Agents & collaboration AI coworkers Supported: Specialized coworkers with their own responsibilities and tools.
Supported: Zapier Agents can act independently or respond in chat.
Supported: An AI coworker that works across business tools.
Team collaboration Supported: Shared conversations and Slack threads with people and AI.
Supported: Shared agents, folders, and pods.
Supported: Workspace members can work with Viktor in channels and DMs.
Communication channels Conditional: In-app chat, Slack, and email; other channels require setup.
Conditional: Agents chat on the web and run from app triggers; Slack and Teams touchpoints run through Zap triggers and actions.
Supported: Slack and Microsoft Teams.
Agent handoffs Supported: Delegate work to other AI coworkers.
Limited: Not offered: work runs inside a single agent or AI step; no delegation between specialized agents documented.
Conditional: External agents can delegate work to Viktor through its MCP server and public API; internal multi-agent handoffs not documented.
Persistent memory & skills Supported: Persistent memory, company knowledge, and reusable skills.
Conditional: Connected knowledge sources; persistent learned memory not verified here.
Supported: Workspace-scoped skills and memory.
Automation & tools Schedules & triggers Supported: Schedules, events, and follow-ups with run history.
Supported: Agents run from configured triggers and instructions.
Supported: Recurring tasks and proactive automations.
Browser automation Conditional: Hosted browser with persistent sessions; browser service required.
Limited: Not offered: agents act through app actions and tools; no controlled-browser capability documented.
Supported: Works the web directly: logs in, clicks through pages, fills forms, and pulls data from real sites.
Meeting intelligence Conditional: Supported meeting recording, transcripts, and follow-up; meeting service required.
Limited: Not offered: meeting tools connect through Zaps; no native meeting recording or transcription documented.
Conditional: Meeting follow-through runs through connected meeting tools like Symbl.ai, Fireflies, or Gong; native recording and transcription not documented.
Integrations Supported: Prebuilt connectors and custom integrations.
Supported: Thousands of connected apps and actions.
Supported: 3,200+ business-tool integrations advertised.
Apps & infrastructure Custom app building Supported: Build apps with AI, inspect code, and iterate in a live preview.
Conditional: Forms and Tables alongside workflows; a different app-building approach.
Supported: Build and deploy internal apps connected to business tools.
Internal publishing Supported: Private, individual, and organization-wide app sharing.
Conditional: Forms and Tables sharing varies by product and plan.
Supported: Viktor Pages share finished documents and dashboards at links; Viktor Spaces are internal tools your team signs into.
Row-level permissions Conditional: Role-based access for owners, admins, editors, and members, with apps kept private, shared, or organization-wide.
Limited: Not offered: Tables sharing uses per-table and per-view roles (Owner, Editor, View only), not per-row permissions.
Limited: Not offered: enterprise access is role-based (RBAC); no per-row data permissions documented.
Private resources & SSH Conditional: SSH tunnels and custom connections for private resources.
Limited: Not offered: a cloud platform connecting through prebuilt app integrations and webhooks; no private-network or SSH access documented.
Limited: Not offered: tools connect through cloud integrations and per-user OAuth; no private-network or SSH access documented.
Models & cost control Model choice Supported: 22 models across nine providers.
Conditional: Agents uses a managed model; workflow AI integrations are separate.
Supported: Choice across OpenAI, Anthropic, and Google.
Automatic model routing Supported: Auto routes tasks to Cheap, Balanced, or Smart tiers.
Conditional: Model tiers (Standard, Advanced, Premium) selected per step with an Auto default; automatic task-category routing not documented.
Conditional: Workspace model and task-level cost presets; automatic category routing not verified.
Custom routing rules Supported: Choose tier models, map task categories, or pin a model.
Conditional: Manual tier and model selection per step; task-category routing rules not offered.
Conditional: Workspace defaults and individual scheduled-task settings.
Separate coding policies Supported: Separate conversation and coding routing policies.
Limited: Not offered: one model policy per step; no separate coding policy documented.
Limited: Not offered: model governance is workspace-wide with per-task presets; no separate coding policy documented.
Bring your own keys Conditional: Bring your own provider keys as part of an enterprise setup.
Conditional: Bring Your Own Model connects organization AI provider accounts on Enterprise.
Limited: Not offered: model providers run under Viktor-managed agreements; tool credentials are per-user OAuth handled by the Viktor gateway.
Bring your own gateway Supported: OpenRouter and Vercel AI Gateway.
Limited: Not offered: bring-your-own-key connects provider accounts directly; no custom gateway or proxy endpoint documented.
Limited: Not offered: models run through the Viktor-managed stack; no bring-your-own gateway documented.
Security & governance Single sign-on Conditional: SAML single sign-on for enterprise.
Conditional: SAML SSO on Team and Enterprise plans, with SCIM provisioning on Enterprise.
Supported: SAML SSO via Okta, Entra ID, Google Workspace, OneLogin, or any SAML 2.0 IdP.
Audit & activity visibility Conditional: Access, agent activity, and tool usage for enterprise review.
Conditional: Agent activity can be reviewed; audit coverage depends on product and plan.
Conditional: Enterprise audit logging; confirm required event coverage.
Human approvals Conditional: Action-specific permissions and contact controls on every channel; explicit approval gates not documented.
Supported: Approval steps can be added to agent instructions.
Supported: Sensitive actions can wait for explicit approval in chat.
Usage visibility & budgets Supported: Usage visibility and per-agent credit budgets.
Conditional: In-app plan usage views and Enterprise usage alerts.
Conditional: Auto-topups with monthly spend caps; per-user spend caps on Enterprise.