EN FR
Editorial illustration of an email archive being distilled into structured patterns

Eighteen years of email, turned into a pattern library

Over 500,000 messages in my email archive, filtered down to 736 high-signal customer recommendations — now a pattern library my sales and marketing partner's AI assistant queries live, every week.

For eighteen years I've answered the same recurring customer email at CoachingOurselves: a client describes their situation and asks which peer-learning topics we'd recommend. I've developed a careful style for those replies — validate their own picks, flag readiness-dependent topics, sequence the program. None of it was written down. It lived in my head and in my sent folder. In late March 2026 I pointed a pipeline at the archive and turned eighteen years of judgment into something my sales and marketing partner's AI assistant now queries live, every week.

The raw material: decades of expert judgment locked inside one person's sent folder.

The archive — years of expert correspondence in a single list, every row authored by the expert

The cheap pass collapses the haystack first. Only the survivors get the expensive treatment.

Cheap-first funnel: full archive narrowed by keyword filter, then scored for density, then handed to the human

Body length × keyword count beats semantic similarity for finding actual worked examples.

Density heuristic scatter plot — long bodies full of recommendation vocabulary land in the gold zone

The same words, restructured. Structure is what makes them findable when a different person hits a similar problem.

A long reply distilled into a structured pattern entry with situation, topics, caveats, sequencing, and when-to-use fields

The library is the durable artifact. The expert's voice scales without the expert in the room.

Pattern library in use: partner query reads matched patterns, produces a grounded recommendation for a prospect

The reusable part is the pipeline plus the pattern guide — cheap-first filtering, density scoring, hand-curated structure. It works on any senior expert's long-form archive: sales correspondence, consulting engagement logs, customer support histories, decision threads. The bottleneck isn't that the knowledge isn't there. It's that it's trapped in a format nobody else can search.

My sales partner at CoachingOurselves ran the same pipeline on his own emails. Then we pulled an export of our Salesforce data and the invoices we'd sent, and generated a lessons-learned report that let me learn from his patterns and him from mine. Two people who had worked together for years, discovering things about each other's judgment that had never been said out loud.

If you're sitting on years of your own knowledge locked in email, this one isn't a one-session job — the pipeline needs to know what it's looking for before it starts pulling. We get on a call, you tell me what kind of knowledge you want extracted and what you'd use it for, and I scope out how much work the archive will take. Then we work through it together.

Let's talk →

Related projects