Business lens demos/biz-03-kpi-dashboard.html Fictional data ← all artifacts
KPI dashboard · customer operations

Contact centre KPIs: May 2026

Latest week ending Sun 31 May 2026 · weekly spreadsheet export

ABC Corp is a fictional company. Every name, number and date is invented. This is a reference artifact generated with an LLM coding agent; the brief that produces it is at the bottom of this page.

Contacts handled per week

Volume by channel

Phone Chat Email

What the numbers say — targets & RAG read

GREEN
Avg handle time — 7.2 min vs ≤ 7.5 min target. Fifth straight weekly fall; the team is getting more efficient.
GREEN
First-contact resolution — 73.8% vs ≥ 73% target. An eight-week high, so fewer customers come back a second time.
AMBER
CSAT — 4.19 / 5 vs ≥ 4.20 target. Just under target and down from 4.22 two weeks ago — the metric to watch.
AMBER
Contacts handled — 2,735 / week vs a 2,400–2,700 capacity band. Above the band; chat volume up ~38% since mid-April is the driver.

So what: efficiency (AHT and FCR) is absorbing the rising volume for now, but CSAT slipping below target is the early warning. If chat keeps climbing, add chat capacity before CSAT drops under 4.15, not after.

KPI summary — every week behind the charts

Week endingContactsAHT (min)FCR %CSATPhoneChatEmail
12 Apr2,5108.170.44.121,480610420
19 Apr2,5008.070.94.151,455640405
26 Apr2,5767.971.54.101,510668398
3 May2,5557.772.04.181,462701392
10 May2,6527.671.74.211,530742380
17 May2,6377.572.64.241,495768374
24 May2,7147.473.14.221,551802361
31 May2,7357.273.84.191,538845352
How this was made: the brief, how to reproduce it, and an honesty note

The brief

I'm pasting a table exported from a spreadsheet [paste]. Build a one-file
HTML dashboard: four KPI cards with week-over-week change arrows, a line
chart of weekly volume, and a bar chart by channel. Add a 4-week/8-week
toggle. Inline SVG only: no chart libraries, no external requests.

How to reproduce

Paste the brief into any capable LLM: GPT, Claude, Gemini, Grok, DeepSeek, or the assistant your company provides. Iterate a few rounds on layout and content until it reads well. Save the final answer as a .html file and open it in any browser. Expect similar output, not identical: every model has its own taste, and that is fine.

Honesty note

This reference artifact was built with Claude Code, an LLM coding agent, over several iterations. Treat it as the bar to aim for, not as a guaranteed first answer. All data on this page is fictional.

Next artifact Process and onboarding guide →
vishalshah.app