All loops
FinanceEasy 13 min· claude-opus-4-1
Budget vs actual narrator
Budget vs actual narrator with auditable Claude reasoning.
Read the full Finance build guide →NOT DEPLOYEDNOT DEPLOYED
0163ms
Trigger
cron(0 7 * * *) fired · every day · 07:00
02943ms
Agent
claude-opus-4-1 · in 1243 tok · out 397 tok
03213ms
Tools
postgres-mcp/anthropic:messages.create → 200 OK · 183ms
0453ms
Verify
schema check · zod v3 passed
0583ms
Output
invoice row upserted · $4,120
0643ms
Notify
audit log written · runbook link attached
SUCCESS
0%
0 runs
P50
0ms
median
P95
0ms
tail
AVG COST
—
per run
LAST OK
never
—
LAST FAIL
never
none
Latency · last 30 runs0 samples
no runs yet
Latest output · what your users see
Invoice · SegmentTooling
$1,063.33 USD
// press Test to run once · Watch live to keep streaming · Deploy to make it real
The problem
Finance ops are spreadsheets glued together with hope.
The outcome
A scheduled agent does the join, the variance, and the narrative.
Ingredients & skills
Secrets
- ANTHROPIC_API_KEY
- STRIPE_KEY
Providers
- Anthropic
- Stripe
MCP servers
- postgres-mcp
- fetch-mcp
#finance#ops#claude
How it works
Budget vs actual narrator with auditable Claude reasoning.
Step 1
1 — Pull
Read from billing + GL via read-only keys.
Step 2
2 — Join + narrate
Claude joins, computes, and writes the narrative with citations.
Step 3
3 — Distribute
PDF + Slack + (optional) board portal.
One-line deploy
The button above runs the same command with your saved config. This is the raw CLI form.
bash
npx claudeloops deploy budget-vs-actual-narratorRelated loops
Finance
Weekly investor update generator
Stripe + Postgres metrics → narrative artifact → Resend to your investor list.
Ops
On-call alert → AI runbook
PagerDuty → Claude reads last 5 deploys + logs → draft runbook in the alert thread.
Finance
Stripe revenue anomaly alert
Detect MRR cliffs in real time and ping #revenue with the suspect customer.