We build agents tuned to your domain →
Skills
Composable know-how, yours to keep
A skill is a small, open SKILL.md file that teaches an agent one job — when to step in, how to do it, which tools to use, plus any reference files it needs. Agents load them only when relevant. Some run on demand; others are always on, encoding conventions like citation discipline and locale.
legal-playbook-setup
On demand
An interactive interview that captures your team's positions on NDA terms, vendor contracts, escalation, and delegations.
nda-review
On demand
Fast GREEN / YELLOW / RED triage of inbound NDAs, so legal time only goes where it's genuinely needed.
extract-tender-questions
On demand
Parses a tender RFT into a structured list of the questions and criteria a bidder must answer.
standards-reference
On demand
Cites and applies external standards correctly — IFRS, US GAAP, AASB, and data-protection regimes.
research-brief
On demand
Produces a structured research brief: background, key findings, sources, and open questions.
document-extraction-helper
On demand
Pulls structured data — tables, key/value pairs, entities — out of PDFs, CSVs, and spreadsheets.
source-fidelity
Always on
Strict citation discipline: quote the source verbatim, then paraphrase. Never invent a figure.
aussie-english
Always on
Locks the conversation to Australian English spelling and conventions.
user-locale
Always on
Carries the user's locale so numbers, dates, and currency are formatted consistently.
Export — take it anywhere
Download any skill as a name.zip — its SKILL.md plus every reference file and asset. Because it's the same open Agent Skills format Claude uses, it runs in Claude (Code & API) and other agent tools, not just Envoy.
Import — bring your own
Add a skill by pasting its SKILL.md, uploading a .md or .zip, or filling in a guided form. Envoy lints it, versions it, and tracks every change — so your team can author, fork, and refine skills with no lock-in.
Numbers AI can actually trust
Envoy Warehouse ingests your data and models it as an ontology — typed objects, named metrics, and dimensions. Metrics are computed deterministically in the database and served to AI through a locked-down MCP server, so models reason over governed facts instead of guessing from raw tables.
- Deterministic metrics. Every number is computed in Postgres from a defined formula — same question, same answer, every time.
- Token-efficient by design. A full management summary is ~134 tokens, not thousands of rows — fast, cheap, and within context.
- Locked-down MCP server. Nothing is discoverable without a credential. Connect Claude (Desktop, web, Enterprise) via token, OAuth, or Microsoft Entra SSO.
- Configuration, not rewrites. Onboarding a new client or domain is a new ontology config — the generic core never names a client.
Customised to you
Built around your work, not the other way round
Your language, your workspaces, and agents and skills tuned to exactly what your team does.
Your language, your workspaces
Your terms, your documents, your way of working — organised into workspaces shaped to how your team actually operates.
Bespoke agents & skills
We build highly targeted agents and skills for your specific tasks — tuned to your terminology, documents, and workflows. Not generic assistants bolted on.
Skills that travel with you
Skills are open SKILL.md files — the same format Claude uses. Export them and they run in Claude (Code & API) and other tools, not just Envoy.
See how export & import work →Trust & security
Your brand, your data, honest answers
Security is structural — enforced by the database and the protocol, not by hopeful application code. And because the numbers come from the warehouse, the AI can't make them up.
Your brand and domain
Runs white-label under your logo, colours, and domain. Your team and customers see your product, not ours.
Schema-per-tenant isolation
Each tenant's data lives in its own PostgreSQL schema — isolation enforced by the database itself.
Encrypted credentials
Integration credentials are encrypted per tenant; authorisation is explicit on every action.
Deterministic, cited answers
Numbers are computed in the warehouse and cited. Same question, same answer — no hallucinated metrics.
Locked-down MCP
Nothing is discoverable without a credential — token, OAuth, or Microsoft Entra SSO. Every call is scoped.
Full observability
Every agent run, tool call, and cost is captured — so you always know what your AI is doing.
How we work with you
We get your team self-sufficient
As an early-access design partner you work directly with us — but the goal is always to hand your team the controls, not to make you depend on us.
Understand
We learn the problem and the language your team uses to describe it — and model it as your ontology.
Tailor
We set up Envoy and the Warehouse around that — agents, metrics, tools, and integrations tuned to your work.
Hand over
Your team takes the controls through the admin console and runs it themselves.
The Ontology AI
Let's ground AI in your business
A genuine conversation about the problem you're trying to solve — no pitch, no pressure. We'd rather make your team brilliant at solving their own problems than sell you a black box.