Impact Measurement

Persona

Role: Data systems developer at an education non-profit running 12 programs across four regions.

Program managers collect outcome data in spreadsheets that use different formats and definitions. Impact reports are assembled quarterly by a single analyst who spends weeks standardizing data before any analysis can begin. The board and funders want real-time dashboards, but the underlying data infrastructure does not support it.

Business Problem

Every program defines and measures success differently. One program tracks graduation rates, another tracks employment placement, and a third tracks literacy scores -- all in incompatible formats. When the CEO needs to report aggregate impact to the board, the data team manually harmonizes metrics across programs. This scenario builds an impact measurement platform that defines programs with standardized metrics, collects indicator data at regular intervals, and produces structured reports that can feed dashboards and funder communications.

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 Program, ImpactMetric, and Report.

• Mission metric focus: greater mission reach, stronger stewardship, and better reporting 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 Impact Measurement journey with complete, trusted context.
• Required data: Program context such as name, description, budget, and startDate.
• 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 Impact Measurement without forcing the human reviewer to assemble the case manually.
• Required data: Program state and history; ImpactMetric fields such as indicator, target, actual, and period.
• 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: ImpactMetric execution state; Report fields such as period, narrative, status, and publishedDate.
• 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 Program, ImpactMetric, and Report.
• 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 greater mission reach, stronger stewardship, and better reporting 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 Impact Measurement through Object Types, tenant-scoped resources, document processing, chat workflows, and CLI verification. For this scenario, the main records are Program, ImpactMetric, and Report.

Process step	What EAI provides	Calling pattern
Step 1. Capture demand and context	Tenant-scoped intake resources for Program context such as name, description, budget, and startDate. 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 Program records with useResources('Program') or eai resources create Program, and keep browser calls behind /api/eai/....
Step 2. Prepare the decision	Linked resource queries over Program state and history; ImpactMetric fields such as indicator, target, actual, and period. Search, schema checks, document classification or RAG indexing, and chat summaries turn raw context into a prepared decision.	Use useResources('Program') 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 ImpactMetric execution state; Report fields such as period, narrative, status, and publishedDate. 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 Program, ImpactMetric, and Report. 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 Impact Measurement with Object Types for Program, ImpactMetric, Report. 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
Program	name (text), description (text), budget (number), startDate (date), status (select: planning, active, completed, suspended)	one-to-many → ImpactMetric, one-to-many → Report	--
ImpactMetric	indicator (text), target (number), actual (number), period (text), unit (text)	many-to-one → Program	--
Report	period (text), narrative (text), status (select: draft, review, published), publishedDate (date)	many-to-one → Program	publishReport

CLI Workflow

1. Scaffold the project

   eai init impact-measurement

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 Program, ImpactMetric, and Report types in src/eai.config/object-types.ts (see code example below).

4. Validate the type definitions

   eai types validate

   Tenant: impact-measurement
   ✔ Program — 4 props, 2 links, 0 actions
   ✔ ImpactMetric — 5 props, 1 link, 0 actions
   ✔ Report — 4 props, 1 link, 1 action
   
   ✔ All Object Types are valid

5. Seed types to the platform

   eai types seed

6. Create sample resources

   eai resources create Program --data '{"name": "Youth STEM Academy", "description": "After-school STEM education for grades 6-8", "budget": 150000, "startDate": "2025-01-15", "status": "active"}'

7. Start local development

   eai dev

Code Example

// src/eai.config/object-types.ts
export const objectTypes = {
  'impact-measurement': [
    {
      name: 'Program',
      displayName: 'Program',
      description: 'A program operated by the organization',
      properties: [
        { name: 'name', type: 'text' as const, required: true, indexed: true },
        { name: 'description', type: 'text' as const, required: true },
        { name: 'budget', type: 'number' as const, required: false },
        { name: 'startDate', type: 'date' as const, required: true, indexed: true },
        { name: 'status', type: 'select' as const, required: true, defaultValue: 'planning', options: [
          { label: 'Planning', value: 'planning' },
          { label: 'Active', value: 'active' },
          { label: 'Completed', value: 'completed' },
          { label: 'Suspended', value: 'suspended' },
        ]},
      ],
      linkTypes: [
        { name: 'impactMetrics', targetObjectType: 'ImpactMetric', cardinality: 'one-to-many' as const },
        { name: 'reports', targetObjectType: 'Report', cardinality: 'one-to-many' as const },
      ],
      actions: [],
      status: 'published' as const,
    },
    {
      name: 'ImpactMetric',
      displayName: 'Impact Metric',
      description: 'A quantitative impact measurement for a program',
      properties: [
        { name: 'indicator', type: 'text' as const, required: true, indexed: true },
        { name: 'target', type: 'number' as const, required: true },
        { name: 'actual', type: 'number' as const, required: false },
        { name: 'period', type: 'text' as const, required: true },
        { name: 'unit', type: 'text' as const, required: true },
      ],
      linkTypes: [
        { name: 'program', targetObjectType: 'Program', cardinality: 'many-to-one' as const },
      ],
      actions: [],
      status: 'published' as const,
    },
    {
      name: 'Report',
      displayName: 'Report',
      description: 'A periodic impact report for a program',
      properties: [
        { name: 'period', type: 'text' as const, required: true },
        { name: 'narrative', type: 'text' as const, required: true },
        { name: 'publishedDate', type: 'date' as const, required: false },
        { name: 'status', type: 'select' as const, required: true, defaultValue: 'draft', options: [
          { label: 'Draft', value: 'draft' },
          { label: 'Review', value: 'review' },
          { label: 'Published', value: 'published' },
        ]},
      ],
      linkTypes: [
        { name: 'program', targetObjectType: 'Program', cardinality: 'many-to-one' as const },
      ],
      actions: [
        {
          name: 'publishReport',
          displayName: 'Publish Report',
          description: 'Publish a reviewed impact report for stakeholder distribution',
          requiredRole: 'tenant-staff',
          validationRules: { requiredFields: ['narrative'], requiredStatus: 'review' },
          sideEffects: [
            { type: 'set_field', field: 'status', value: 'published' },
            { type: 'set_timestamp', field: 'publishedDate' },
          ],
        },
      ],
      status: 'published' as const,
    },
  ],
};

Key Takeaways

• Standardized metrics: A consistent structure for impact indicators across all programs eliminates the data harmonization bottleneck that delays reporting.
• Target vs. actual tracking: Every metric records both the target and actual values, making it immediately clear which programs are on track and which need attention.
• Report lifecycle: Impact reports move through draft, review, and published stages, ensuring quality control before stakeholder distribution.
• Program-level aggregation: Linking metrics and reports to programs enables both program-specific deep dives and organization-wide impact summaries.