nexos.ai

Workspace Integrations reach Google Drive, Mail and Calendar and Microsoft Outlook, OneDrive, SharePoint, Teams and Calendar on the productivity side, Atlassian, GitHub and GitLab through their MCP servers, and Slack, HiBob, Looker, Google Ads and BigQuery. Organization admins activate them and each user connects through the provider's own sign in. The approvals page documents agents taking write actions through these integrations (sending a message, creating a ticket, updating a record), so agents take authenticated action in outside systems.

Sourcedocs.nexos.ai/workspace/integrationsread 2026-09-22

A visual Flow in Agent Builder shows the steps an agent will take to complete its task, with optional human in the loop review steps, and agents run multi step work across connected tools on demand or on a schedule. No deterministic nodes, branching or multi agent handoff are documented.

Sourcedocs.nexos.ai/workspace/agents/agent-builderread 2026-09-22

Files added to a Project are chunked, embedded and stored in the Project's context index, and nexos.ai uses Retrieval-Augmented Generation to pull relevant context from them when answering; Projects can be shared with view or edit access. Agents take files from a Project as their knowledge base to give sourced answers, and that knowledge can be updated or removed at any time. New customer knowledge enters a persistent index without retraining, so the retrieval structure scales past the context window and stays queryable.

Sourcedocs.nexos.ai/workspace/projectsread 2026-09-22

Before any action that changes something in another tool, such as sending a message, creating a ticket or updating a record, Human-in-the-Loop Approvals pause the agent and show an approval card naming the action, the integration and its key details. The person approves (the agent acts and continues) or declines (the action is not taken and the run stops). Approvals appear in the conversation for chat agents and in Activity history for scheduled agents, and are switched on per integration inside each agent's settings.

Sourcedocs.nexos.ai/workspace/agents/human-in-the-loop-hitl-approvalsread 2026-09-22

Access is managed per user: organization admins invite, update and remove users and assign each a role and team (Users page), accounts can be managed through the customer's identity provider with linked SSO sign in (Account page), and company wide guardrails with per model overrides and exclusions apply across the workspace (changelog). nexos.ai's integrations and EU gateway pages state SOC 2 Type II and ISO 27001 certification, with reports in its Trust Center.

Sourcedocs.nexos.ai/workspace/settings/organization/usersread 2026-09-22

Every API request is recorded in Observability: which model was used, latency, cost, token usage and errors, with full request details, and admins can drill into a call to see the exact messages and responses, filtering by time, model, user or team. A Metrics dashboard shows usage, cost and health, and the changelog adds log spans. Scheduled agents keep an Activity history of their runs and approvals, and retention is stated.

Sourcedocs.nexos.ai/workspace/settings/observabilityread 2026-09-22

User Memory keeps context about each user across chats and agents: the app adds context as the user works, and the user can view saved memories, edit them, delete one or all, or turn Memory off, alongside personalization details and custom instructions the user writes. The scope is stated (per user, in Chat and Agents) and the user can delete their own entries, but no lifetime is stated.

Sourcedocs.nexos.ai/workspace/chat/memory-and-personalizationread 2026-09-22

Europe hosts the platform and most available models, according to nexos.ai's own pages, and its EU gateway runs Claude, GPT, Gemini and Mistral EU hosted with zero data retention. That is a stated residency commitment, but no named region list, named customer environment option or selection surface is documented.

Sourcenexos.ai/eu-gatewayread 2026-09-22

Ready made assets are there to adopt: the changelog's AI Agents entry lets users start from premade templates, the pricing FAQ lists an extensive template library in every plan, and the docs publish a prompt library of assistant instructions organized by department, such as a product strategy evaluator.

Sourcedocs.nexos.ai/workspace/agents/prompt-libraryread 2026-09-22

A schedule can be set on an agent (hourly, daily, monthly or yearly), per the changelog entry Agent Builder and Scheduling, so it runs automatically in the background with no person initiating it. The Agent Builder page describes agents set to run periodically, such as a morning summary of Slack updates, and scheduled runs appear in the agent's Activity history. Agents are also reachable from Slack, Microsoft Teams, Telegram and WhatsApp.

Sourcedocs.nexos.ai/changelog/changelog/latest-updatesread 2026-09-22

Users pick any of 200+ models per chat, Project or agent, or let Smart Routing choose, and organization admins add models with their own guardrails, timeouts, ordered fallback models and a trusted-model badge. The Gateway API exposes the same catalog to the customer's code, so model choice sits with the customer.

Sourcedocs.nexos.ai/workspace/settings/organization/modelsread 2026-09-22

A Gateway API at api.nexos.ai is documented with a published OpenAPI reference: Chat, Anthropic native Messages, Responses, audio, images, embeddings and storage endpoints, plus management endpoints for teams, users, agents, assistants, company API keys, budget limits and usage, with Python, Go and .NET code examples. Agents can be managed from outside through it.

Sourcedocs.nexos.ai/gateway-apiread 2026-09-22

Models can be compared side by side on the same prompt in nexos.ai Chat, and the changelog adds the customer's own assistants to Compare Models to test them against other models on performance and output differences; Agent Builder has a Try Agent window for testing on real scenarios before launch. These let a person inspect and compare an agent's outputs by eye. No scored test cases, pass rate, judge verdict, quality gate or optimization loop is documented.

Sourcedocs.nexos.ai/workspace/chatread 2026-09-22

Web pages are fetched and analyzed by the Web Scraper, which per the changelog processes URLs found in web search results, uploaded files and agent instructions, so agents continue tasks without a person supplying the link. That is a headless fetch; no hosted browser, desktop session or remote computer control that an agent drives is documented.

Sourcedocs.nexos.ai/changelog/changelog/latest-updatesread 2026-09-22