# Care Coordination

This guide covers how Amigo supports ongoing care coordination across multiple patient encounters. Unlike a single scheduling interaction, care coordination involves repeated touchpoints over weeks or months across voice and text channels, with the agent building context over time and personalizing each interaction.

## The Challenge

Patients with chronic conditions or complex care plans interact with the health system frequently. Each interaction generates information that should inform the next one. In practice, this context is often lost: different staff members handle different calls, notes are incomplete, and patients have to repeat themselves.

Effective care coordination requires continuity. The agent must remember what happened in prior conversations - whether they occurred over phone or text - track progress against care plan goals, and adapt its approach based on what has worked (or not worked) for each patient.

## Memory Across Encounters

Amigo's [memory system](https://docs.amigo.ai/agent/memory) tracks patient context across every interaction through four layers: raw transcripts (L0), extracted facts and preferences (L1), synthesized per-patient models (L2), and a global user model (L3) that gives the agent instant access to the most relevant patient context at the start of every call. Each conversation adds to the patient's record, and the agent draws on that history in future calls.

**What the agent remembers:**

* Prior conversation summaries and outcomes
* Patient-reported barriers and preferences
* Medication adherence patterns
* Scheduled and completed appointments
* Escalation history and care team instructions

**How memory improves coordination:**

On a first call, the agent follows a standard check-in script. By the third call, it knows that this patient prefers morning calls, has trouble remembering evening medications, and gets anxious about lab results. The agent adjusts its timing, reminders, and tone accordingly.

Over longer time horizons, the platform identifies patterns that are not visible in any single interaction. For example, a patient's medication adherence dips every few weeks. Individual calls show nothing unusual, but the pattern over months reveals a cycle tied to work travel. The agent can address this pattern in future conversations.

## World Model Unifies Data Sources

The world model brings together information from multiple systems into a single view that the agent can access during a conversation.

| Data Source         | What It Provides                                 |
| ------------------- | ------------------------------------------------ |
| EHR                 | Diagnoses, medications, lab results, care plan   |
| Voice conversations | Patient-reported symptoms, concerns, preferences |
| Manual entry        | Care team notes, social work assessments         |
| Scheduling system   | Appointment history, upcoming visits             |
| Connected devices   | Vitals, weight trends, activity data             |

During a call, the agent does not need to ask the patient questions that the system already has answers to. If the patient's weight has been trending up based on connected scale data, the agent can bring that into the conversation directly rather than asking the patient to report it.

This also prevents conflicting information. If the EHR shows a medication was discontinued but the patient mentions still taking it, the agent can flag the discrepancy for the care team.

## Personalized Interactions

Each interaction is shaped by what the platform knows about the patient. Personalization happens across several dimensions:

**Communication style**: Some patients want detailed explanations. Others want brief, direct updates. The agent learns this from prior interactions and adapts.

**Timing and cadence**: The platform adjusts call frequency and timing based on patient response patterns. A patient who consistently misses afternoon calls gets moved to morning scheduling.

**Content focus**: The agent prioritizes the topics most relevant to each patient's current situation. A patient who just had a medication change gets focused adherence support. A patient approaching a care milestone gets progress reinforcement.

**Barrier awareness**: If a patient has reported transportation issues, financial concerns, or caregiver availability problems, the agent factors these into its recommendations and referrals.

## Operator Escalation

Not every situation is within the agent's scope. When clinical complexity exceeds the agent's confidence level, it escalates to a human operator.

**When the agent escalates:**

* Patient reports new or worsening symptoms that require clinical assessment
* The patient's situation has changed significantly since the last care team update (new diagnosis, hospitalization, family crisis)
* The patient explicitly requests to speak with a nurse or provider
* The agent's confidence in its response falls below the configured threshold

**How escalation works:**

The agent does not simply transfer the call and disappear. It prepares a handoff summary for the operator that includes:

* Current conversation context and patient concern
* Relevant history from prior interactions
* Data from the world model (recent labs, vitals, medication changes)
* Reason for escalation

The operator receives this context before connecting with the patient, which means the patient does not have to start from scratch. After the operator resolves the issue, the outcome is recorded and available to the agent for future interactions.

## What This Looks Like Over Time

In a care coordination deployment, the agent handles routine touchpoints (medication check-ins, appointment reminders, care plan reinforcement) while care managers focus on patients who need clinical judgment.

As the system accumulates interaction history, it becomes more effective. Early calls follow standard protocols. Later calls are personalized based on months of patient-specific data. The testing and evaluation framework tracks whether this personalization produces better outcomes: improved adherence rates, fewer missed appointments, earlier identification of deterioration.

{% hint style="info" %}
For details on how to verify clinical quality in care coordination workflows, see the [Clinical Verification](https://docs.amigo.ai/use-cases/use-cases/clinical-verification) guide. For the memory system's layered architecture, see [Memory](https://docs.amigo.ai/agent/memory).
{% endhint %}