Open the workspace
Launch AgenTorQ Cloud in any modern browser. No download, no install, no infrastructure to stand up — you are in seconds.
A standalone AI platform — no Salesforce required — connecting Salesforce, Microsoft 365, Google Workspace, Slack, GitHub, databases, APIs and 14+ AI models. Governed AI Workmates ground on your data, cite their sources, and take approved actions — right in the browser.
One platform, two editions — the standalone Cloud workspace and the Salesforce-native package share the same engine.
Nothing to deploy, no package to install, no admin project. Sign in, bring your own model keys, connect the apps you already use, and start working — the full enterprise AI platform, standalone on the web.
Launch AgenTorQ Cloud in any modern browser. No download, no install, no infrastructure to stand up — you are in seconds.
Sign in with Google, Microsoft or email. Your workspace, chats and connected accounts are isolated and private to you by default.
Add your own AI provider keys and connect Salesforce, Microsoft 365, Google Workspace, Slack, GitHub and more — each with per-user OAuth.
Same engine, Workmates, governance and connectors as the Salesforce-native edition. The only difference is where it runs.
Salesforce is one supported system among many. From the standalone workspace, connect the tools your teams already run on — then reach the long tail through REST, GraphQL, databases and MCP.
Read records and take governed actions — alongside your other systems, never required.
Outlook, Teams, SharePoint and OneDrive with per-user OAuth.
Gmail, Calendar and Google Drive for grounding and actions.
Read channels and post updates where your teams already work.
Repos, issues and branches — plus real git ops in DevSpace.
SharePoint, OneDrive, Google Drive and Box for documents.
Postgres, MySQL, Snowflake and BigQuery via the connector layer.
REST, GraphQL, webhooks, custom MCP servers and 600+ apps.
600+ apps via the connector layer, plus REST, GraphQL, databases and MCP — each with per-user OAuth and full call logging. Long-tail and enterprise systems are reachable through the connector layer, REST or MCP, not bespoke certified integrations.
Add your own provider keys and pay for AI directly — no per-message metering, no per-seat AI tax. Route every task by cost, latency, reasoning quality or policy across 14+ providers, plus self-hosted and any OpenAI-compatible endpoint.
A Workmate is a role-aware AI agent that reads your data, reasons over your knowledge, and takes approved actions across your connected systems — each one configurable, and running on the model you choose.
Grounds on your live pipeline to brief reps, surface risk, and log the next step.
Answers case questions from records and knowledge, then acts on the resolution.
Connects systems and runs the busywork across your apps and workflows.
A configuration copilot grounded in your org metadata and access model.
A developer-grade copilot for Apex, LWC, Flows and GitHub inside DevSpace Studio.
The Intent Router grades every request and routes it to data lookup, knowledge, reasoning, or a real action — nothing hardcoded.
Grounds on connected apps, uploaded files and your knowledge base across 600+ connectors — cited every time.
Routes by task across OpenAI, Claude, Gemini, Grok, DeepSeek, Mistral, Groq, Ollama and more — with fallback and cost control.
Creates and updates records, runs Flows, and sends email behind approval cards — every action logged to an immutable audit trail.
DevSpace Studio is a developer-grade copilot inside AgenTorQ Cloud — a VS Code-style, three-pane workspace that browses, edits and ships Apex, LWC and Flows, and drives real git on GitHub. Ask, plan, edit, diff, approve, deploy, test, fix — nothing deploys until you approve.
Full developer walkthrough on the Developers page.
Explore PlatformBuild a RAG knowledge base from your files and connected systems, then search across everything from one place. Every answer is grounded and cited, so people can trust it and trace it.
Organize content into folders, files and chunks with embeddings, so answers stay grounded in your own material.
Every grounded answer links back to the records, files and passages it used — verifiable, not invented.
Search across connected apps, documents and knowledge in one query — results respect each source's access rules.
Include or exclude specific objects and fields, and mask personal data before it is ever embedded or sent.
Blend uploaded documents with live records from connectors so answers reflect the current state of your business.
See which sources shaped each answer, and review or refine the knowledge base as your content changes.
AgenTorQ Cloud does not just chat. Workmates create and update records, run Flows, send email and render edit forms across your connected systems — each gated behind an explicit approval, with destructive steps always requiring confirmation.
Create a task for Jordan Lee due Friday, draft a re-engagement email citing the Q3 usage lift, and log the touch to the opportunity. Runs across Salesforce and Microsoft 365 once approved — then writes to the audit trail.
Drop in the documents you already work with, and pull in fresh, dated facts from the web — both grounded and cited alongside your connected data.
Upload PDF, Word, Excel, CSV and images. AgenTorQ reads spreadsheets and documents natively and runs OCR on scans and screenshots, then summarizes and reasons over them with any model — even ones without native vision.
Model-agnostic web search brings back current, sourced results with dates — so time-sensitive answers cite where and when the facts came from, next to your internal data.
Each Workmate keeps its own memory of Concepts, Entities, Workstreams and Notes, and applies it on future turns — on top of cross-session semantic recall. Memory is isolated per user and private by default, and you can view and manage it in a dedicated Memory tab.
Zero-trust controls wrap every request in the standalone workspace — so security teams can say yes to AI, and you keep a complete record of every action. This is a compliance-ready architecture.
Named personal data is masked before any prompt leaves — only the masked prompt reaches the model you chose.
When connected to Salesforce, every read passes a SOQL guard and every write a DML guard before it touches your data.
Connection credentials live in an external vault with per-user OAuth and automatic token refresh — never shared.
Every prompt, action and model call is recorded to an immutable audit trail for review and compliance.
Allow or restrict specific providers and models per role, team or workflow — and enforce operating modes.
Personal chats and OAuth tokens stay private; each user, team and tenant sees only its own data.
Compliance-ready architecture — your data stays in your systems, and only the masked prompt reaches the model you chose. Read our Privacy Policy.
Start solo in minutes. When you are ready, turn your workspace into a team WorkSpace: invite users, build Salesforce-style Profiles from a feature-toggle grid, and assign them with per-user overrides and deny-by-default access — all server-enforced.
Shared: Workmates, knowledge, engine keys, app catalog. Private: personal chats and OAuth tokens.
AgenTorQ Cloud is the standalone web workspace on this page. The same engine also ships as a native AppExchange managed package that runs inside Salesforce — same Workmates, governance, connectors and model routing.
The standalone web workspace — no install, no Salesforce required. Connect Salesforce alongside Microsoft 365, Google Workspace, Slack, GitHub, databases, APIs and more, and start in the browser.
A real AppExchange managed package installed in your org. Record-aware AI on every page and utility bar, enforced in USER_MODE — admin-managed, and your data stays in Salesforce.
Same AI engine · Same Workmates · Same governance · Same connectors · Same model routing. Different deployment.
The standalone enterprise AI workspace — what it is, what it connects to, and how it stays governed.
No. AgenTorQ Cloud is a standalone enterprise AI workspace that runs in the browser with nothing to install. Salesforce is one supported connector among many — connect it alongside Microsoft 365, Google Workspace, Slack, Teams, GitHub, Jira, SharePoint, Drive, OneDrive, databases, REST APIs and MCP servers, or use none of them.
No. Open the workspace in your browser, sign in, bring your own model keys and connect the apps you use. There is no package to deploy and no admin setup required to start.
You add your own API keys for the AI providers you want, so you pay them directly at cost — no per-message metering and no per-seat AI tax on top. AgenTorQ routes each task to the right model across 14+ providers with cost control and fallback.
OpenAI, Anthropic Claude, Google Gemini, xAI Grok, DeepSeek, Mistral, Groq, SambaNova, Cerebras, Perplexity, MiniMax, AI21 and Hugging Face, plus self-hosted Ollama and any OpenAI-compatible endpoint. Hundreds of models are available via live fetch, switchable per Workmate and task.
Salesforce, Microsoft 365, Google Workspace, Slack, Teams, GitHub, Jira, SharePoint, Drive and OneDrive, plus 600+ apps through the connector layer and REST, GraphQL, database and custom MCP connectors — each with per-user OAuth and full call logging. Long-tail and enterprise systems are reachable through the connector layer, REST or MCP rather than bespoke certified integrations.
Yes. AgenTorQ Cloud is governed by default: named PII is masked before any prompt leaves, credentials live in an external vault with per-user OAuth and token refresh, write actions are gated behind approval cards, and every prompt, action and model call is recorded to an immutable audit trail. Only the masked prompt reaches the model you chose, and personal chats and tokens stay private per user — a compliance-ready architecture.
Yes. AI Workmates can create and update records, run Flows, send email and render edit forms across connected systems — each gated behind an explicit approval card, with destructive steps always requiring confirmation and everything logged for audit.
They are two deployment editions of one platform. AgenTorQ Cloud is the standalone web workspace; AgenTorQ for Salesforce is a native AppExchange managed package that runs inside Salesforce in USER_MODE. Both share the same AI engine, AI Workmates, governance, connectors and model routing — only where it runs differs.
No install, no Salesforce required. Bring your keys, connect your apps, and put governed AI Workmates over your whole enterprise — or book a guided walkthrough with our team.
reachout@agentorq.com