One agent · your council & your desk

Decisions you can defend.
Trades you have to approve.

VIGIL is an AI workspace that thinks before it acts — a multi-advisor council, a data-grounded trade desk, and your finance, CRM, mail and document studio, all under one human-in-the-loop agent.

Read the docs
Live market pulse
BTC
ETH
BTC dom.
Fear/Greed
The Council

A workspace that deliberates

Convene an AI council over any decision — CFO, CTO, Legal, Product lenses argue, score, and a chairman synthesizes a verdict. Run meetings, crystallize artifacts, ground everything in your own documents.

The Desk

A desk that never trades alone

Forecasts and a data-grounded signal debate propose trades — every order passes a single-use human approval gate, capped at 5% of NAV. Connect your own broker; keys never leave your account.

Everything in one workspace

Each surface is a real tool the agent can read, reason over, and act in — never autonomously where money or messages are involved.

AI Council & Meeting Room

Multi-advisor deliberation over any topic or transcript, with weighted consensus and a chairman's verdict.

Trade Desk

Live candles, forecasts, and a data-grounded signal debate — proposing trades behind the approval gate.

Finance

Capture → classify → reconcile your books. A P&L the CFO suite reasons over.

CRM

Contacts and a deal pipeline; value rolls up to Finance, deals route to the Council.

Mail

Inbox triage over your mailbox, with AI classification. Outbound is review-then-send.

Studio

Draft, refine, and crystallize artifacts — proposals, briefs, contracts — grounded in your Vault.

Vault

Your real documents, so the agent cites what your contracts and statements actually say.

Audit

A tamper-evident, hash-chained log of everything the agent does. Defensible by design.

How the agent works

01

Thinks first

Before building or recommending, it brainstorms approaches and presents a design. No jumping to output on unexamined assumptions.

02

Grounds in your data

It reasons from your Vault documents, your live broker, your books — citing real numbers, never fabricating.

03

Waits for you

Trades go through an approval gate; outbound mail is review-then-send. You stay in control of anything with consequence.

Human-in-the-loop

Single-use approval gate on every order. 5%-NAV cap. Nothing moves money on its own.

Your keys, your data

Connect your own broker; credentials stay in your account. Every record scoped to you alone.

Dissent by design

The council surfaces the bear case, not just the bull. You can always override the verdict.

Evidence over confidence

No 'done' without verification. No tax or trade claim without a cited source.

Questions, answered

What is VIGIL?+

VIGIL is an AI workspace that deliberates before it acts. It combines a multi-advisor AI council, autonomous AI departments, and a human-in-the-loop crypto trade desk with your finance, CRM, mail, and documents — all under one agent that thinks first and waits for your approval.

How is VIGIL different from a chatbot or AI assistant?+

Unlike a chatbot, VIGIL is built around human-in-the-loop control: every trade passes a single-use approval gate and outbound mail is review-then-send, so nothing with real consequence happens autonomously. It also brainstorms and presents a plan before acting, and grounds answers in your own documents and live data.

What is the AI council?+

The AI council is a panel of advisor lenses — CFO, CTO, Legal, and Product — that debate a decision, score it, and have a chairman synthesize a defensible verdict. It surfaces the bear case and dissent instead of hiding it, and you can always override the verdict.

Can VIGIL trade crypto automatically?+

No. VIGIL proposes trades from data-grounded forecasts, but every order is human-approved and capped at 5% of NAV. You connect your own broker and your API keys never leave your account.

Is my data private and secure?+

Yes. Every record is scoped to your account with row-level security, your broker and API keys stay in your account, and a tamper-evident, hash-chained audit log records everything the agent does.

What can VIGIL's AI departments do?+

VIGIL runs autonomous AI departments for recurring work — support triage, finance reconciliation, revenue follow-ups, lead scouting, and legal review. Each department only counts a task as done when it passes a deterministic effectiveness check, so output is verified, not assumed.

Bring your judgment.
We'll bring the rigor.

Create an account and convene your first council, or wire up your trading desk in minutes.

Sign in