Skip to content
American owned and operated
Nightshift

AI Connect

Give your assistant your data, and ask it anything

One governed connection between your business and the assistants your team already uses: ask questions, automate the work behind them, build applications on top.

Let’s chatSee the engagement

Works with the assistant your team already uses

  • Claude
  • ChatGPT
  • Gemini

What it looks like

Ask in plain English, get something you can check

Not a paragraph of prose. Figures, a filterable table, an export, and the method it used, on one page. Four examples below, built on sample data.

Asked: Which customers have not ordered in one to five years?

Customers who have not ordered in 1 to 5 years

Accounts with no order in the window, rolled up to parent and deduped, so a chase list can go straight to a rep.

window: ≥365 and <1825 days inactive · cutoff 2026-06-02 · qualifying states sale, done · rolled up to parent account · deduped by name · 40 confirmed-closed accounts excluded

4,936

Inactive total

571

Wholesale

2,261

Retail

1,703

No rep assigned

2016

Oldest account since

Longest inactive, largest lifetime value first

AccountLast orderLifetimeStatus
Kestrel Hospitality Group2019-11184,200Chase
Bramble & Vine Retail2021-0396,400Chase
Old Quarry Taproom2022-0841,900Review
Sandpiper Provisions2024-0128,300Recent

By channel

Public225
Wholesale37
Retail18

Top regions

Northeast30
West23
Midwest21
Southeast17

Illustration of the shape of a real report. Every figure and label here is invented sample data.

Asked: Which product lines are selling below cost?

Product lines ranked by contribution margin

Contribution after freight, duty and accrued rebates, ranked lowest first rather than averaged into a category figure.

window: rolling 90 days to 2026-06-02 · landed cost includes freight and duty · customer rebates accrued to the line that earned them · intercompany transfers excluded · 3 lines with no cost record shown as unqualified

26

Lines below cost

18.4%

Blended margin

31.4%

Best line

3

Cost record missing

Lowest contribution, after freight and rebates

LineRevenueLanded costMarginStatus
Bordeaux 750ml, flint184,200189,000-2.6%Below cost
Crown cap, gold 26mm96,40085,80011.0%Thin
Cork, natural 44 x 24142,700115,30019.2%Healthy
Champagne 750ml318,900233,40026.8%Healthy

Contribution margin by category, percent

Closures27
Cork21
Glass16
Capsules9
Labels4

Illustration of the shape of a real report. Every figure and label here is invented sample data.

Asked: Who owes us money, and how late is it really?

Receivables by age, with the buckets labeled honestly

Balances aged from due date, with not-yet-due kept in its own column instead of folded into current.

as at 2026-06-02 · aged from invoice due date, not issue date · credit notes netted against the invoice they relate to · disputed balances flagged, not removed · 2 accounts in payment plans shown separately

47

Days sales outstanding

116.6k

Past due

5

Accounts over 60 days

2

On payment plans

Largest past-due balances

AccountBalancePast dueDaysStatus
Meridian Hospitality Group84,12061,40074Chase
Cobalt Retail Partners52,94038,21061Chase
Harbor Line Distributors41,30012,88038Watch
Fairmont Beverage Co29,7604,12019Watch

Balance by age

Not yet due214
1 to 3063
31 to 6034
61 to 9019
Over 9012

Illustration of the shape of a real report. Every figure and label here is invented sample data.

Asked: Which suppliers are actually delivering on time?

Supplier on-time and in-full, accumulated over 12 months

On-time and in-full against the confirmed date, accumulated over every order rather than assembled before a review.

window: 12 months to 2026-06-02 · on-time measured against the confirmed date, not the original request · partial deliveries counted as late until complete · 1 supplier with fewer than 5 orders excluded as not comparable

86%

On time, in full

31 d

Longest lead time

4

Suppliers below 80%

1

Too few orders to score

On-time and in-full by supplier

SupplierOrdersOn timeIn fullStatus
Ashgrove Packaging18661%74%Review
Harbor Line Glass24378%88%Watch
Cedar Ridge Closures41291%94%Good
Northvale Glass58896%97%Good

Average lead time, days

Northvale12
Cedar Ridge19
Harbor Line24
Ashgrove31

Illustration of the shape of a real report. Every figure and label here is invented sample data.

How it is put together

  1. 01

    It speaks MCP

    Model Context Protocol is the open standard for connecting AI to real systems, published by Anthropic and adopted across the industry. AI Connect is an MCP server over your data, so anything that speaks MCP can reach it.

  2. 02

    Claude, ChatGPT and Gemini

    Every assistant that speaks MCP reaches the same data: Claude Desktop and Code, ChatGPT, Gemini. Your team keeps whatever they already use.

  3. 03

    You decide what it can reach

    It exposes the slice you grant it and nothing else. Read-only by default, against the tidied copy.

AI Connect is one MCP server over your own data

An MCP server over your own data

Works with Claude, ChatGPT and Gemini

You grant the scope

Answers state their own method

What comes back

Reports that tell you how they were built

Ask a broad question and you get a working report, not a paragraph: figures, charts, a filterable table, an export. Each states its window and cutoffs at the top.

  • The method is on the page

    Which tables it read, the date range, the rules applied, the records left out. Check it instead of trusting it.

  • Filters that work

    Search, dropdowns, date ranges, export. A working view of your data, not a screenshot of one moment.

  • It tells you what it left out

    Where a list is capped, or records were excluded deliberately, the report says which ones and why.

  • Built by people who do this

    We run MCP servers in production against real customer systems.

Why it holds up in production

It works with Radiance

Radiance watches the numbers on a schedule. This lets anyone dig into the same data, on the same definitions, whenever they need to.

It works from your data

Answers get built from your records and show what they drew on. Where the data cannot support a claim, it says so.

No new tool to adopt

Nobody learns an interface. The assistant your team already uses just knows the business now.

See the whole engagement

The other half

One Nightshift Ecosystem

Radiance

Radiance automates away hours of manual reporting.

Discover more →

Ready to start building your AI workforce?

It only takes an hour, no fluff. Meet with a Nightshift engineer to get started.

Let’s chat