How a National Pharmacy Society Gave Nine Departments Their Own Assistant on One Subscription

9

Assistants, one per job that needed one

35.2M

Words of clinical and member content processed

0

Support tickets in three years

Summary

A US national professional society for pharmacists working in hospitals and health systems runs nine purpose-built assistants, each grounded in one department’s own material. Between them they cover member support, knowledge discovery across clinical reference content, and internal staff support, over 6,767 documents and 35.2 million words. The busiest month carried 1,006 questions, and in three years the society has raised zero support tickets. All nine run on a single entry-level subscription. The society shared the deployment anonymously.

Industry

Member Associations, Healthcare

Use Case

Enterprise Search, Customer Support, Knowledge as a Service

Teams

Operations, Customer Support, Cross-Functional

At a glance

IndustryNational professional society, hospital and health-system pharmacy
SizeAround 1,000 staff, serving pharmacists across US hospitals and health systems
ObjectiveGive each department an accurate answer service over its own body of content, without running a project for each one
Key use casesMember self-service and support, knowledge discovery across clinical reference material, residency program resources, advocacy positions, practice-advancement research, news, association management system support for internal staff
SolutionCustomGPT.ai. Nine purpose-built assistants on a single subscription, each grounded in its own content, deployed as web assistants
Corpus6,767 documents and 35.2 million words processed across the estate
OwnerThe departments themselves, not IT
SharedAnonymously, at the customer’s request

The challenge

A hospital pharmacist checking a drug monograph mid-shift. A resident working out which residency programs take her specialty and when applications close. A policy staffer who needs the society’s published position on a bill before a meeting starts.

These are not variations of one question. They come from different people, draw on different bodies of content, and belong to different departments inside the society. A single assistant trained on everything would answer all three badly.

The society’s problem was never a shortage of content. It was that each department needed its own narrow, accurate answer service, and none of them could justify a project of their own.

The solution

One corpus per assistant. Drug reference material and residency deadlines have nothing to do with each other, and an assistant holding both will blend them at exactly the wrong moment. Narrow scope is an accuracy decision before it is a design decision.

It reports what is published, and it does not practice. A society can tell you what its own monograph or position statement says. It cannot make a clinical judgment for a pharmacist at a bedside. Retrieval limited to published material keeps that boundary structural.

Standing up the tenth agent has to be trivial. If each new department needs its own contract, budget line and procurement cycle, the second one never happens.

Internal audiences count. Staff asking each other how the membership system works is the same problem as members asking how a program works, and internal agents need no brand review or legal sign-off.

What the nine actually are

Drug information came first, over the society’s formulary reference, and it remains the busiest by a wide margin. Residency programs followed, with a dedicated agent for the resources residents and preceptors ask about every cycle. Advocacy and practice advancement each got their own, one for policy positions and one for the society’s national survey work.

A general society assistant, a content search agent and a news agent cover knowledge discovery and member services. The last two sit over the association management system’s own documentation, so staff can answer their own questions about the platform they work in daily.

The capability that made it possible

What stops an organization putting an assistant in front of a second department is rarely the technology. The second one needs a business case, a budget line and somebody to own the procurement, and at that point the idea quietly dies.

Here, a department with a body of content and a recurring question can have an assistant over it, scoped to that content alone, without asking anyone for a new contract. No procurement between agents, no API build, no connector work, no engineering team standing behind it. The ninth agent cost the same as the second, which is why there are nine and not one.

The results

MEASURETO DATE
Purpose-built assistants in production9
Documents processed6,767
Words processed35.2M
Questions in the busiest month1,006
Support tickets raised0

The number that matters is nine. Most organizations that buy an assistant end up with one, because the second has to be argued for. This society has agents for drug information, residency programs, advocacy, practice advancement, news, member search and events, plus two pointed at internal staff, and none of them required a separate purchase.

The drug information assistant alone has carried the majority of every question asked across the estate, which is where the corpus weight sits.

Three years, nine agents, zero support tickets. All nine run on a single entry-level subscription, so the platform decision was made once and every department since has been a configuration rather than a purchase.

Why it worked

Scope is per agent, not per account. Each assistant is grounded in its own content and nothing else, so the residency agent cannot answer a drug question badly. For clinical content, that separation is an accuracy requirement.

Adding one is a configuration. No contract, no procurement, no engineering ticket. A department with content and a recurring question can be answered this week.

It keeps working unattended. Three years with no support tickets, across agents owned by departments rather than by IT.

The newest agent is the most capable. It uses retrieval, web search and code execution together, built years after the first one and on the same subscription.

Frequently asked questions

What is a member services AI assistant for a professional association?

It is an assistant grounded only in the association’s own published material, so a member asks in plain language and gets an answer drawn from that content with the source cited. Here it is nine of them, each scoped to one department’s content rather than one assistant trained on everything the society publishes.

Why nine assistants instead of one?

Because scope is an accuracy decision. Drug reference material and residency application deadlines have nothing in common, and an assistant holding both will blend them at the moment it matters most. Scoping each assistant to a single body of content means the residency agent cannot reach the drug content at all.

Does it make clinical recommendations?

No. It reports what the society’s own monograph or position statement says and cites the source. It cannot make a clinical judgment for a pharmacist at a bedside, and restricting retrieval to published material keeps that boundary structural rather than instructional.

What does it cost to add a second or ninth assistant?

Nothing beyond the existing subscription. All nine here run on a single entry-level plan, with no new contract, budget line or procurement cycle for any of them. The test of a platform is what the ninth agent costs, not the first.

Can assistants be pointed at internal staff rather than members?

Yes, and two of these nine are. They sit over the association management system’s own documentation so staff can answer their own questions about the platform they work in daily. Internal agents need no brand review and no legal sign-off, which makes them the fastest way to prove the idea works.

How much content can one assistant handle?

Across this estate, 6,767 documents and 35.2 million words have been processed. The drug information assistant carries the majority of all questions asked and holds the largest share of that corpus.

Does each department need IT involvement?

No. The departments own these assistants rather than IT, and there is no API build, connector work or engineering team behind them. An assistant that needs regular rescuing gets quietly abandoned by the one person who set it up.

How much support has it needed?

Zero support tickets across three years and nine agents. Nobody at the society has had to contact us about any of them. For assistants owned by departments rather than by IT, that matters as much as answer quality, because one that needs regular rescuing gets quietly abandoned by the person who set it up.

Which department should go first?

The one with the busiest content, or an internal one. Drug information went first here and became the heaviest-used assistant in the estate. Two internal agents came later and are the cheapest to justify, because they face staff rather than members.

Can small assistants be worth running?

Yes. An events agent and a news agent here carry modest volume and cost nothing extra to run, which is as much the argument for the ninth assistant as it was for the second.

Figures from CustomGPT.ai product usage records. Shared anonymously at the customer’s request.

Ready to give each department its own answer service?

Count the departments, not the use cases. One assistant over everything is the intuitive design and the wrong one.

See other success stories