Give your teams back the time to focus on what matters most.
Agents work across the services and systems involved in someone’s care, retrieving information, updating records and following things up. Each one acts under its own permissions, and comes back to a person whenever judgement is needed.
Clarity and coordination, out of the noise.
An agent is given the systems involved in a piece of work as tools it can use: retrieving information, updating records, triggering actions. It is told what the job is, not how to do it, and it works until the job is done or it needs somebody to make a decision.
One date moves, and everything else has to follow.
A discharge date changes, and transport, the care package, the equipment and the ward all need to know. Each sits in a different organisation’s system, so today it depends on somebody noticing and ringing round. Agents can ensure every service holding a piece of that discharge is told the moment the date moves, and that anything which no longer fits is put back in front of a person while there is still time to change it.
- No criteria to reside set to 21 AugAcute trust
- Reablement can start 24 AugReablement
First visit 09:00, answered in eleven minutes
- No transport available on 24 AugBlockedPatient transport
No morning capacity until 25 Aug
- Decided to ask reablement to moveDecision
Only 25 Aug works for both
- Reablement agreed 25 Aug, first visit 11:00Reablement
- Transport booked for the morning of 25 AugPatient transport
- Discharge plan updated and the ward toldCompletedAcute trust
Reason recorded: no transport on 24 Aug
Avoid duplicating work.
Nobody books a duplicate visit on purpose. It happens because teams schedule independently and neither can see the other’s diary, so nothing surfaces it until the second visit turns up. Agents can ensure a clash like this is spotted before either team sets off, and that any change is agreed by both teams and the resident before anything moves.
- Two teams booked to the same addressScheduling
A therapy session and a support call, ninety minutes apart on Tuesday morning
- Proposed moving therapy to 11:00Decision
The carer is already there at 11:00
- Therapy can move to 11:00Therapy team
Same clinician, no change to the session
- Support call stays at 11:00Homecare provider
- Resident agreed to the changeScheduling
- Both schedules updatedCompletedScheduling
One journey saved, both teams told
An agent is just another principal.
This does not need a new governance model, and inventing one would be a bad sign. An agent authenticates, holds permissions and leaves an audit trail exactly as an application or a member of staff does.
An agent is its own principal
It holds its own credentials and never borrows a member of staff's login. That is what lets you tell the discharge agent's actions apart from Jane's, and withdraw its access without touching anybody's account.
Permissions belong to the data owner
The organisation that holds a record decides what an agent may see and change, down to the field. Not us, and not whoever happens to be running the agent.
Everything it does is on the record
Every read, write and action is captured against the agent that did it, the task it was for and the time it happened, in the same audit trail as a person's activity.
It escalates rather than decides
When an agent meets a constraint it cannot satisfy, it goes back to a person rather than picking an answer. Judgement stays where it belongs.
Reversible work only
Agents handle coordination a person can look at, question and undo. Anything irreversible, or properly a clinical decision, needs a person.
A team can switch it off
Each agent has a narrow, defined job, and withdrawing its permission takes effect on its next call.
Anything that amounts to a clinical decision brings clinical risk obligations with it, and that is not what agents are for. They work on the coordination around a decision, where getting it wrong costs a wasted journey rather than harm.
Here’s where we’re up to.
Agents are in active development, and we are building them in the open. Rather than announcing a finished product, we are designing and testing alongside the services that would use them, and the people in their care.
That means starting on narrow, low-stakes coordination work, with the teams involved shaping what an agent is pointed at, what it may touch and when it has to stop and ask. Trust in something new is earned that way rather than claimed up front.
If there is a piece of coordination costing your team real time, we would like to hear about it.
Talk to us about agentsFrequently asked questions
- Not as something you can buy yet. Agents are in development and available for early trials and co-development, so a service can point one at a narrow piece of coordination and shape it with us. The useful conversation now is which piece of coordination is costing your team the most time.
What is your team spending its time coordinating?
Discover how agents could integrate into your workflows and support better outcomes and happier teams.