Company knowledge should compound wherever agents work.

Wrenfield builds fleet telematics software: a nine-year-old monorepo, 140 engineers, a coding agent on every machine. Ten engineers on the dispatch services ran memco for thirty days against a measured baseline. The platform team then rolled it out to everyone.

Pellam sells accounting software to small businesses and answers 1,900 tickets a week from Manchester and Lisbon. A drafting agent wrote the first reply on every ticket, and reviewers edited six in ten. Thirty days of memco on the billing queue changed what the reviewers spent their time on.

Carrow Street owns fourteen software companies. At the largest, the token bill had become a board-level line and 380 developers were learning the same lessons separately. The first rollout took eleven days to prove value. The second, seeded from the firm's playbook, took four.

Tillingham's data engineering group builds the pipelines behind its regulatory returns and client reports. Coding agents wrote most of the changes and reviewers corrected the same unwritten rules every week. An eight-week pathfinder put those rules under four-eyes review, in the firm's own cloud, with an audit trail the regulator could read.

Merriwether runs 23 orthopaedic and imaging clinics. Its assistants draft prior authorisations, propose codes and fill the schedule, and the people who check them know every payer's habits. Thirty days on imaging authorisations at four clinics turned those habits into rules every desk reads, with no patient in memory.

Dunmore Pryce is a 380-lawyer firm in London and Leeds. Its agents mark up contracts and partners correct the markups, the same corrections across associates and matters. Thirty days in the commercial group put those corrections into memory a matter at a time, with one network per matter and nothing crossing between them.

Tomas works alone from Porto for three clients, in Claude Code, Cursor and Codex, on three codebases with three sets of rules. One personal network followed him between tools and models. Three client networks never touched. The first reuse came on day two and the free allowance ran out in week three.

Nine people shipping a scheduling product for field crews with coding agents all day, and a founder who reviewed nearly every pull request because she was the only one who knew the rules. She connected memco in an afternoon. By day three an agent had reused a lesson. By week six a new engineer was productive in days.

Ferrant is 240 people and 120 engineers in six teams, each with its own prompt file, one of them 900 lines long. The payments team ran memco first, on the Team plan. A quarter later the whole company was on a governed tenant with the same memory, and support was reading engineering's lessons.

Greyfriars Mutual is modernising a twenty-year-old policy administration estate with 600 engineers, a third of them from a systems integrator. The agents were already on the programme. An eight-week pathfinder on one named workflow, in the insurer's own UK cloud, measured what they learned and converted to a programme licence.

Halden Reed runs 40,000 people and thousands of engagements a year, and its agents relearned the firm's method on every one. The AI lab ran memco first, as client zero, on its own fleet of fourteen agents. Then the data engineering practice, then the first client programme. The walls held at every step.

Brennick has 3,100 engineers on a core banking estate that four people understand, and two of them were retiring. The developer platform team ran memco on-premises with locally hosted models, sixty engineers first, then four hundred, then everyone. The approved model changed in week nine and nothing was lost.