AI Features

A grounded AI workspace
for MSP operations.

Ask about any client, dashboard, or integration in your tenant. ScopeGrid’s AI reads your live data, knows the page you’re on, renders answers as inline widgets you can pin to dashboards, and keeps every prompt under your provider, your redaction policy, your audit log.

Try it in the demo
01 · The Workspace

Chatthatdoesthework,wheretheworkhappens.

A side panel that opens beside the page you're already on. Multi-turn, persistent threads, AI-titled, with click-to-pick choice cards.

02 · Page-aware

Italreadyknowswhereyouare.

The workspace knows which dashboard, widget, client, integration, or settings page you're on — and remembers where each thread started.

03 · Reads your live data

Groundedinyourtenant.

Tools fetch your real dashboards, widget config, alert history, backup health, security posture. Answers cite which integration the data came from.

04 · Builds the things

Alerts.Reports.Dashboards.

Ask the workspace to set up an alert, a weekly client report, or a brand-new dashboard. Each request returns a previewable, savable spec inline.

05 · Stats as widgets

Numberscomebackascharts,notparagraphs.

KPI cards, gauges, mini bar / donut charts, ranked lists — inline in the chat bubble. Same widget vocabulary as your dashboards.

06 · Pin to dashboard

Savethemoment.

One click pins the rendered widget onto any of your custom dashboards as a moment-in-time snapshot — perfect for QBR-style tiles.

07 · Drives the UI

Tellstheappwheretogo.

"Show me Acme's action items" routes you straight to that client, that tab, with the workspace still open alongside.

08 · Curated templates

Astarterlibrary,filteredtoyou.

New orgs get starter alerts and reports narrowed to integrations they've connected — Veeam failures, secure score drops, weekly recap, QBR.

09 · Threads survive reload

Pickituptomorrow.

Inline widgets, dashboard previews, and savable spec cards persist alongside the message text. The visuals re-render exactly as before.

AI Workspace
Acme · Profitability
How is the estate doing on backups and security right now?
Two clients to watch — Acme's backup chain failed twice overnight, and InsureCo's secure score dropped 4 points after the new tenant was onboarded.
Show me Acme specifically.
Acme · ProfitabilityAcme's blended margin is 28% with three agreements in at-risk territory. Backup chain healthy after this morning's retry.
What's behind the secure-score drop?
✓ getSecurityPosture✓ getM365PostureConditional-access policies dropped from 4 to 2 last week. SentinelOne flagged 3 risky sign-ins in the same window.
Set up an alert when Acme's score drops 5 points or more.
New alert rule · ready to save
Secure score delta < -5 · 60 min cooldown · Acme only
Save rule →
What's CSAT looking like this month?
CSAT this month
92%
+3
Secure score
78%
Pin that CSAT card to Acme's dashboard.
Pinned to Acme · Operations
Take me to Acme's open actions.
Routing to Acme · Actions tab
What other starter alerts should I set up?
Reload · 9am next morning
Welcome back. Your thread + every widget you pinned are restored, exactly as they appeared yesterday.
Operational AI

Six focused uses of AI you turn on individually.

Each of these is its own feature with its own settings page — enable what's useful, leave the rest off.

01 · Anomaly callouts

The1–3thingsonthisdashboardworthasecondlooktoday.

A dismissible top-of-dashboard banner that highlights anomalies the AI noticed. Threshold-tunable, per-tenant, and never repeats the same callout twice in a row.

Acme · Operations dashboard
1 anomaly detected
Acme's backup chain ran 40% slower overnight than its 30-day average. Worth checking before client open of business.
Backup health
92%
Threats active
3
CSAT
91%
Top 5 clients by alert volume · 7d
Acme12
InsureCo10
GreenfieldCo8
RiverbankIT6
NorthstarCo4
02 · Widget explainers

PlainEnglishforanywidget,ondemand.

Click the sparkle on any widget and the AI writes a one-paragraph explanation of what it shows and what's standing out — fetched from the actual rendered values, not a generic template.

Acme · CSAT trend widget
CSAT · last 30 days
92%
↑ 3 points from previous month
AI explanation
CSAT's trending up across the past 30 days — the +3 point jump is driven by a quieter ticket month at Acme and InsureCo. The slight wobble around day 18 was a single 4-star response; all replies since have been 5-star.
03 · Alert digests

Lastweek'snoise,triagedintoaparagraph.

One AI-generated summary that turns a wall of alert history into a triage list with concrete next steps. Sent on demand or attached to your weekly recap.

Inbox — Weekly Alert Digest
AI summary
Quiet week overall — 12 alerts across 4 clients, down from 31 the previous week. Three threads still open: Acme's backup chain (3 retries), InsureCo's secure-score regression, and GreenfieldCo's patch SLA. None require escalation today.
Acme4 alerts
InsureCo3 alerts
GreenfieldCo3 alerts
RiverbankIT2 alerts
04 · Product match suggestions

RankedcatalogcandidatesforunmatchedPSAsignals.

Zod-typed structured output, not free text. The AI proposes the top 3 catalog matches with a confidence score; you approve or skip. No hallucinated SKUs.

Settings · PSA & Products · Matching
Unmatched PSA product
Microsoft 365 Business Premium — Annual
Microsoft 365 Business Premium
96%
Microsoft 365 Business Standard
71%
Microsoft 365 Apps for Business
42%
05 · Report exec summaries

Aone-paragraphsummaryatthetopofeveryscheduledreport.

Aggressively redacted (names tokenised before they leave your tenant), then drafted into a concise executive summary that sits above the rendered widgets.

Inbox — Monthly Client Report
Acme · Monthly Operations Recap
To: contact@acme.co.uk · From: alerts@yourmsp.com
AI executive summary
Operations were stable this month with one notable improvement and one ongoing watch-item. CSAT held steady at 92% (+3 vs last month). Backup health is green across all servers. Recommend reviewing Person_3's licence assignments — three E3s are inactive 30+ days.
Backup
100%
Threats
0
CSAT
92%
06 · Integration knowledge

Askwhatanintegrationsyncsandgettheactualanswer.

The AI reads our integration catalog — sources, fields, types, capabilities — and answers grounded in real metadata rather than guessing what BackupRadar or CIPP exposes.

Settings · Integrations · BackupRadar
User asked
What does BackupRadar sync?
From the integration catalog
BackupRadar syncs daily backup status across every connected customer. ScopeGrid exposes three data sources from it:
backupradar.summary6 fields
backupradar.failures9 fields
backupradar.coverage5 fields

Governance

Yours to control

Built for MSPs who need to put AI in front of clients without losing the audit trail.

Bring your own provider

Azure OpenAI (UK South recommended), OpenAI, Anthropic, or any OpenAI-compatible endpoint. Per-tenant key, encrypted at rest.

Per-feature controls

Enable/disable each feature, override the model, set monthly token caps, choose redaction level — all from one settings page.

Per-client opt-outs

Exclude any client from every AI feature. Enforced before data leaves the database for tool-scoped queries.

Default redaction

Email and phone stripped from prompts before they go to the provider. Aggressive mode tokenises contact names → Person_N.

Audit log + usage

Every call logged with hashed prompt, token counts, status, model, cost estimate. Browse by feature, user, status. No raw prompt text retained.

Rate limits

Per-user 30/min and per-tenant 600/min fixed-window limits, counted via the audit log — no extra infrastructure.

How It Works

Roll out in three steps

1
1

Connect your provider

Paste an API key (Azure OpenAI, OpenAI, Anthropic, or compatible). Test connection, pick default + fast models.

2
2

Enable features per tenant

Turn features on individually with per-feature redaction, monthly cap, and model override. Default is everything off.

3
3

Use it in flow

⌘K from anywhere. The palette inherits page context and keeps threads across sessions. Audit log gives you visibility.

Supported Providers

Use the provider your team trusts

Hosted, self-hosted, or anything OpenAI-compatible. Per-tenant configuration, no shared models, no vendor lock-in.

Azure OpenAI

Recommended for UK/EU GDPR-conscious deployments. Use UK South or another approved region.

OpenAI

Direct OpenAI API. Data-processing terms apply per OpenAI's standard DPA.

Anthropic (Claude)

Direct Anthropic API. Strong for long-context reasoning.

Custom (OpenAI-compatible)

Self-hosted Ollama / vLLM, OpenRouter, Together, Groq, LM Studio — any endpoint exposing the OpenAI Chat API.

Logos shown for identification only — ScopeGrid is not endorsed by these providers.

Ready To Try It

Enable AI on your terms

Start with one feature, validate the value, then expand across your tenant. Or hit ⌘K in the demo and just talk to it.

View demo