# Care Coordination Agents: Referrals and Transitions > Healthcare · AI Course · MED-8 > Source: https://ibl.ai/solutions/medical-healthcare/course/care-coordination-agents > Last updated: 2026-08-25 **Automate the handoffs where patients are most often lost — referral tracking, transition communication, and follow-up that reduces readmission.** ## The Short Answer **Care transitions are where patients are most often lost, and referral loops close far less often than organizations assume. ibl.ai runs coordination agents inside the health system where you own all the code and the data — so referral and transition records containing PHI stay within the covered entity and its BAAs.** On ibl.ai you own all the code and the data, run it model-agnostic across any LLM, and pay with no per-seat pricing — so you can deploy anywhere, from your own cloud to a fully air-gapped network. [Request Access](https://ibl.ai/contact) · [Explore Healthcare](https://ibl.ai/solutions/medical-healthcare) ## Course facts - **Level:** Intermediate - **Duration:** 5 hours across 8 modules - **Format:** Cohort workshop with workflow labs - **Modules:** 8 - **Catalog code:** MED-8 - **Frameworks covered:** CMS transitions of care, HIPAA, Information blocking rules, HL7 FHIR ## What is this course about? Transitions are the highest-risk moment in a care episode and the point where patients most often fall out of the system. This course covers referral loop closure, transition summaries the receiving clinician can actually use, post-discharge follow-up sequences, social determinants and resource navigation, and interoperability across organizations that do not share an EHR. ## Who is this course for? - Care coordination and case management staff - Population health teams - Transitions of care programs - Clinical operations leaders ### What do I need before starting? - Care coordination or case management experience - Familiarity with your referral workflow ## What will I be able to do afterwards? - Quantify where patients are lost in transitions - Close referral loops and detect the ones that stall - Produce transition summaries the receiving clinician can use - Design post-discharge follow-up that reduces readmission - Coordinate across organizations that do not share an EHR ## What does each module cover? ### Module 1 — Where are patients actually lost? Measuring loop closure and the transition points where patients disappear. _(45 min)_ **Objectives** - Measure referral loop closure rates - Identify the highest-loss transition points - Quantify the clinical consequence **Topics:** Loop closure measurement · Transition points · Loss quantification · Clinical consequence **Activity:** Measure loop closure for one referral type and identify where patients are lost. ### Module 2 — How do you close a referral loop? Tracking a referral through to a completed visit and a report back. _(50 min)_ **Objectives** - Track referrals through to completion - Detect stalls at each stage - Escalate before the patient is lost **Topics:** Referral tracking · Stage-level stall detection · Escalation · Report-back capture **Activity:** Build referral tracking with stall escalation for one specialty. ### Module 3 — What makes a transition summary usable? Summaries the receiving clinician reads, rather than a document dump. _(50 min)_ **Objectives** - Produce summaries a receiving clinician can use - Include what the receiver actually needs - Avoid the information dump that gets ignored **Topics:** Summary usability · Receiver needs · Information dumps · Format **Activity:** Produce transition summaries and have receiving clinicians rate their usability. ### Module 4 — How do you design post-discharge follow-up? Follow-up sequences timed and targeted to reduce readmission measurably. _(45 min)_ **Objectives** - Design follow-up timing and content - Target patients by readmission risk - Measure the readmission effect **Topics:** Follow-up timing · Risk targeting · Content design · Readmission measurement **Activity:** Design a follow-up sequence with a measurable readmission comparison. ### Module 5 — How do you handle social determinants? Resource navigation for the barriers that actually prevent follow-through. _(45 min)_ **Objectives** - Identify social barriers to follow-through - Match patients to available resources - Track whether the connection was made **Topics:** Barrier identification · Resource matching · Connection tracking · Resource currency **Activity:** Build resource matching for your service area and verify the resources exist. ### Module 6 — How do you coordinate across organizations? Interoperability with organizations that do not share your EHR. _(45 min)_ **Objectives** - Exchange information across organizational boundaries - Handle organizations without modern interfaces - Meet privacy requirements in exchange **Topics:** Cross-organization exchange · Legacy interfaces · Information blocking · Privacy in exchange **Activity:** Map information exchange with a referral partner outside your EHR. ### Module 7 — How do you measure the program? Loop closure and readmission as outcome measures rather than activity counts. _(40 min)_ **Objectives** - Define outcome measures for coordination - Distinguish activity from outcome - Report honestly including null results **Topics:** Outcome measures · Activity versus outcome · Comparison design · Honest reporting **Activity:** Design the measurement plan with a comparison condition. ### Module 8 — Building the loop-closure agent The lab module: an agent that escalates stalled referrals before patients are lost. _(50 min)_ **Objectives** - Build the loop-closure agent - Implement stage-level stall escalation - Measure closure rate improvement **Topics:** Agent build · Stall escalation · Closure measurement · Staff workflow **Activity:** Deploy the agent and measure loop closure against baseline. ## What is the capstone project? **Referral loop-closure agent with measured improvement.** Build a care coordination workflow with referral tracking and stall escalation, usable transition summaries rated by receiving clinicians, risk-targeted follow-up, verified resource matching, cross-organization exchange, and measured loop closure against baseline. _Deliverable:_ A deployed agent with before-and-after loop closure and readmission figures. ## How are learners assessed? - Loop closure measured against a real pre-deployment baseline - Transition summaries rated for usability by actual receiving clinicians - Resource matching verified — every resource must actually exist and accept referrals ## What ships with the course? - **Facilitator guide.** Session-by-session running order, discussion prompts, and the questions that reliably derail a room. - **Learner workbook.** Exercises, checklists, and the templates each module's activity produces. - **Hands-on lab environment.** A sandboxed ibl.ai deployment so exercises run against real agents, not screenshots. - **Assessment bank.** Scenario questions and rubric criteria mapped to each stated learning outcome. - **Source bibliography.** Every primary regulation and standard cited on this page, linked and dated. ## Which AI agents does this course use? - [Care Coordination Agent](https://ibl.ai/solutions/medical-healthcare/agent/care-coordination-agent) - [Patient Education Agent](https://ibl.ai/solutions/medical-healthcare/agent/patient-education-agent) - [Documentation Agent](https://ibl.ai/solutions/medical-healthcare/agent/documentation-agent) - [Quality Improvement Agent](https://ibl.ai/solutions/medical-healthcare/agent/quality-improvement-agent) ## Where does the course material come from? Every module is grounded in primary sources — the regulation, standard, or research itself, not a summary of it. Each was resolved at authoring time. - [Centers for Medicare and Medicaid Services](https://www.cms.gov/) — CMS. Transitions of care requirements and readmission programs. - [HL7 FHIR](https://www.hl7.org/fhir/) — HL7. The interoperability standard for cross-organization exchange. - [Agency for Healthcare Research and Quality](https://www.ahrq.gov/) — AHRQ. Transitions of care evidence and measurement methodology. - [HealthIT.gov](https://www.healthit.gov/) — ASTP/ONC. Information blocking rules and exchange requirements. ## Delivery notes Binding guidance for anyone preparing and delivering this course: - Module 1's loop closure measurement is usually a shock. Organizations assume closure rates far above reality, and the measurement is what motivates the rest of the course. - Module 5's resource verification matters. Referring a patient to a resource that no longer exists or does not accept their insurance is worse than not referring. - Module 3's usability rating must come from receiving clinicians, not the sending organization. Senders consistently overestimate how usable their summaries are. - Module 6 should acknowledge that many referral partners have no modern interface. Fax remains real and the workflow must handle it. - Coordinate with MED-5 — post-discharge patient education and coordination follow-up are the same touchpoint and should not be two separate contacts. ## Why run AI training on a platform you own? - **You own the course, not a licence to it.** Course content, learner data, and the platform run inside your perimeter — you own all the code and the data. - **Model-agnostic delivery.** Run the course's AI components on any LLM — Claude, GPT, Llama, Gemini, Command — and switch anytime. - **No per-seat training licences.** Usage-based or self-hosted, so cost tracks actual use rather than headcount. - **Deploy anywhere.** Cloud, private VPC, on-premise, or fully air-gapped — including for cohorts that cannot use public AI tools. ## Frequently asked questions ### What does the Care Coordination Agents: Referrals and Transitions course cover? Transitions are the highest-risk moment in a care episode and the point where patients most often fall out of the system. This course covers referral loop closure, transition summaries the receiving clinician can actually use, post-discharge follow-up sequences, social determinants and resource navigation, and interoperability across organizations that do not share an EHR. It runs 5 hours across 8 modules across 8 modules, at intermediate level, and closes with a capstone: Referral loop-closure agent with measured improvement. ### Who should take Care Coordination Agents: Referrals and Transitions? It is written for Care coordination and case management staff, Population health teams, Transitions of care programs, Clinical operations leaders. Prerequisites: Care coordination or case management experience; Familiarity with your referral workflow. ### Can we run this course on our own infrastructure? Yes. ibl.ai is model-agnostic and deploy-anywhere — cloud, private VPC, on-premise, or fully air-gapped — and you own all the code and the data. Cohort data, submissions, and any material learners upload stay inside your perimeter, which matters for healthcare teams that cannot send work to a public AI tool. ### How do we get access to Care Coordination Agents: Referrals and Transitions? Request access and we will set it up for your cohort — hosted by ibl.ai, or running against your own deployment. Tell us the group size and timing you need, and whether it should run inside your own perimeter. ### How much does AI training for healthcare cost on ibl.ai? There is no per-seat pricing — you pay for usage or self-host and pay only for the infrastructure, so a 5,000-person rollout does not cost 5,000 licences. 1.6M+ users across 400+ organizations run the platform this way, including NVIDIA, MIT, and Syracuse University. ## More Healthcare courses - [HIPAA-Compliant AI: PHI, BAAs, and Where the Data Lives](https://ibl.ai/solutions/medical-healthcare/course/hipaa-compliant-ai): What HIPAA actually requires of an AI deployment — the BAA analysis, Security Rule safeguards, minimum necessary, and the architecture that keeps PHI inside your boundary. - [Clinical Documentation with AI: Ambient Notes and Review](https://ibl.ai/solutions/medical-healthcare/course/clinical-documentation-with-ai): Deploy ambient documentation safely — accuracy in clinical language, the attestation requirement, note bloat, and measuring whether it returns clinician time. - [Medical Coding with AI: ICD-10, CPT, and Denial Prevention](https://ibl.ai/solutions/medical-healthcare/course/medical-coding-with-ai): AI-assisted coding that improves accuracy rather than just speed — code suggestion, documentation gap detection, denial prevention, and staying clear of upcoding. - [Prior Authorization Automation with AI Agents](https://ibl.ai/solutions/medical-healthcare/course/prior-authorization-automation): Compress the highest-friction administrative process in healthcare — payer requirement lookup, packet assembly, status tracking, and appeal drafting. - [Patient Education Agents: Health Literacy and Safety](https://ibl.ai/solutions/medical-healthcare/course/patient-education-agents): Patient-facing AI that explains conditions and discharge instructions safely — reading level, language access, scope boundaries, and symptom escalation. - [AI in Clinical Decision Support: Evidence, Limits, and Liability](https://ibl.ai/solutions/medical-healthcare/course/ai-clinical-decision-support): Deploy clinical decision support responsibly — evidence grounding, automation bias, transparency obligations, and where liability actually lands.