4 agents active today
Live demo

A sample workspace, with questions agents really asked. Look around: nothing here is saved.

Start free with your data

Audit

9 agent calls in the last 7 days: 1.1 s of query time, 0 errors.

Calls
9
from 1 agent, 1 person
Query time
1.1 s
120 ms per call, median 120 ms
Rows returned
42
to agents, never stored
Repeated questions
0 same answer
no question asked by 2+ agents
Errors
0
none

9 calls in the last 7 days, all from Cursor.

Tool calls per day, last 7 days

0127 Nov8 Nov9 Nov10 Nov11 Nov12 Nov13 Nov121212
Source: call log, days in UTC. Calls are kept 90 days; results are never stored, only a fingerprint to compare answers.

Sessions 6

One session is one agent conversation.
northwind via Cursortoday 12:42–12:44 · 2 calls · orders · 216 ms
12:44
Rows: order_id, order_date, customer_id, amount, where status is "refunded", first 50orders v1 · query_rows · 8 rows · 96 ms
12:42
Paid_revenue, where order_date ≥ "2026-07-01"orders v1 · aggregate · 1 row · 120 ms · metric paid_revenue
northwind via CursorWed 11 Nov 12:42 · 1 call · orders · 144 ms
Wed 12:42
Paid_revenue, by customers.segmentorders v1 · aggregate · 4 rows · 144 ms · metric paid_revenue · 1 row unmatched on customer_id → customers.customer_id
northwind via CursorTue 10 Nov 12:42–12:44 · 2 calls · orders · 252 ms
Tue 12:44
Refunded_orders, by customers.segmentorders v1 · aggregate · 4 rows · 168 ms · metric refunded_orders · 1 row unmatched on customer_id → customers.customer_id
Tue 12:42
Rows: order_id, order_date, customer_id, amount, where status is "refunded", first 50orders v1 · query_rows · 8 rows · 84 ms
northwind via CursorMon 9 Nov 12:42 · 1 call · orders · 108 ms
Mon 12:42
Paid_revenue, where order_date ≥ "2026-07-01"orders v1 · aggregate · 1 row · 108 ms · metric paid_revenue
northwind via CursorSun 8 Nov 12:42–12:44 · 2 calls · orders · 288 ms
Sun 12:44
Paid_revenue, by customers.segmentorders v1 · aggregate · 4 rows · 132 ms · metric paid_revenue · 1 row unmatched on customer_id → customers.customer_id
Sun 12:42
Refunded_orders, by customers.segmentorders v1 · aggregate · 4 rows · 156 ms · metric refunded_orders · 1 row unmatched on customer_id → customers.customer_id
northwind via CursorSat 7 Nov 12:42 · 1 call · orders · 72 ms
Sat 12:42
Rows: order_id, order_date, customer_id, amount, where status is "refunded", first 50orders v1 · query_rows · 8 rows · 72 ms
Esc

Do this with your own data

The demo is read-only. With a free account you add your own sheets and CSVs, fix them, and connect Claude, ChatGPT or Cursor in about two minutes.

Create free account