Situation
The most valuable event in outbound is also the most perishable
Someone you wrote to wrote back. From that moment, every hour of silence costs you, and the honest response, a researched, specific, personalized proposal, used to take hours to assemble. Research the company. Work out the angle. Build the deck. By the time it was ready, the warmth had drained out of the thread.
We sell systems that fix exactly this kind of bottleneck, so we built one for ourselves. This is the pipeline that runs our own sales motion. We publish it because a vendor's own operations are the one case study they cannot fake.
What we built
Five stages from reply to ready-to-send, with a person on the send button
- Stage 1, reply detection. Monitors on our outreach inboxes catch responses as they land and classify them: interested, not interested, question. Interested replies trigger the pipeline and post to a Slack channel.
- Stage 2, research. A research agent calls Perplexity for company intelligence and Apify to read the prospect's website, then merges the findings into one research record.
- Stage 3, strategy. A three-pass model pipeline turns research into an argument. A research analyst pass (GPT) extracts hooks and pain points. An ROI calculator pass (a smaller model in the same family) estimates what the prospect's current process costs and what automation would return. A message writer pass (GPT) drafts the personalized follow-up.
- Stage 4, deck generation. The strategy is flattened into 40+ personalized fields and assembled into a proposal deck through PandaDoc, from template to shareable link without a human touching a slide.
- Stage 5, human approval. The finished message and deck land in a Slack channel and wait. A person reviews, edits if needed, and sends.
One strategy run, from a live pass of the pipeline, produced an analysis for a prospect whose manual processes the ROI pass costed out at $132,600 in annual waste, against $85,800 in projected first-year savings from automation, a 17x multiple on the proposed build.
Those numbers are an illustrative sample from a live run. Not an average, not a promise, and not a measured client outcome. They show what the strategy stage produces for a single prospect from that prospect's own situation: a specific, checkable financial argument instead of a generic pitch. Every deck the pipeline builds carries its own version of that math, calculated fresh from the research record. The numbers we stand behind as results live on the Breez case.
How it runs
Webhooks on Railway, a directive per stage, and a gate where the deal begins
Each stage is a webhook-triggered script paired with a plain-text directive, running on Railway. The Slack channels mirror the stages, so the whole pipeline is watchable: reply detected, research ready, strategy ready, ready to send.
The pipeline is fully automated precisely up to the moment the output would touch a prospect. That boundary is deliberate, and it is the same boundary we build into client systems. Everything before the gate is assembly work: reading, extracting, calculating, formatting. Machines do that faster than people, and nothing is lost when they do. The send itself is a relationship decision, and a live deal is the wrong place to discover an edge case. The gate costs us seconds per deal. The alternative failure mode costs deals.
GPT and a smaller model in the same family run the three-pass strategy pipeline. The cheap model does the arithmetic-shaped middle pass and the stronger model does the judgment-shaped ends. Perplexity is the research agent for company intelligence, Apify reads prospect websites, PandaDoc assembles proposals from the structured fields, and Slack is the pipeline's face, one channel per stage plus the approval gate. Stack reasoning, including when we reach for which model, is at /stack.
Running this on our own revenue taught us things client builds only suggested. Stage isolation earns its keep on bad days: a failed research call delays one prospect, not the pipeline. The ROI pass is the deck, because prospects skim everything except the math about their own business, which is why the calculator sits in the middle of the strategy stage instead of bolted on. And cost control in an LLM pipeline is an architecture decision, not a procurement one: cheap models in the middle, strong models at the edges. That pattern now ships in client builds.
This is the engine behind the outbound engine we sell. The client-facing version is the Breez build, where the same reply-to-proposal discipline runs at a lead generation company. The orchestration layer that feeds this pipeline its replies is our outreach orchestration system. And if you want to see what the strategy stage would calculate for your own operation, the free audit is the manual version of exactly that pass.