AI Insights
AI Salesforce reports and dashboards from plain English
Tell Insights what you want to see (“funding by month by region for the last year”) and it builds the queries, chooses the visualisation, validates everything, and saves a dashboard that runs against your live org data — refreshed when you say, not on every open. Then put it in front of the people who need it — including inside Salesforce itself, as a Lightning component.
Funded this quarter
Win rate
Open pipeline
Average days to fund
Funded amount by month
Open pipeline by stage
Largest open opportunities
| Account | Stage | Amount | Close date | Owner |
|---|---|---|---|---|
| NORTHWIND HOLDINGS PTY LTD | Settlement | A$1.85M | 18 Sep 2026 | Priya Nair |
| BRIGHTWATER LOGISTICS PTY LTD | Offer issued | A$1.42M | 2 Oct 2026 | Jordan Chen |
| MERIDIAN TRANSPORT PTY LTD | Credit assessment | A$1.18M | 9 Oct 2026 | Wendy Turner |
| STONEBRIDGE CIVIL PTY LTD | Credit assessment | A$0.96M | 23 Oct 2026 | Priya Nair |
| CEDAR HAULAGE PTY LTD | Qualification | A$0.81M | 6 Nov 2026 | Miles Doyle |
What you can do
- Charts, reports, and multi-block dashboards: bar, line, area, pie, and metric blocks on a grid
- Live when you need it: SELECT-only SOQL against your org, with Refresh always going live
- Cached briefly when you don’t: a recent run is reused for 5, 15 or 60 minutes (or until you refresh), encrypted and tied to the login that read it, so a busy dashboard doesn’t spend your API allowance on every open
- An “As of” time on every dashboard, and an Always live setting for dashboards that list personal data
- A semantic layer of named KPIs, dimensions, and filters the AI must use — no guessed field names
- The AI asks a clarifying question when your request is ambiguous, instead of guessing
- Every asset is dry-run validated before it can be saved — broken dashboards can’t exist
- Folders that nest and hold any mix of dashboards, reports and charts, in one searchable list with breadcrumbs
- Share an item or a whole folder with a member or with everyone in the workspace, as “Can view” or “Can edit”
- A shared dashboard runs through each viewer’s own connection to the org, so nobody sees data their Salesforce permissions hide
- Embed any dashboard inside Salesforce as a Lightning component, on a record page, app page or Home
- Pin filter values per placement, so the same dashboard shows one region on one page and another elsewhere
- The Salesforce package (Apex, the Lightning component, a viewer permission set, a sandbox post-copy class, a settings object and the CSP Trusted Site) is scaffolded for you into a Development Studio project, ready to review and deploy
- Embedded dashboards check the viewer can read the record before showing it, and everyone in an org shares one cached run instead of each view hitting the API
- A versioned package: each org shows the version it runs, and an update keeps any files you customised
How it works
Define your language once
Optional but powerful: name your KPIs (“Funding per month”), dimensions (“Region” → Account.BillingState), and filters (“Funded deals”).
Describe the output
“Top 10 accounts by open pipeline as a bar chart.” The AI compiles SOQL from your definitions.
It checks its own work
The complete spec is executed in preview (every query, every column binding) before anything is saved.
Open it, refresh when you like
Like a Salesforce dashboard: it shows when its numbers are from, reuses a recent run for the window you choose, and Refresh always queries live.
Put it inside Salesforce
One click scaffolds the embed package into a Development Studio project. Review it, deploy it through the normal flow, then drop the component onto any Lightning page.
Step by step: Show dashboards inside Salesforce
Why it's different
KPIs your team defines
Most “AI reporting” guesses which of your 900 fields means revenue. Insights compiles queries from KPI and dimension definitions your team controls, so “Region” means the same thing in every chart, for every person, every time.
Try asking
- “Revenue by region by month, last 12 months, as a line chart.”
- “Win rate by lead source, quarterly, with a target line.”
- “A dashboard: pipeline by stage, top 10 open opportunities, and cases by priority.”
- “How is each sales team tracking against target this quarter?”
- Put the finished dashboard on the Account record page, filtered to the account being viewed
- Give the sales team a live pipeline chart on their Salesforce Home page, with no second tool to open
- Keep a “Board pack” folder of dashboards and share it with everyone in the workspace, including people who join later
AI Insights — questions
Works even better with
Replacing something?
- orgadmin.ai vs Agentforce
Salesforce’s platform for customer-facing AI agents. Compare when what you wanted was AI for the people who run the org.
Read next
- How to build Salesforce dashboards across multiple objects
When two objects share only an indirect relationship, forcing them into one report can duplicate rows and distort totals. Start with grain, not the chart.
- Agentforce, Einstein, or your own AI key?
Salesforce sells AI licensed per user for customer-facing agents. Most admin teams want something quite different — and the pricing reflects that mismatch.
Put AI Insights to work on your org
Every AI feature on your own provider key, from A$14.99 per user per month.
- 14-day free trial
- No credit card required
- Cancel any time