Bot Connect

Bring your own chatbot. You keep the backend; MangoApps is the front end — in Ask AI, a pop-up, a full-page tab, or a Home widget.

MangoApps

Book a walkthrough Ask AI Download datasheet

Overview

Register a customer-controlled chatbot and surface it inside MangoApps without rebuilding it. Embed it by URL (iframe) or connect it by authenticated API and let MangoApps proxy questions and stream answers back. Choose where it appears — routed inside the unified Ask AI box, as a site-wide pop-up bubble, a full-page tab, or a Home dashboard widget — as a setting, not a separate build. Ask AI routing sends the right questions to the right assistant (yours for its domain, native agents for everything else), disambiguating across multiple registered bots. API endpoint and keys live encrypted in Integrations, never exposed to app code, with optional HMAC request signing.

Platform

Highlights

Bring your own chatbot — you keep the backend, connectors, and source systems; MangoApps is the front end.

Surface it inside the unified Ask AI box, as a pop-up bubble, a full-page tab, or a Home widget — a setting, not a rebuild.

Route questions by topic so the right brain answers — your bot for its domain, native agents for everything else.

Keep it secure: endpoint and keys live encrypted in Integrations, never exposed to app code, with optional HMAC signing.

See how it's used — success rate, latency, per-surface volume — and get alerted the moment a bot starts failing.

Answer follow-ups with multi-turn context and clean markdown formatting in the in-app chat panel.

Capabilities

Integration Modes

Embed by URL (iframe) — you provide a chat URL
Connect by API — we proxy questions to your endpoint
Bearer-token authenticated API calls
HMAC-SHA256 request signing (verify the call is ours)
Multiple external assistants per business

Where It Appears (Placements)

Inside the unified Ask AI box (routed by topic)
Floating pop-up chat bubble, site-wide
Full-page tab in the app rail
Home dashboard widget
Shareable deep link to the full-page assistant

Conversation Experience

In-app chat panel for API-backed bots
Multi-turn follow-up context (prior turns sent)
Markdown-formatted answers (lists, links, code)
Streaming answers via Server-Sent Events
Animated typing indicator while the bot thinks

Ask AI Routing

Keyword + topic routing rules per assistant
Disambiguation across multiple registered assistants
Fall-through to native MangoApps agents when off-topic
Admin toggle to turn routing on or off

Reliability & Analytics

One-click connection test from the admin console
Automatic health monitoring of API-backed bots
Admin alert when an assistant starts failing
Usage analytics — questions, success rate, latency
Per-assistant and per-surface breakdowns
Daily volume chart and recent-activity log
CSV export of usage data

Security & Governance

Endpoint and keys stored encrypted in Integrations
Credentials never exposed to app code
SSRF protection (private-network endpoints blocked)
Per-assistant framed-origin allow-list (CSP)
Group / audience visibility scoping
Admin-only assistant management

Limits & Specs

Integration modes: iframe or authenticated API
Max question length: 4,000 characters
Follow-up context sent: Up to 10 prior turns
Request timeout: 25s (60s max)
Request signing: HMAC-SHA256
Health check cadence: Every 15 minutes
Analytics windows: 7 / 30 / 90 days, all time
Assistants per business: Unlimited

Use cases

In-house job-aid bot

Embed your internally-built parts/procedure assistant so frontline employees ask it from the same box they use for HR and scheduling.

Proprietary domain assistant

Connect a bot trained on systems we don't integrate with, and let Ask AI route the relevant questions to it.

Site-wide help bubble

Turn on the floating pop-up so a support or IT bot is one click away on every page, without a separate portal.

Monitored production bot

Register a business-critical assistant and rely on health monitoring to alert admins the moment its API key expires or its endpoint breaks.

Resources

Bot Connect Datasheet (PDF)

Datasheet

Features, capabilities, pricing model, and FAQ on one downloadable sheet — share it with your team.

Bot Connect — setup guide

guide

Register an external assistant, choose where it appears, and route it inside Ask AI.

iframe vs API mode — which to use

guide

When to embed by URL and when to connect by authenticated API (and why API avoids domain allow-listing).

Ask AI routing for external bots

guide

How keywords and topics decide which assistant answers a question — and how multiple bots are disambiguated.

FAQ

No. In iframe mode we render your URL; in API mode we proxy the question and stream back the answer. Your backend owns the logic and data.

An authenticated HTTPS endpoint that accepts a JSON question and returns a JSON answer (streamed via Server-Sent Events if you want incremental delivery). Endpoint and keys are stored encrypted in Integrations, and private-network addresses are blocked.

Yes. Register as many as you like; Ask AI routing disambiguates between them by the keywords and topics you assign.

Yes. Run the one-click connection test from the admin console when you register the bot to confirm the endpoint responds, then rely on usage analytics (success rate, latency) and automatic health monitoring — admins are alerted the moment an assistant's requests start failing.

Anywhere you choose — inside the unified Ask AI box (routed by topic), as a floating pop-up bubble site-wide, as a full-page tab in the app rail, as a Home dashboard widget, or via a shareable deep link. Each placement is a setting, not a rebuild.

Assistant management is admin-only, and you can scope each assistant's visibility to specific groups or audiences. Endpoints and keys are stored encrypted in Integrations, never exposed to app code, and private-network addresses are blocked.

Yes. The in-app chat panel sends the recent conversation turns with each question so an API-backed bot can answer follow-ups in context, and it renders markdown answers cleanly.