SHT-01Agent schedule
One of the systems we built has AI in it, and this is the only sheet where we say so. Everything below names the file it comes from. The agent's job is to catch the call, sort the reply, and put a person in front of the lead while it is still warm.
SHT-02Detail A · inbound voice
A Vapi assistant takes the inbound call. When it ends, Vapi posts the end-of-call report back into the system, which checks a shared secret before it believes anything, reads the duration to tell a conversation from a wrong number, matches the caller to a lead record, and sends the owner a Telegram alert while the lead is still warm. Short calls and no-answers are recorded but not announced, because an alert that fires for everything gets ignored.
SHT-03Detail B · telephony
Six routes carry the actual telephony: a token endpoint so a call can be placed from the browser, a voice route that answers, a status callback so the system knows how the call ended, and a hook that fires when a recording finishes writing.
SHT-04Detail C · follow-up engine
Automated follow-up is easy to build and easy to get wrong in ways nobody notices for a month. Each module below was written after a specific failure, and the failure is written into the top of the file.
Every inbound message used to count as a human answering. Bounces, out-of-office autoreplies, and opt-out shouts all promoted a lead to 'replied' and quietly paused its sequence, which then had to be undone by hand. The classifier separates the four cases and routes each one differently.
A lead that answered and has heard nothing back since is the most expensive thing in the pipeline. It goes into a daily digest and stays there until someone actually moves it, rather than being announced once and forgotten.
When sending volume is high and real replies are not, the daily cap comes down on its own. Sending harder into a spam folder costs the sending domain, and the domain is the one asset here that cannot be replaced.
Every wait in the system is counted in business days, and a step that lands on a Saturday moves to the Monday. A nudge that arrives on a Sunday reads as a machine, because it is one.
Steps are stored relative to the step before them, and where a subject line has variants, the variant is picked by a deterministic hash of the lead. The same lead always gets the same one, so a restarted sequence never reads as a different sender.
Sends over SMTP and reads replies back over IMAP from the actual mailbox, so a reply is a reply rather than an inference from a tracking pixel. Every message carries a working unsubscribe.
Proof · wallflow-saas · lib/followups/ (12 modules)
SHT-05Detail D · the dialer
A caller opens one tokenised page and works a list: the next number, who it is, what happened last time, and where the outcome goes. Eight endpoints stand behind that page, the campaign, the lead, the log, the callbacks, the calendar, the activity feed, the history, and the outreach record. Nothing is generated for the caller mid-conversation. The software's job is that they never have to look anything up.
SHT-06Detail E · scheduled work
The parts of the working week that depend on a person remembering are the parts that stop happening in a busy month. These run on a schedule instead.
Proof · wallflow-saas · app/api/cron/ (13 jobs)
SHT-07General notes · what this page will not claim
SHT-08Cross-reference
An agent that answers the phone and writes into nothing is a novelty. The reason the handoff works is that there is a system on the other side of it: the lead, the estimate, the deposit, the schedule. That is on its own sheet.
See the systemSHT-08Issued for construction
A short video walkthrough of where your lead flow leaks and what it would take to close it. Free, and there is no call afterwards unless you want one.
Get my free audit →
