Reconciling 86 invoice lines against POs
Virtual employee platform you can trust.
AI teammates that work in your tools, inside the rules you set.
Send 9 corrected follow-ups to external contacts
“The ability to quickly onboard agents at‑scale has been a key inflection point in KGG’s growth.”
Trustworthy agents for any role.
Start with one. Grow to dozens.
Everything your security review will ask.
Sixteen controls across policies, identity, data and infrastructure.
Execution policies
- Governance policies
Define which actions agents may take. Allow, warn, require human approval, or block an action before it runs.
- Guardrails
Baseline protections govern tool connections, integration access, and policy changes. Add presets that fit your organization.
- Prompt-injection protection
Scan untrusted messages and tool results. Feed risk signals into policies to block suspicious content or require approval.
- Kill switch
Say “stop” to halt a running task. Pause an agent to prevent new messages and scheduled work from starting.
Identity & access
- Accountable human
Every agent has a named manager who sets direction and can approve or deny sensitive actions.
- Separate agent identities
Provision separate identities and credentials for agents. Keep their access distinct from human accounts.
- Communication controls
Choose who can reach each agent, internally and externally. Restrict access to specific people and channels.
- Org-wide controls
Apply policies across every agent. Organization-level restrictions cannot be loosened by an individual agent’s rules.
Data & providers
- Full auditability
Review actions, policy decisions, and configuration changes in a tamper-evident audit log. Export records for independent review.
- No training by default. You own your data.
Training-data collection is off by default. Your organization controls whether to explicitly opt in.
- Full provider control
Choose approved model vendors, pin models per capability, and disable providers your organization does not allow.
- Data-flow transparency
Inspect provider and model choices, review subprocessors, and restrict processing to providers you approve.
Infrastructure & limits
- Budgets & cost controls
Set spend caps per agent and scheduled task. Track usage and stop work when a limit is reached.
- Bring your own keys
Use your own model-provider credentials so inference runs under your account and commercial terms.
- Dedicated tenants
Choose a dedicated data plane with isolated storage, secrets, and independently revocable tenant access.
- Multi-cloud & BYOC deployment
Deploy a dedicated data plane in your own AWS or Google Cloud account and chosen region, with private networking and encryption keys you control.
While you were busy.
They finished the work.
Real tasks, done in the tools you already use.
Working now
NoahFinance operations
LunaExecutive assistantReading 23 new emails and drafting the replies that need you
Recent activity
Scheduled taskNew
DanaUpdated 12 stale deals in HubSpot
Weekly pipeline review · 2m 14s
Scheduled task
DanaFlagged 3 deals with no next step to their owners
Weekly pipeline review · 1m 08s
Slack
DanaLogged call notes on 9 HubSpot deals
52s
Slack
LeoVerified and enriched 41 new leads in Salesforce
48s
SlackNew
AvaWaiting for approvalSend the Q3 renewal quote to Northwind
Needs your approval
Microsoft Teams
SophieAdded Monday's agenda to the management doc and asked 7 people for topics
1m 05s
Phone call
MarcusBriefed you on 4 changed opportunities before the account review
2m 02s
A model answers questions.
A Vicaro employee finishes the task.
Memory, subagents and your rules, around whichever model you pick.
Any model
- Anthropic
- OpenAI
- AWS
- Databricks
Vicaro Harness
- Long-term memory
- Subagents
- Smart model routing
- Self-improvement
- Integrations
- Governance
Finished work
- Enriched 41 new leads in Salesforce
- Sent the Q3 renewal quote, after your approval
- Delivered the weekly management brief
No new app to learn.
Same memory, same rules, every channel.
Mention them in any channel, DM or thread. Explore Slack
@Sophie which renewals need attention before Monday?
Three renewals are due and two tools overlap. Details are in the thread.
Keep your stack.
Add the workforce.
Explore integrations - Your tools
- SlackSalesforceGoogle DriveNotionGitHubJiraPlus API and MCP
- Your models
- AnthropicOpenAIGoogleAWSDatabricksYour keys
They only do what you allow.
Plain-language rules, checked before every action.
Rule: “Only talk to John, Dan and the Marketing team.”
Attempt in Slack: Reply in #marketing
Result: Allowed
Rule: “Managers approve new Salesforce accounts.”
Attempt in Salesforce: Create Northwind account
Result: Needs approval
Rule: “Never email anyone outside the company.”
Attempt in Gmail: Email jane@northwind.com
Result: Blocked
Rule: “Ask before deleting anything.”
Attempt in Google Drive: Delete “Q3 forecast”
Result: Needs approval
No surprise spend. No blind spots.
A budget per employee
Warns as spend climbs, stops at the cap.
- #4,821
9f2c41 - #4,822
3a7bd9 - #4,823
c51d7e
A log you can prove
Chained, signed and kept up to 10 years.
- Salesforce, encrypted
- Notion, encrypted
- Google Drive, encrypted
- GitHub, encrypted
Keys that stay sealed
Encrypted, scoped, never shown again.
Start with one employee.
Grow at your pace.
One credit pool for the whole team.
Of compute: models, browsers, sandboxes, and web tools. On-Demand is $2.00 per credit with no commitment; Growth at $1.90 with a $3,000 monthly commitment, Scale at $1.80 with a $6,000 monthly commitment, and Scale Plus at $1.70 with a $9,000 monthly commitment. All plans are month to month.
On-Demand
Start with a pilot. Add credits as you go.
Pay as you go. Top up when you need.
Apply for accessWhat’s included:
- Top-up credits never expire
- One shared pool across your organization
- All frontier models and tools
- Standard support
Growth
Grow your team with AI employees.
$3,000 / month commitment
Book a demoEverything in On-Demand, plus:
- About 1,579 credits each month
- Top-ups at $1.90 / credit
- Subscription credits renew monthly
- Dedicated shared Slack channel
Scale
Bring AI employees to teams across your company.
$6,000 / month commitment
Book a demoEverything in On-Demand, plus:
- About 3,333 credits each month
- Top-ups at $1.80 / credit
- Subscription credits renew monthly
- Dedicated shared Slack channel
Scale Plus
Run AI employees across every department.
$9,000 / month commitment
Book a demoEverything in On-Demand, plus:
- About 5,294 credits each month
- Top-ups at $1.70 / credit
- Subscription credits renew monthly
- Dedicated shared Slack channel
- Month to month
- Auto top-up
- Budget per employee
Everything you’d
ask before hiring.
Something else on your mind? Talk to us.
What is an AI employee?
An AI teammate with its own role, manager, and tools. It works in the channels your team already uses, carries context between conversations, and turns a request into a finished piece of work.
Where do they work?
In Vicaro Chat, Slack, Microsoft Teams, email, and phone (calls and text), and on Zoom, Google Meet, and Teams meetings. The same employee keeps its identity, memory, and policies across every channel.
Which tools can they use?
Thousands of integrations, plus your internal APIs and MCP servers. Each employee also has its own computer, a cloud browser, and a code sandbox.
How do we stay in control?
Policies decide who an employee can talk to, what it can do in each app, and which actions need approval. Every governance decision goes into a sealed audit trail, kept 365 days by default and up to 10 years.
How is our data protected?
Data is encrypted in transit and at rest. Credentials are scoped and injected only when a tool needs them, never placed in prompts. The trust center covers the full set of safeguards.
Does Vicaro support SSO and role-based access?
Yes. Your team signs in with single sign-on through your identity provider, people and groups sync from it, and role-based access decides who can manage, work with, and oversee each AI employee. Everything is also available through the Vicaro API.
Can we choose the providers?
Yes, for everything, not only the model. Choose the providers behind inference and tooling, such as browsers, sandboxes, and search, bring your own keys, and allow only the ones you approve.
Can we run Vicaro in our own cloud?
Use Vicaro’s cloud, or talk to us about a private deployment in your own cloud account.
How does pricing work?
One shared credit balance for your whole team, where a credit covers $1 of compute spend. Pay as you go, or commit monthly from $3,000 for lower rates. Top-up credits never expire.
How fast can we get started?
Apply for access first. Once your organization is approved, hiring an AI employee takes a few minutes: give it a role, a manager, and a budget, and hand it a first real task in Slack.
Hire your first AI employee.
It works inside your rules.