Ask AI
Answers from your company's knowledge and each app's live data.
Overview
Ask AI routes each question to whichever specialist agent owns the answer — scheduling for shift questions, leave management for PTO balances, service desk for ticket status, and more, as most OneMango apps bring their own assistant — instead of a single model guessing from a document index. Because each agent is wired into that app's own live data, answers reflect what's actually in your schedule or ticket queue, not just what a policy document says.
When a request spans two areas, one agent hands the rest to another app's assistant mid-conversation, so a single question can cover both without being asked twice. Most actions that change data pause for your explicit confirmation. A few run straight away: small changes to your own items, such as a bookmark, a page watch or a notification's read state, and saving the result of an analysis you asked for, such as a candidate's screening scores; automations an admin sets up can also run chosen actions on their own.
Available from a web sidebar, the mobile app, and a browser extension, with one conversation carrying across all three.
Music and on-screen words follow one overnight shift: Ask AI answers from your company's own content and shows its source, asks before it posts anything, and when it can't answer, one press sends the question to a person; once an admin approves an answer for everyone, it's there, marked Verified, the next time anyone asks.
Highlights
Capabilities
AI Chat & conversation
-
Chat from a web sidebar, the mobile app, and a browser extension — one conversation synced across all three
-
Multi-turn follow-ups that keep context, including short/ambiguous ones ("two weeks ago", "no", "those")
-
Streaming, token-by-token responses — the answer appears as it's written
-
Rich, interactive answers — inline tables, charts, timelines, report cards, and clickable action buttons
-
Start a question with an agent's @name to send it to that agent (e.g. @scheduling)
-
Answers in the language you ask in
-
In-app Prompt Library of reusable starter prompts (central + tenant-authored)
-
Searchable history of your past conversations — kept 24 months by default; an admin can set 1 to 36
-
Share a conversation with named colleagues — as readers, or as contributors who can ask follow-ups
Proactivity, memory & journeys
-
The assistant prompts you — playbook results and approvals arrive in Notifications instead of waiting to be asked
-
Reply to a proactive item in Notifications and the assistant answers in-thread, grounded in the item
-
Cross-session personal memory of durable per-user facts, with a private review/erase page — provided by Muscle Memory, which comes in the same editions as Ask AI, once an admin turns it on
-
Journeys — tracks a multi-step goal (onboarding, a migration) across sessions and guides you step by step, on a private My Journeys page
-
Auto-detect goals — starts tracking a multi-step goal it notices and tells you; you can stop tracking any goal from its notice or from My Journeys (on by default; an admin can turn it off)
-
Weekly self-improvement — analyzes failed / misrouted / low-rated turns and sends admins concrete fixes (off by default; an admin turns it on)
Agent routing
-
Automatic routing of each question to the best-fit specialist agent
-
Sticky routing keeps a multi-turn session with one agent ("Continuing with: <Agent>")
-
Cross-app handoff — one agent hands the goal to another app's assistant
-
Plugin agent proxies for third-party marketplace extensions
-
Number of built-in domain agents: 100+ — an app's agent answers when that app is on and you have access to it
Knowledge & grounding (RAG)
-
Grounds answers across your knowledge base, HR policies, SOPs, wikis, Sites pages, and shared Drive files
-
Admins choose which knowledge sources the AI is allowed to draw on
-
Optional platform help articles included in answers (admin toggle)
-
Semantic, meaning-based retrieval finds the right passage even when the wording differs
-
Answers built from your data or content say where they came from — Computed, Live data, Verified by your organization or Retrieved knowledge, with the sources listed
-
Company Brain — a user's correction becomes admin-approved verified knowledge; News Feed "verified answers" flow in too
-
Live data pulled from connected apps via agent tools (schedules, leave, tickets)
-
Browser extension can use the LinkedIn profile, Gmail message or Google Calendar event you have open
Tool calling & actions
-
Agents call live, read-only tools for real-time data across apps
-
Changes wait for your confirmation, except small changes to your own things and saving the result of an analysis you asked for; automations your admin sets up can run chosen actions on their own
-
When a change asks first, many show a before/after preview
-
Human handoff — "Get human help" files a service desk ticket, or tells the app's admins when there is no Service Desk
-
Attach files to a question — image (PNG/JPG/WebP/GIF) vision + PDF text extraction (Word, Excel, and CSV files can also be attached), on a computer and in the Mango Ops app; a phone's browser opens the full page to attach
Voice & multimodal
-
Voice mode — speak a question, hear a spoken answer, on a computer and in the Mango Ops app (not in a phone's browser)
-
Live, hands-free voice conversation you can speak into and interrupt naturally
-
Admin-configurable AI voice, response style (concise/balanced/detailed), and speech pace — one tenant-wide default, set with an in-settings preview
-
Short video clips in chat (up to two minutes, 100 MB) — read from sampled frames and the soundtrack
Safety, audit & admin control
-
Content moderation with prompt-injection / system-prompt-security checks
-
Business-scoped tenant isolation — one organization's data and conversations are never shown to another
-
Admin Agent Guidelines + per-agent instruction overrides
-
Admin toggles to disable action execution, voice, or help-article grounding
-
Admin review queue to approve, edit, or retire verified-knowledge (Company Brain) entries
Limits & specs
-
Voice daily limit (admin-configurable): 30 minutes per user (0 = unlimited)
-
Voice session limit: 15 minutes per session
-
Attachments per message: Up to 3 files, 8 MB each (a video clip up to 100 MB); PDFs up to 100 pages
-
Pricing: Included in Platform Standard, which comes with any purchase, and in Platform Enterprise (not in Platform Free); AI use draws on your organization's AI credits
Screenshots
Use cases
FAQ
Responses are grounded in your organization's knowledge base, admin-verified corrections ("Company Brain"), any files you attach to a message, and live data pulled from connected apps through agent tools. Platform help articles can optionally be included by an admin.
From a chat sidebar in the web app, the mobile app, and a Chrome browser extension. All three route through the same agentic pipeline and share one conversation, so you can start a question on the web and continue it on mobile. In the browser extension, answers can also use the LinkedIn profile, Gmail message or Google Calendar event you have open.
Each question is automatically routed to the best-fit specialist agent — each app your organization turns on brings its own (scheduling, HR, leave, service desk, reporting, safety, and more). Multi-turn sessions stick with the same agent ("Continuing with: "), one agent can hand a goal off to another app's assistant, and you can send a question to one agent by starting it with that agent's @name (e.g. @scheduling).
Specialized agents can read live data (schedules, leave balances, tickets, reports) and take actions. Most actions that change data stop and ask you to confirm first, and many show a preview of the change. Some changes that affect only your own things — saving or removing a bookmark, watching a page, marking notifications read, tracking a Journey — run as soon as you ask, without a confirm card (a few only where your admin has turned them on), and so does saving the result of an analysis you asked for, such as a candidate's screening scores. Admins can also turn on automations that act on a schedule without asking each time.
Yes — on a computer and in the Mango Ops app (in a phone's browser, Attach files opens the full page), up to 3 files per message, 8 MB each. Images (PNG, JPG, WebP, GIF) are analyzed with vision, and PDFs are read via text extraction (up to 100 pages; scanned image-only PDFs may have no extractable text). Word, Excel, CSV and plain-text files are read as text too.
Yes, on a computer and in the Mango Ops app — a phone's browser has no voice mode. Voice mode lets you speak a question and hear a spoken answer, including a live, hands-free OpenAI Realtime conversation you can interrupt naturally. Your admin sets one AI voice, response style, and speech pace for the whole organization, chosen with an in-settings preview. Voice is metered: sessions are capped at 15 minutes, plus an admin-configurable daily limit (30 minutes per user by default, or unlimited).
Ask AI is the unified conversational assistant that routes each question across every specialist agent and grounds answers in org-wide knowledge. Personal Agent is a separate app; where it is on, it adds a specialist hard-scoped to your own bookmarks, notes, drafts, tasks, and notifications, plus your shifts, leave, pay, and certifications. Workforce Bots are standalone document-Q&A bots (HR Policy, SOP, Compliance, etc.) that admins install against specific knowledge bases. You reach the same intelligence through Ask AI's single chat surface.
Conversations are scoped to your business tenant and never shown to another organization. Every question you type is checked by content moderation, and page or file content an answer reads is marked as untrusted, so the assistant is told not to follow instructions inside it. Your history page is yours: colleagues see a conversation only when you share it with them by name. Your organization's admins can review AI requests, including the questions people typed, for the last 30 days in AI Analytics.
Journeys — the multi-step goals Ask AI tracks with you, like onboarding a hire or migrating a policy — are on by default, private to you, and managed on your My Journeys page; admins can turn Journeys or auto-detect off under Agent Guidelines → AI Features. Durable cross-session memory of personal facts (your preferences, what you're working on) is a separate capability provided by the Muscle Memory app: once an admin enables it and its "Remember durable facts for each user" setting, those facts are strictly per-user — managers and admins never see them — and you can review or erase them on your private Personal Memory page.
When it can't find an answer, it says so and offers Get human help: with Service Desk that files a ticket you can follow; without it, the admins of the app the question was about are told.
