Hermes brings general reasoning on an open model foundation, and the one part of this digest that needs judgement is WORTH A LOOK. Deciding that three cancellations from a single address are a pattern while an unusually large wholesale order is not, measured against a store description you wrote yourself, is not a lookup. The counting half stays pinned to Shopify responses.
Run a staged conversation — no account needed. The agent handles it for real while a simulated world answers its tool calls; nothing touches real accounts, and nothing is actually sent.
Morning tick, Monday 08:00
The 08:00 tick fires. Yesterday the store took 214 orders worth 18,940 EUR against 176 orders worth 15,220 EUR on Saturday, and 63 of yesterday's buyers were new. The largest single order is 1,180 EUR of wholesale ceramic drippers to a cafe in Lyon, and three orders placed from the same Rotterdam address were cancelled within an hour.
Using this template drops you into a guided setup. It asks exactly this, nothing else:
Connect Shopify
One sign-in. The agent acts through your account, scoped to what this template uses.
Connect Slack
One sign-in. The agent acts through your account, scoped to what this template uses.
Store context
What your store sells and what a normal day looks like, in your own words: main products, typical daily order count and average order value, your currency, and anything seasonal. The agent uses this only to tell an ordinary morning from an odd one, never as a source of numbers.
Digest style
The exact sections you want in the message and the order you want them in, how much detail each gets, your date format, and whether you want plain numbers or a line of commentary with them.
Runs on Hermes
Preselected for this page — connect your Hermes account during setup, or switch to NoClick's built-in models with one click.
Watch it handle a test run
A staged conversation against a simulated world — then it’s live.
Order counts are arithmetic, but naming what a person should decide today means reading the numbers against your description of a normal day.
You run an open-model agent that still calls Shopify and Slack with your connected credentials, without standing up any serving of your own.
The instructions are strict: figures are copied exactly, currency stays as Shopify returned it, and nothing is extrapolated to a week or a month. That is worth testing rather than trusting, so run Sale Weekend Spike, where a 903-order day invites a model to reach for a trend. If the output projects anything, tighten the digest style variable before you schedule it.
Free to start. Guided setup, a test run against staged conversations, and it's live.