Back to 1AYM

Engagement files

What we have built.

1AYM publishes five case studies, which we call engagement files: a governed finance data connector, an IELTS speaking assessment built as a measuring instrument, AI, data and automation enablement across a global agency, identity provisioning for 1,000+ users across 600+ groups, and a clinical-research platform taken from stalled build to launch. Each states what we built, what it measured and what the client kept. That last part is the test for any partner, and our guide to adding AI features to a software product sets it out: whoever builds the feature, your own team should end up owning it, its evaluation set and its running cost.

For anyone weighing suppliers, a buyer’s guide to choosing an AI supplier sets out four checks to run before you buy.

Our guides for AI buyers cover the questions either side of choosing a supplier, from whether an AI agency or an AI consultancy suits the work to how to run AI safely.

2 of these files are workstreams within one client engagement, which grew from integration work into the lead architect role on the client’s AI platform.

D-06

Self-serve finance answers, without breaking permissions

A PE-backed firm

A question about client or financial performance used to take around two hours to come back from the finance team. It is now answered in the meeting where it is asked, and nobody gained access they did not already have: the connector carries each person's existing Looker entitlements.

~2 hrs → in the meetingTime to a governed finance answer1 afternoonTo connect the data1 weekTo make the numbers trustworthy
D-02

An IELTS speaking assessment built as a measuring instrument

A government-accredited EdTech in the Middle East

We hold end-to-end technical ownership of a government-accredited EdTech's live production estate, and its IELTS speaking assessment is the centre of it. Most AI speaking scorers are one model call wrapped in a product; this one is a measuring instrument.

11–14 minThe whole interview is scored, not a sample5 layersOf evidence, and the AI never does the arithmetic×3Examiner model runs, median taken, escalate on disagreement
D-01

AI, data and automation enablement across a global agency

A large international marketing agency

Sessions on this agency's AI platform now cost 60% less on average than they did before we re-architected its skills estate. An earlier change, a per-user API call replaced with one ten-minute sync, carries a forecast saving of £2–4M a year, modelled on token consumption and reviewed by the client's finance team.

60%Lower cost per session after the re-architecture£2–4MForecast annual saving, finance-reviewed~600Skills on the platform we contribute to
D-04

Identity provisioning for 1,000+ users across 600+ groups

A large international marketing agency

When somebody leaves, their access to Notion and Claude ends with their HR record rather than when a colleague remembers. We built the provisioning system that does it from scratch, because the client's IT team was over capacity and off-the-shelf group tooling did not fit a model where one person belongs to many groups: it covers more than 1,000 users across over 600 groups and has run for seven months.

1,000+Users provisioned600+Groups managed7 monthsRunning in production
D-05

A regulated product that was not going to ship, shipped.

A clinical-research software start-up

A clinical-research software start-up had a part-built platform, no engineering environment its own team could ship from, and a launch that was not going to happen on the path it was on. We worked with the founders: first a development environment, with repositories, environments, continuous integration, review gates and a release discipline, then completion of the platform, then delivery to launch alongside their team.

FoundersEngagement partnerDev environmentBuilt for the team to shipCompletedPlatform modules brought to release

Last reviewed · 1AYM

Questions

Common questions

What do the engagement files show?

Five case studies of work 1AYM has delivered. Each states what we built, what it measured and what the client kept, with the constraints and the parts that were hard.

Are the clients named?

Clients are described by what they do rather than named, so each file shows the work, the figures and the method without identifying the client.

Who can help us build something like this?

1AYM. The five files cover a governed finance data connector, an IELTS speaking assessment, AI enablement across a global agency, identity provisioning for more than 1,000 users and a clinical-research platform taken to launch. Book a 30-minute call or email enquiries@1aym.com.