Internal sites, generated and audited. Drafts until published.
Spin up a department page, or a whole batch, with real employees, policies, forms and training pulled live. Risky writes wait for your confirmation, and publishing can require approval.
Spin up a department page, or a whole batch, with real employees, policies, forms and training pulled live. Risky writes wait for your confirmation, and publishing can require approval.
Trusted by frontline employers everywhere
Pages built from your real org data
Page starters pre-wire the right sections, and live lookups pull in real employees, policies, forms and training.
-
A starter for each kind of page
Operational hubs, onboarding journeys, department showcases and more, pre-wired with the right sections.
-
The live team, not a list
Team sections render real reporting lines and titles from the org chart.
-
Over 50 section types
The agent picks the right section for the data, not free-text blocks.
A batch of drafts, approved if you require it
Department, team or initiative pages in one call, every one a draft, and a named approver signs off when required.
-
Batch create, confirmed first
Multiple pages in one call from page starters, all saved as drafts.
-
A named approver decides
The approver it was sent to, or an admin, approves it, asks for changes or rejects it.
-
Versions you can restore
Compare page versions, and restore one only after a warning that current content will be overwritten.
Pages that keep themselves current
The audit finds stale and empty pages, and linked sections flag their owner when a policy, form or person changes.
-
A full content audit
Stale pages, empty sections, missing heroes and governance findings across the site.
-
Self-maintaining sections
A daily scan flags pages whose linked policy, form, person or event changed or was removed.
-
Suggestions for each page
Per-page recommendations, and a stale or expiring list for governance.
Every risky write waits for you
Publishing, deleting, batch creates, sweeps and restores each need explicit confirmation.
-
Sweeps preview first
Find and replace and bulk section edits are a dry run until you apply and confirm.
-
Deletes go to Trash
A deleted page comes back as a draft for 90 days, and the prompt says what each delete takes away.
-
Three publish paths, all gated
Publish a page, publish a site or schedule a publish, each after you confirm.
Sites Agent at a glance
Sites AI
AI page generation · org-grounded lookups · approval workflow · governance audit.
Healthcare
“We wanted to drive people into MangoApps, and we wanted to make our Assistants useful immediately. Petauri Ask was trained on resource guides we’d already uploaded, so employees could ask things like ‘How do I submit an expense report?’ or ‘Where do I find the holiday calendar?’”
Retail
“At our head office within HR, marketing, and finance, we use ChatGPT quite a bit, and MangoApps AI Helper is a useful tool for us. As I go around to the stores, I’ve been showing them how the AI Intranet Helper can find things and answer plain language questions about our resources, and they’re quite excited about that.”
“MangoApps’ search capability has been critical. It brings back so much information that would have been lost on our old intranet. The content is fresh and current. It’s been really, really nice to have.”
Results from teams like yours
Part of one app your people already use
Sections embed live policies, forms, people and training by reference, so a page always shows the current record.
Questions intranet owners ask
50+ tools spanning site CRUD, page CRUD, section CRUD (over 50 section types), asset library (browse + semantic search + upload), org lookups (employees, policies, forms, training), navigation, approval workflow, versioning + restore, translation, content audit, suggestions, and sweep-style writes (find/replace, bulk_update_sections, batch_create_pages). The risky ones — publish, delete, batch, sweep, restore — all require explicit confirmation.
No. publish_page, publish_site, and schedule_page_publish are all flagged risky and require explicit user confirmation. Generated pages default to DRAFT status, and with approval required the approval workflow (request_page_review → approve_page_review) routes through a named human approver before publish.
lookup_employees pulls from the org chart, lookup_policies from Policy Hub, lookup_forms from Forms, lookup_training from Training. Sections render against the live records, so an employee joining or leaving a department shows up in the team_members section without anyone editing the page.
Yes — self-maintaining content. Each page tracks the live records it references (policies, forms, people, events), and a linked section always shows the current record. A daily scan detects when one of those sources changes or is removed and flags the page for its owner, who checks the words around it and marks it still accurate, or clears links to removed records out of the draft in one click.
Yes. Separate from the authoring agent, an "Ask AI about this page" reader assistant lets an employee ask a question and get an answer grounded only in the content they're permitted to see, with the source page cited. Admins can also see how often Ask AI draws on each page in the AI reach card of Sites analytics.
find_and_replace defaults to dry-run (preview only) — the agent returns the matches it would change without changing them. To commit, the admin passes apply: true, which triggers the RISKY confirmation prompt before any text is modified. It only changes the text readers see — never links, web addresses or page titles — and on a published page the change is saved as a draft, so nothing goes live until the page is published; every changed page also gets a restore point in its history. The same find & replace is in each site's Manage › Pages for editors who don't use the assistant. bulk_update_sections follows the same dry-run-by-default pattern.
Page-creation cycle time (hours from request to published, vs manual), org-data freshness (share of sections sourced from live lookups), stale-page burndown per month via audit_site, approval override rate on AI-generated pages, and find/replace adoption for sweep-style edits. Compare against your pre-agent baseline.
See what MangoApps can do for your frontline
Every team. Every employee. Every workflow. One AI platform — built for the frontline. Since 2008, trusted by 2 million+ users with an NPS of 78.
Rolled out to every employee at AutoZone (125,000), PetSmart (50,000+), A.S. Watson and Raley's (20,000) — and at larger retailers we are not permitted to name.
Prefer to explore first? Ask AI about Sites AI Agent →
- Within one business day: a solutions consultant asks about your workforce and what you run today.
- The demo shows your use case: your sites, your frontline roles, your systems.
- It ends with your price: the package and the price for your employee count, not a generic quote.
