Situation
The resource everyone prices at zero until it is gone
Burn a domain or an account and no amount of good copy will save you, because nothing you send arrives. The graveyard of outbound operations is full of teams that scaled volume first and discovered deliverability second.
The math that kills them is simple. Channels enforce limits, formal and informal, on how much a sender can do and how fast. Push past them and the channel quietly stops delivering you, then not so quietly. Most teams respond by either under-sending from one precious account or blasting from disposable ones, which torches the one thing outreach cannot work without: the credibility of the sender.
We send at meaningful volume across channels for ourselves. So we built the orchestration layer that makes volume and reputation compatible. This page describes it at the level of detail we are willing to publish.
Three rules were fixed before the first line of code. Reputation outranks throughput: whenever volume and account safety conflict, the system throttles, because a slower week is recoverable and a burned sender is not. Safety is enforced by the system, not by discipline: limits, pacing and rest patterns are code paths, so the safe behavior is the only behavior the system can produce. And humans approve what goes out: campaign targeting, messaging and sequences pass a human gate before any account carries them, and replies route to a person.
What we built
One control plane over a fleet of sending accounts
Each account has its own dedicated infrastructure and its own state.
- Staged warmup. No account carries campaign volume until it has completed a minimum 21-day warmup, ramping activity gradually the way a new account behaves. The schedule is defined in the system's operating directives.
- Sender rotation. Campaign load spreads across the fleet so no single account exceeds conservative daily caps. Volume is a fleet property, not an account property.
- Humanized pacing. Activity follows natural rhythms: variable timing, varied session lengths, rest periods. No account behaves like a machine with a quota.
- Per-account isolation. Each account runs on its own infrastructure, so accounts do not share fate and one problem cannot cascade across the fleet.
- Monitoring and automatic pause. Account health signals are watched continuously. Anything anomalous pauses the affected account first and asks questions second.
- Approval gates. New campaigns, new messaging and new targeting are human-approved before launch. The rules are plain text the team can read and audit.
The system runs containerized on infrastructure we control, with campaign logic centralized and AI-assisted messaging generated upstream of the approval gate.
How it runs
Conservative by construction, and lighter on mechanics than our other cases
Node.js runs the orchestration and campaign logic. Python handles execution-layer automation. Gemini generates message drafts upstream of the human approval gate. Docker packages the fleet for deployment on infrastructure we control. The broader stack reasoning is at /stack.
This case says less about mechanics than our others, and that is a choice worth explaining. Outreach automation sits in an arms race. Channels evolve their detection and their rules, and operators evolve their tooling. We operate conservatively inside that reality, and we do not publish the specific techniques, channel by channel, that make this system durable, for the same reason a security firm does not publish its red-team playbook. The principles above are complete at the level that matters for evaluating us. The implementation details are a client conversation.
What we will say plainly: every message identifies its sender, unsubscribes and opt-outs are honored, and the system is built to respect CASL. Conservative is the compliant strategy as well as the safe one.
Running it taught us three things. Warmup patience is the highest-return safety spend. Three weeks feels expensive exactly once, and replacing a burned account teaches you the real price. Caps must live in code, because every operator believes they will respect limits manually and under quota pressure nobody does. And fleets beat heroes: one excellent account is a single point of failure, while rotation turned sender capacity into something we can budget and survive losses in. Those lessons now shape every outbound system we ship. Client builds send through warmed, throttled, compliant delivery because we learned the cost curves on our own accounts first.
The replies this system generates flow into the reply-to-deck pipeline, and the productized client version of research-first outbound is the outbound engine, running in production in the Breez case. If your team is sending from one overworked inbox or a pile of disposable ones, the free audit is where we would start.