The drafting agent
Using the notes and information you provide, it prepares draft reports, letters and summaries.
A structured draft for you to review and correct.
MEDICALCITY · The AI Factory for Healthcare
A digital team to prepare your everyday work.
Healthcare is our starting point. We design, develop and deploy multi-agent systems to help healthcare teams prepare documents, administrative processes and follow-up. Health, food, housing and mobility guide the needs to explore together. You set the scope and remain in control of decisions.
For healthcare teams
Care staff · Medical secretaries · Administrative teams · Healthcare facilities · Physicians
Four pillars of life
Prepare work around four everyday needs.
These are possible uses of digital support to scope with teams; uses related to food, housing and mobility remain to be defined and developed.
-
Health
Gather documents for a file and draft summaries from the information provided, for professionals to review.
-
Food
Draft a meal-request summary from information supplied by the team, for review before taking the next step.
-
Housing
Organise documents for a residential admission request or support in a person’s living environment, identify missing items and prepare follow-up.
-
Mobility
Draft a checklist of travel-related documents for the team to review and complete.
Teams specify sources, constraints and approvals. Agents prepare; the people responsible check, correct and decide what happens next.
One team, complementary roles
Draft. Prepare. Coordinate.
These examples of support are a starting point for your needs. We confirm available features, data access and connections to your tools together before setup.
The administrative agent
It helps gather the elements of a file, identify missing items and prepare documents for an administrative process.
A file to complete and check before submission.
The coordination agent
It helps organise tasks, draft follow-ups and highlight outstanding items for the team.
An overview of next actions for you to confirm.
From digital work to physical execution
Two infrastructures. Human responsibility.
The agent team is the AI Factory’s digital workforce. It draws on knowledge, working memory and authorised tools. In robotics projects, it can also prepare a task for an operator to review.
Digital infrastructure for multi-agent AI
Connect specialised agents to AI models, reference knowledge, memory and business software. Workflows organise document preparation, administrative processes and follow-up, with access and approvals defined for each project.
Research direction: “Multi-Agent AGI”, towards artificial general intelligence. A development ambition; the systems presented rely on specialised agents.
Infrastructure for robotic execution
Prepare robot connections, operator supervision and execution feedback. Each pilot must confirm hardware capabilities, permitted tasks, site conditions and ways to stop or take over the work.
Robotics: pilots in preparation. Drones: a longer-term development prospect. Scope, timing and service conditions remain to be confirmed for each project.
From a request to a supervised robotic task.
Proposed pilot scenario, to be validated in a trial: a team requests that small supplies be moved to a defined receiving point. This is a material-handling task, without a care procedure or physical contact with a person.
-
The agents prepare
Using the team’s request, they propose a task sheet specifying the items, route, recipient and missing information.
-
The operator authorises
The operator checks the information, equipment, route, execution conditions and stopping arrangements before deciding whether to start.
-
The robot executes under supervision
Within the pilot, the robot receives only the authorised task. The operator supervises and takes over when necessary.
-
The team confirms the result
The recipient checks receipt. Agents can prepare a report; the designated person checks the facts and approves follow-up.
An AI draft never triggers a physical action. If information is missing or a condition is not met, the task waits for clarification and a human decision.
An example of working together
One request. Several agents. Your approval.
Take an admission file for a healthcare facility: a summary to review, a list of documents to complete and suggested next steps. The agents share the preparation work; you check the result.
Example request
“Help me prepare this admission file: summarise the information provided, compare the documents against the required-document checklist I am supplying and suggest next steps.”
-
You set the scope
You specify the objective, the information that can be used, the reference checklist and who is responsible for reviewing the work.
-
The agents prepare together
Drafting structures the summary, administration lists the items to complete and coordination suggests follow-up actions.
-
You review and decide
You correct the content, fill in missing details and approve what can be shared. A draft does not mean an application has been accepted.
People remain responsible
Support with clear boundaries.
Your professional decisions
Medical decisions, signatures and approvals remain with authorised professionals.
Your review
AI suggestions may contain errors or omissions. You compare drafts with the information supplied, check the facts and adapt documents before using them.
An agreed scope
Permitted tasks, necessary data, access rules and approval steps are defined with your team before use.
Start with a specific task
Which need should we explore with your team?
Health, food, housing or mobility: let’s start with a specific task in your daily work. The AI Factory defines sources, roles and approvals with you for the support to build. Any proposed physical task requires a separate pilot scope.