Mental Health

Persona

Role: Full-stack developer at a behavioral health practice management company (80 employees) serving independent clinicians and group practices.

Each practice is onboarded as a separate tenant, keeping patient assessment data, treatment plans, and clinical notes fully isolated. The platform must support multiple assessment instruments (PHQ-9, GAD-7, etc.) and track treatment progress over time.

Business Problem

Mental health clinicians spend excessive time on administrative tasks -- hand-scoring assessments, manually updating treatment plans, and transcribing session notes into disconnected systems. This scenario builds a clinical workflow platform where standardized assessments feed directly into treatment plans, and session documentation captures progress against treatment goals in a structured format.

Four-Step Application

This scenario works best as a four-step, human-in-the-loop application. The existing object model already gives this scenario a strong delivery backbone through Assessment, TreatmentPlan, and Session.

• Mission metric focus: better patient experience, lower administrative burden, and higher care quality.
• Human + AI pattern: Each step combines structured workflow data with chat assistance, background generation, document understanding, and accessible interaction patterns when they improve the experience.

Step 1. Capture demand and context

• Goal: Make it easy for the user to start the Mental Health journey with complete, trusted context.
• Required data: Assessment context such as type, score, date, and clinician.
• AI support: Use chat to guide intake, generate clearer prompts, create accessible summaries, and assist with voice or vision-led capture when a form alone is not the best experience. EAI can support structured intake, chat workflows, and document-centred capture today; richer native multimodal capture may still need workflow extensions or connected services.
• Business impact: Improve completion rate, reduce first-touch effort, and raise customer or staff confidence in the UX from the very first interaction.
• EAI delivery: Model the intake as tenant-isolated object types and resources, then use actions, chat workflows, and document indexing or classification to keep the initial record complete and usable.

Step 2. Prepare the decision

• Goal: Turn the captured context into the next best action for Mental Health without forcing the human reviewer to assemble the case manually.
• Required data: Assessment state and history; TreatmentPlan fields such as goals, interventions, reviewDate, and status.
• AI support: Run background summarisation, extraction, classification, recommendation drafting, and answer generation so a reviewer sees a prepared case instead of raw fragments. EAI delivers the structured records and AI workflow hooks for this today; specialised scoring engines, external rules, or advanced reasoning controls may still need integration work.
• Business impact: Reduce cycle time, improve quality and consistency, and protect the mission-critical metric before the case moves into execution.
• EAI delivery: Link records across the scenario, persist decision state as resources, and use workflow actions plus chat assistance to keep humans in control while AI prepares the work.

Step 3. Execute and collaborate

• Goal: Coordinate the actual work, handoffs, approvals, and user updates needed to deliver the service or outcome.
• Required data: TreatmentPlan actions such as activatePlan; Session fields such as date, duration, notes, and nextSteps.
• AI support: Draft replies, produce work packets, monitor exceptions in the background, and surface the next action for each operator. EAI can orchestrate tenant-isolated records, actions, chats, and document workflows today; deeper system-to-system automation may require additional connectors or workflow capability.
• Business impact: Increase operator productivity, reduce rework across handoffs, and improve service consistency across the application journey.
• EAI delivery: Use linked object types, actions, resource updates, and workflow-triggered AI assistance so the team can execute in one model instead of splitting work across disconnected tools.

Step 4. Resolve, explain, and improve

• Goal: Close the loop with a clear outcome, an understandable explanation, and feedback that improves the next case.
• Required data: final status, outcome, audit history, and follow-up signals across Assessment, TreatmentPlan, and Session.
• AI support: Generate outcome summaries, customer-friendly answers, compliance-ready notes, management insights, and accessible follow-up content. EAI can store outcome records and support answer generation today, while richer proactive agents, advanced analytics, or channel-specific accessibility features may need additional product capability.
• Business impact: Increase trust, quality, and measurable business value through better patient experience, lower administrative burden, and higher care quality.
• EAI delivery: Keep the full audit trail in structured resources, use AI workflows to explain outcomes, and feed the resulting signals into future product, service, and operational improvement work.

EAI Platform Support By Step

EAI provides the safe service boundary for Mental Health through Object Types, tenant-scoped resources, document processing, chat workflows, and CLI verification. For this scenario, the main records are Assessment, TreatmentPlan, and Session.

Process step	What EAI provides	Calling pattern
Step 1. Capture demand and context	Tenant-scoped intake resources for Assessment context such as type, score, date, and clinician. Object Type validation, starter forms, optional document intake, and chat-guided capture keep the first record complete.	Define fields in src/eai.config/object-types.ts, run eai types validate and eai types seed, create initial Assessment records with useResources('Assessment') or eai resources create Assessment, and keep browser calls behind /api/eai/....
Step 2. Prepare the decision	Linked resource queries over Assessment state and history; TreatmentPlan fields such as goals, interventions, reviewDate, and status. Search, schema checks, document classification or RAG indexing, and chat summaries turn raw context into a prepared decision.	Use useResources('Assessment') list/query/search patterns, verify shape with eai resources schema, use useDocuments().upload/classify/ragIndex, eai docs upload, eai docs classify, and eai docs index where supporting material exists, and send decision-support prompts through useChat(workflowId, 'chat') or eai chat send.
Step 3. Execute and collaborate	Resource updates and actions for TreatmentPlan actions such as activatePlan; Session fields such as date, duration, notes, and nextSteps. Status changes, assignments, notes, generated work packets, and chat support keep humans in control during execution.	Model actions in the Object Type code, call client.resources.executeAction(type, id, action) or the app hook equivalent, update records through the app service layer, and verify with eai resources get/list/query.
Step 4. Resolve, explain, and improve	Outcome resources for final status, outcome, audit history, and follow-up signals across Assessment, TreatmentPlan, and Session. Audit-friendly links, indexed final documents, reporting snapshots, and answer generation make the result explainable and reusable.	Persist outcomes as resources, index final material with eai docs index or useDocuments().ragIndex, send explanation prompts with useChat or eai chat stream, and use eai resources aggregate/search for reporting checks.

Prompt, Code, And Service Pattern Mapping

The Object Type code example on this page is the implementation contract for the EAI platform services. eai-gofer should read that code as the source of truth for which resource, document, and chat calls belong in the app.

Use this prompt shape when asking eai-gofer or another coding agent to implement the scenario:

Use the EAI App Template. Model Mental Health with Object Types for Assessment, TreatmentPlan, Session. Use useResources for records and actions, useDocuments for uploads/classification/RAG where documents appear, useChat for workflow assistance, and verify with eai types/resources/docs/chat commands. Use eai publicapi only when no named command covers the required platform call.

Scenario artifact	How it maps to EAI service calls
Four-step process	Step 1 becomes resource creation, Step 2 becomes resource query/search plus optional document or chat preparation, Step 3 becomes resource update/action calls, and Step 4 becomes outcome persistence plus explanation/reporting calls.
Object Type definitions	eai types validate, eai types seed, and eai resources schema make the model available and checkable before UI work starts.
Properties and indexes	Fields become useResources payloads, filters, list views, and eai resources create/list/query/search checks. Indexed fields should support lookup and triage, not duplicate canonical records.
Links between Object Types	Relationships become linked-resource UI, timeline context, and audit trails that app code loads through resource queries rather than separate bespoke stores.
Actions and status fields	Workflow buttons and operator transitions call resource action/update helpers, then verify state with eai resources get/list/query.
Document and chat prompts	Prompts should call the platform documents and chat patterns: useDocuments().upload/classify/ragIndex, eai docs upload, eai docs classify, and eai docs index for documents, and useChat, eai chat send, or eai chat stream for conversational assistance.

Object Types

Name	Key Properties	Links	Actions
Assessment	type (select: PHQ-9, GAD-7, PCL-5, AUDIT, custom), score (number), date (date), clinician (text), interpretation (text)	one-to-many → TreatmentPlan	scoreAssessment
TreatmentPlan	goals (text), interventions (text), reviewDate (date), status (select: draft, active, completed, revised)	many-to-one → Assessment, one-to-many → Session	activatePlan
Session	date (date), duration (number), notes (text), nextSteps (text), moodRating (number)	many-to-one → TreatmentPlan	completeSession

CLI Workflow

1. Scaffold the project

   eai init mental-health

2. Authenticate and pull environment

   eai login
   eai env pull --include-secrets

   If you are an external developer, see [Configuration](/docs/configuration) for login and local environment setup.

3. Define your Object Types

   Create the Assessment, TreatmentPlan, and Session types in src/eai.config/object-types.ts (see code example below).

4. Validate the type definitions

   eai types validate

   Tenant: mental-health
   ✔ Assessment — 5 props, 1 link, 1 action
   ✔ TreatmentPlan — 4 props, 2 links, 1 action
   ✔ Session — 5 props, 1 link, 1 action
   
   ✔ All Object Types are valid

5. Seed types to the platform

   eai types seed

6. Create a sample assessment and treatment plan

   eai resources create Assessment --data '{"type": "PHQ-9", "score": 14, "date": "2026-03-01", "clinician": "Dr. Emily Park", "interpretation": "Moderately severe depression"}'
   
   eai resources create TreatmentPlan --data '{"goals": "Reduce PHQ-9 score below 10 within 8 weeks; establish consistent sleep hygiene", "interventions": "CBT weekly sessions; behavioral activation; sleep diary", "reviewDate": "2026-04-26", "status": "draft"}'

7. Start local development

   eai dev

Code Example

// src/eai.config/object-types.ts
export const objectTypes = {
  'mental-health': [
    {
      name: 'Assessment',
      displayName: 'Assessment',
      description: 'A standardized clinical assessment instrument with scored results',
      properties: [
        {
          name: 'type', type: 'select' as const, required: true,
          options: [
            { label: 'PHQ-9 (Depression)', value: 'PHQ-9' },
            { label: 'GAD-7 (Anxiety)', value: 'GAD-7' },
            { label: 'PCL-5 (PTSD)', value: 'PCL-5' },
            { label: 'AUDIT (Alcohol Use)', value: 'AUDIT' },
            { label: 'Custom', value: 'custom' },
          ],
        },
        { name: 'score', type: 'number' as const, required: true },
        { name: 'date', type: 'date' as const, required: true },
        { name: 'clinician', type: 'text' as const, required: true, indexed: true },
        { name: 'interpretation', type: 'text' as const, required: false },
      ],
      linkTypes: [
        { name: 'treatmentPlans', targetObjectType: 'TreatmentPlan', cardinality: 'one-to-many' as const },
      ],
      actions: [
        {
          name: 'scoreAssessment',
          displayName: 'Score Assessment',
          description: 'Calculate the total score and generate clinical interpretation',
          inputs: [
            { name: 'responses', type: 'text' as const, required: true },
            { name: 'type', type: 'select' as const, required: true },
          ],
        },
      ],
      status: 'published' as const,
    },
    {
      name: 'TreatmentPlan',
      displayName: 'Treatment Plan',
      description: 'A structured treatment plan with goals and intervention strategies',
      properties: [
        { name: 'goals', type: 'text' as const, required: true },
        { name: 'interventions', type: 'text' as const, required: true },
        { name: 'reviewDate', type: 'date' as const, required: true },
        {
          name: 'status', type: 'select' as const, required: true,
          defaultValue: 'draft',
          options: [
            { label: 'Draft', value: 'draft' },
            { label: 'Active', value: 'active' },
            { label: 'Completed', value: 'completed' },
            { label: 'Revised', value: 'revised' },
          ],
        },
      ],
      linkTypes: [
        { name: 'assessment', targetObjectType: 'Assessment', cardinality: 'many-to-one' as const },
        { name: 'sessions', targetObjectType: 'Session', cardinality: 'one-to-many' as const },
      ],
      actions: [
        {
          name: 'activatePlan',
          displayName: 'Activate Plan',
          description: 'Move the treatment plan from draft to active status after clinical review',
          inputs: [
            { name: 'reviewNotes', type: 'text' as const, required: false },
          ],
        },
      ],
      status: 'published' as const,
    },
    {
      name: 'Session',
      displayName: 'Session',
      description: 'A therapy session record with clinical notes and progress tracking',
      properties: [
        { name: 'date', type: 'date' as const, required: true },
        { name: 'duration', type: 'number' as const, required: true },
        { name: 'notes', type: 'text' as const, required: true },
        { name: 'nextSteps', type: 'text' as const, required: false },
        { name: 'moodRating', type: 'number' as const, required: false },
      ],
      linkTypes: [
        { name: 'treatmentPlan', targetObjectType: 'TreatmentPlan', cardinality: 'many-to-one' as const },
      ],
      actions: [
        {
          name: 'completeSession',
          displayName: 'Complete Session',
          description: 'Finalize session notes and record next steps for the patient',
          inputs: [
            { name: 'notes', type: 'text' as const, required: true },
            { name: 'nextSteps', type: 'text' as const, required: false },
            { name: 'moodRating', type: 'number' as const, required: false },
          ],
        },
      ],
      status: 'published' as const,
    },
  ],
};

Key Takeaways

• Assessment-driven treatment: Assessments link directly to treatment plans, ensuring that clinical goals are grounded in validated measurement instruments like PHQ-9 and GAD-7.
• Progress tracking: The moodRating field on Session combined with periodic reassessment scores enables clinicians to visualize treatment effectiveness over time.
• Practice-level isolation: Each practice operates in its own tenant, so a solo clinician and a 20-provider group practice both use the same codebase with complete data separation.
• Structured clinical workflow: The progression from Assessment to TreatmentPlan to Session mirrors the real clinical workflow, reducing the gap between how clinicians think and how the software works.