Work entry points
Start tasks from the desktop client, web console, or WeCom.
- Desktop client
- Web console
- WeCom
Read files, run commands, follow your processes. Tasks are dispatched automatically and results are verified independently. Work runs on your computer by default, sensitive actions need approval, and everything is auditable.
Windows / macOS · About 1–2 minutes to install
From a single goal to a verifiable deliverable. Pick a role scenario and see how a digital worker gets it done.
Upload files, describe the deliverable, and the digital worker organizes the material, writes a draft, and follows your format.
Reconcile bank statements, invoices, and ledgers automatically; list each difference with an explanation.
Organize account lists and conversation notes into a customer profile, follow-up plan, and next actions.
Read logs, code, and environment details, locate the root cause, and propose a fix with verification steps.
Summarize dashboards and competitor pages into a daily report, trend analysis, and anomaly alerts.
Classify tickets against your knowledge base, draft a reply, and suggest when to escalate.
A unified entry point, specialized roles, and an open capability layer — from task creation to delivery.
Start tasks from the desktop client, web console, or WeCom.
Configure roles, skills, and permissions; multiple agents divide the work.
Models, skills, connectors, and file context work together.
Every run submits a result, and an independent verification task reviews it. Only a pass completes the task; a fail sends it back.
Goal, inputs, and acceptance criteria in one place.
The digital worker reads files, runs commands, and follows the process locally.
Result, attachments, and a self-check are submitted together.
Another machine or session reviews it; only a pass counts as done.
Capture skills by role and connect the systems you already use. Capabilities depend on your market and configuration.
Reconciliation, reports, expense and invoice checks
Contract review, clause identification, compliance checks
Resume screening, interview design, onboarding materials
Account follow-up, material organization, opportunity analysis
Troubleshooting, code maintenance, release checks
Daily reports, competitor monitoring, campaign reviews
From permissions and data to deployment, everything needed to roll out digital workers at scale.
Role- and policy-based access with least privilege.
Commands, files, and external writes require approval and are logged.
Tenant isolation; passwords and credentials stay on the machine.
On-premises deployment with your own models.
Turn team know-how into reusable Skills.
Quotas, metering, and billing make cost predictable.
Still have questions? Read the docs or contact us.
By default, on the computer where the client is installed. Files, commands, and session context stay local, and sensitive actions need your approval. You can also run them in a secure cloud sandbox for isolation or centralized management, subject to your configuration.
Platform-hosted models and your own NewAPI or OpenAI-compatible models. The exact list depends on your configuration.
No. Data is isolated per tenant and your files are not used for model training.
Yes. Private deployment and offline packages are available, and models can point to internal services.
We offer trial, team, enterprise, and private deployment plans. Contact sales for pricing and quotas.
Download, contact us to start a trial, or book a demo and run through your scenario with us.