Loading
Loading
The shop owner's morning ritual is currently: open three tabs (calendar, AR, inbox), scroll each, mentally stitch a picture together, then start the day. My Day collapses part of that into one paragraph. Click 'Brief me' and it's generated fresh from real numbers — not a chatbot, not a static template. It's built from exactly three sources: today's appointments, urgent inbox threads from the last 30 days, and invoices aged 30+ days past due. It doesn't read reviews or playbook plays, and there's no clickable action-chip system — it's a paragraph plus three summary badges (appointment count, urgent count, AR total). Your last brief stays saved right there until you refresh it.
7 jobs on the books today. 2 urgent inbox threads need attention. $4,820 sitting in 30+ day AR.
One paragraph, generated on demand from real DB queries (today's appointments, urgent inbox count, AR aged 30+ days). No review data or playbook data feeds this brief today.
Features, zoomed in
Three capabilities built specifically for the day-to-day of a working shop.
Deep dive · 01
Every fact in the My Day paragraph traces back to a deterministic DB query that runs first. The AI gets a structured summary of today's actual numbers — appointments (time, customer, service, status), urgent inbound-message count over the last 30 days, and AR aged 30+ days (balance + invoice count) — and rewrites it as 2-3 plain-English sentences. It does not have access to reviews or playbook/automation data. No 'maybe' or 'I think' — every claim has a source row in the database.
7 jobs on the books today. 2 urgent inbox threads need attention. $4,820 sitting in 30+ day AR.
One paragraph, generated on demand from real DB queries (today's appointments, urgent inbox count, AR aged 30+ days). No review data or playbook data feeds this brief today.
What's included
Everything that ships on day one. No feature-gating surprises inside a single plan.
Who it's for
What it replaces
How it works
The click fetches today's appointments (time, customer, service, status), the count of urgent inbound messages over the last 30 days, and AR aged 30+ days (balance + invoice count).
The structured fact bundle goes to Claude Sonnet with a system prompt: 'You're the shop owner's morning briefing. Write 2-3 punchy sentences from real numbers... no fluff, no opinions.' Falls back to a deterministic stub sentence built from the same numbers if no API key is set.
The paragraph renders on the dashboard with three badges (appointment count, urgent count, AR total) and stays saved right there — in your browser — until you tap 'Brief me' again.
What this looks like in a shop
Illustrative scenario: Mike opens SalesThumb at 7:42am with his coffee and taps 'Brief me.' A couple of sentences tell him: 7 jobs on the books today, 2 urgent inbox threads need attention, and $4,820 is sitting in 30+ day AR. He knows where to start the day — reviews and playbook activity aren't part of this brief, so he still checks those separately.
Questions
Fits in with
Anthropic Claude
Rewrites structured DB output as plain-English paragraph (Sonnet for higher stakes, Haiku for refresh)
Explore more
Revenue, installer performance, per-job material margin, quote-to-paid counts, customer LTV — organized as individual reports you pick from a sidebar, not one mega-dashboard.
Every customer conversation in one inbox. Auto-reminders run 24/7, but when they reply, a human sees it. MMS, templates, merge fields.
Pick a preset drip sequence — win back lapsed customers, follow up cold leads, or ask for a review after a completed job. Choose your pace, edit the message, turn it on.
Every installer, every bay, every appointment in one view. Drag to reschedule. Color-coded by status. Double-book detection with explicit confirm-to-override.