AI employee FAQ

A chatbot answers from a generic model and sends what it produced. A digital employee runs a role with a validator that can reject its own output, works from your brand material, and hands the result to a person before it reaches a customer or a budget.

Sales, customer support, HR and recruiting, accounting, and operations. Each one ships with its own workflow, scripts and KPI. Custom roles and workflows sit on the Enterprise plan and are built with you.

It reads data, analyses it, drafts, and writes every run to the journal. It does not send a message and does not spend money on its own: those sit behind the approval gate, and an action the rulebook does not recognise waits for you by default.

It replaces the repetitive share of a role, so the same human can manage a higher-value portfolio. Teams use it to avoid the next hire while keeping the people they have. The ROI calculator prices both sides of that trade with your own numbers.

Internal enablement runs the same loop as customer support: your handbooks and policies become knowledge items the role reads on every run, it drafts the answer with the passage it used attached, and a person sends it. There is no LMS connector in the platform today, so the material comes in as documents and the answers go out through the channel your team already uses.

You pick a role and write the instructions in plain language — the job, the tone, the rules, what a good outcome looks like. That brief is what every run reads from, so two answers a month apart cite the same facts.

Your help center, PDFs and past tickets become knowledge items the role reads on every run, which takes an afternoon to load. Week one runs in shadow mode so you can measure how often the draft is right before anything depends on it.

The role shadows your current process: it drafts, a person reads the draft against the source and sends. You get a countable answer to one question — how often the draft went out unedited — before anything is handed over.

Yes. You can run one Starter employee and add Scale employees as your team grows. Billing is per employee based on the plan each employee is assigned.

Starter customers get email support. Scale customers get priority support. Enterprise customers get a dedicated success manager and a launch plan.

Unistaff.ai is priced per digital employee only. Add as many human teammates as you want to the workspace at no extra cost. Usage like messages or tokens is not metered.

The Starter plan includes a 14-day free pilot with full feature access and no credit card required. You can launch one digital employee in production and upgrade or cancel anytime.

Yes. You can run one Starter employee and add Scale employees as your team grows. Billing is per employee based on the plan each employee is assigned.

Scale is for teams that want up to 5 digital employees with custom briefs and priority support. Enterprise adds unlimited employees, custom roles and workflows, SLA-backed support, and a dedicated success manager.

You can upgrade, downgrade, or cancel at any time. Annual Enterprise contracts include predictable pricing and SLA terms.

A full lead record has two doors: an operator session or a bearer secret. The API verifies one of them itself before it touches the database, independent of the page gate. Every other caller receives a masked record — an initial and the names of the contact channels, with the name, phone, email and free-text answers left in storage.

No. Unistaff holds no certification of its own, and none is in progress. Our hosting providers publish their own certifications on their own trust pages; those cover their platforms and say nothing about this application. Treating a provider's audit as an audit of Unistaff would be wrong, and we say so before a procurement review has to ask.

Separation runs on the deployment boundary: a deployment carries its own database, operator key and credential key. The schema holds no tenant, organisation or workspace column, so row-level separation inside one shared database stays absent today. Ask which deployment your pilot would run in before you plan around it.

Four gates sit ahead of every outbound write to an ad account: the kill switch, the daily and monthly spend caps, the autonomy matrix, and a matching approved change request. An action missing from the matrix requires human approval by default, an expired approval stays expired, and an unreachable governance database stops the write where it stands. One limit worth stating: a cap you have not set gives the caps gate nothing to compare against, so it passes and the approval gate is what holds the spend.

Those three do not exist today. Operator access is a single shared key with no per-user accounts, MFA or SSO; the journals are internal tables with no customer-facing search or export; and no DPA, subprocessor list or standard contractual clauses have been drafted. Write to hello@unistaff.ai before you build a rollout plan that depends on any of them.

Meta ads for reporting, with writes behind a separate token and the approval gates. A lead endpoint any form or quiz can post to, with an email to you when a lead comes through your own site form. A daily capture of the public Meta Ad Library for competitor ads. Anything else is a connector we scope with you before we promise it.

One platform connector ships today, and it is Meta ads. Salesforce, HubSpot, Zendesk, Intercom, Greenhouse, Lever and the rest are integrations we build against your account during a deployment. We name what we have built and leave the logo wall to someone else.

It writes the message; a person sends it through the channel you already use. There is no SMS provider and no voice connector in the platform today, and we would rather say that than imply a phone line that does not exist.

The status endpoint answers with that state and names the missing settings, so an empty dashboard is distinguishable from a broken one. A scheduled job without its secret stays shut rather than running open.

The record is written first, then the notification is attempted with a five-second timeout. A delivery failure is recorded as an error line carrying the lead id and an outcome code, with the submitted values and the mail provider key left out of the log entirely.

Week one produces the first countable signal because the role drafts under human review from day one. A two-week baseline measured before the role goes live is what makes the week-three number mean anything.

Sync runs, agent jobs, change requests and approval decisions land in the database with timestamps and outcome, and a failed run is recorded as a failed run. Customer-facing audit-log search and export do not exist today — the security page lists that gap among the others.

Hours × share × rate. The calculator takes the weekly hours on a desk, keeps the share you mark as routine, prices those hours at your loaded hourly cost, multiplies by 4.33 weeks a month, and subtracts the published Unistaff price for the same number of employees. The human side is a model; the Unistaff side is the published price.