Hannah & Elena Client Skill

Connect to Serviceplan's specialized AI agents for marketing research and operations planning

What is This Skill?

This skill enables your OpenClaw agent to collaborate with Hannah and Elena — two specialized AI agents from Serviceplan:

• Hannah — Marketing Research Specialist
• "What is actually true?"
• Market analysis, consumer insights, competitive research, audience profiling
• Premium data sources: Statista, GWI, DataForSEO, Apify, and more
• Elena — Operations & Project Orchestrator
• "What is actually doable?"
• Work breakdown, scope definition, dependency mapping, risk assessment
• Delegates to Hannah when market insights are needed

Important: What AI Agents CAN vs CANNOT Do

AI Agents CAN:

• Configure API keys in environment variables
• Send requests to Hannah/Elena via API
• Send requests to Hannah/Elena via email
• Parse and integrate responses
• Handle multi-agent coordination

• Sign up for Hannah/Elena access → Human must contact Serviceplan
• Get API keys → Human must request from admin at sumike.ai
• Set up email addresses → Human needs valid email account

Available Access Channels

Channel 1: API (Task-Based)

Both Hannah and Elena expose task-based REST APIs:

• Hannah API: https://hannah.sumike.ai/v1
• Elena API: https://elena.sumike.ai/v1

• GET /v1/coworkers - List available agents
• POST /v1/tasks - Create a new task for an agent
• GET /v1/tasks/{taskId} - Check task status
• GET /v1/tasks/{taskId}/result - Get completed task result

• Asynchronous task processing (2-10 minutes typical completion time)
• Task status tracking
• Result retrieval when complete
• 60 requests/minute rate limit per agent

• After creating a task: Wait 2-3 minutes before checking status
• If still processing: Wait another 2-3 minutes before checking again
• Total task time: Typically 2-10 minutes depending on complexity
• DO NOT poll continuously - tasks need time to complete

Channel 2: Email

Both agents can be reached via email:

• Hannah Email: [email protected]
• Elena Email: [email protected]

• Natural language requests in email body
• Attachment support (PPT, XLS, DOC, PDF)
• CC/threading support — they understand context
• Replies within minutes
• Deliverables as email attachments

Quick Start Guide

Step 1: Get Your API Keys

Human must do this:

• Contact Serviceplan at sumike.ai
• Request access to Hannah and/or Elena
• Receive API keys (format: sk-sumike-xxxxx)

Step 2: Configure Environment Variables

AI Agent can do this:

# Hannah API key
export HANNAH_API_KEY=sk-sumike-your-hannah-key-here
export HANNAH_API_BASE_URL=https://hannah.sumike.ai

# Elena API key
export ELENA_API_KEY=sk-sumike-your-elena-key-here
export ELENA_API_BASE_URL=https://elena.sumike.ai

# Optional: Email addresses (if different from defaults)
export [email protected]
export [email protected]

Or add to your .env file:

HANNAH_API_KEY=sk-sumike-xxxxx
ELENA_API_KEY=sk-sumike-yyyyy

Step 3: Use the Tools

Once configured, your agent has access to these tools:

• list_coworkers - List available agents (Hannah, Elena)
• hannah_create_task - Create research task for Hannah
• elena_create_task - Create planning task for Elena
• check_task_status - Check status of a task
• get_task_result - Get result of completed task
• hannah_email - Send email request to Hannah
• elena_email - Send email request to Elena

Usage Examples

Example 1: Market Research with Hannah (API)

Agent: "I need to research the German EV market. Use Hannah."

<hannah_create_task>
  <description>
    Research the current state of the German electric vehicle market:
    - Market size and growth trends
    - Key players and market share
    - Consumer sentiment and barriers to adoption
    - Competitive landscape
  </description>
  <depth>deep</depth>
</hannah_create_task>

Result: Task created (task_xyz789).

⏱️ WAIT 2-3 MINUTES before checking status.

[Agent waits 3 minutes]

<check_task_status taskId="task_xyz789">

Result: Task completed! Hannah orchestrated Statista, GWI, and DataForSEO sub-agents.

<get_task_result taskId="task_xyz789">

Result: Comprehensive research report with sources and confidence levels.

Example 2: Project Planning with Elena (API)

Agent: "Need to break down a Q2 campaign launch. Use Elena."

<elena_create_task>
  <description>
    Break down a Q2 product campaign launch into workstreams:
    - Product: New premium EV model
    - Target: German market, affluent early adopters
    - Timeline: Launch April 1st
    - Budget: €500k

    Provide detailed work breakdown with dependencies and risks.
  </description>
</elena_create_task>

Result: Task created (task_abc456).

⏱️ WAIT 2-3 MINUTES - Elena may delegate to Hannah for market research.

[Agent waits 3 minutes]

<check_task_status taskId="task_abc456">

Result: Completed! Elena delegated to Hannah for market data, then integrated findings.

<get_task_result taskId="task_abc456">

Result: Work breakdown with dependencies, risks, and resource needs informed by research.

Example 3: Email-Based Research Request

Agent: "Send research request to Hannah via email"

<hannah_email>
  <to>[email protected]</to>
  <subject>EV Market Research Request</subject>
  <body>
    Hi Hannah,

    I need comprehensive research on the German EV market for Q2 2026:
    1. Market size and growth projections
    2. Competitive landscape analysis
    3. Consumer sentiment (barriers and motivators)

    Please provide sources and confidence levels for all findings.

    Thanks!
  </body>
</hannah_email>

Result: Email sent. Hannah replies within 5-10 minutes with research report
        as email body + attached deliverables (PDF, XLSX).

Example 4: Elena Delegates to Hannah

Agent: "Elena, plan the EV campaign launch"

<elena_create_task>
  <description>
    Create project plan for German EV campaign launch:
    - Product: Premium EV sedan
    - Launch date: April 1, 2026
    - Target audience: Affluent professionals, 35-55
    - Budget: €500k
  </description>
</elena_create_task>

Workflow:
1. Elena receives task
2. Elena identifies missing market context
3. Elena delegates research to Hannah (internal A2A)
4. Hannah executes research using premium data sources
5. Elena integrates findings into operational plan
6. Elena delivers: Work breakdown + dependencies + risk matrix + deliverables

Result: Comprehensive project plan informed by real market data

Agent Personalities & Best Practices

Working with Hannah

Character:

• Analytical, reflective, opinionated
• Values research integrity over speed
• Calls out weak data honestly
• "What is actually true?"

• Be specific about research questions
• Specify required depth (quick lookup vs deep research)
• Ask for source attribution
• Expect critical assessment, not just data dumps

"Hannah, I need to validate whether 'sustainability' is a real
purchase driver for EVs in Germany, or if it's post-rationalized.
Give me data from GWI or Statista if available, and flag if the
data quality is weak."

Working with Elena

Character:

• Direct, pragmatic, grounded
• Protects delivery through realism
• Challenges vague goals
• "What is actually doable?"

• Provide clear goals and constraints upfront
• Specify dependencies you know about
• Ask for risk assessment
• Expect honest pushback on unrealistic plans

"Elena, break down a 6-week campaign launch:
- Product: New EV model
- Launch: April 1st
- Constraint: No dedicated PM resource
- Concern: Unclear target audience

Flag dependencies and risks."

Multi-Agent Coordination

Pattern 1: Sequential (Research → Planning)

Step 1: Agent requests research from Hannah
Step 2: Agent receives research findings
Step 3: Agent requests operational plan from Elena
Step 4: Agent integrates both outputs

Pattern 2: Elena Auto-Delegates

Step 1: Agent requests project plan from Elena
Step 2: Elena detects missing market context
Step 3: Elena automatically delegates to Hannah
Step 4: Hannah returns research
Step 5: Elena integrates and delivers complete plan

Pattern 3: Parallel Consultation

Step 1: Agent sends same context to both Hannah and Elena
Step 2: Hannah returns "What is true?" perspective
Step 3: Elena returns "What is doable?" perspective
Step 4: Agent synthesizes both viewpoints

Cost & Rate Limits

API Rate Limits

• Hannah: 60 requests/minute
• Elena: 60 requests/minute
• Max concurrent requests: 5 per agent

Sokosumi Sub-Agent Costs

When Hannah or Elena orchestrate Sokosumi sub-agents:

• Statista: ~120 credits
• GWI: ~80 credits
• DataForSEO: ~60 credits
• Apify: ~40 credits

⏱️ Timing Guidance

CRITICAL for AI Agents:

API Task Processing

• After creating task: Wait at least 2-3 minutes before checking status
• If still processing: Wait another 2-3 minutes before checking again
• Total task time: Typically 2-10 minutes depending on complexity
• DO NOT: Poll continuously every few seconds - tasks need time to complete

• Initial processing and context loading (30 seconds)
• Research execution with sub-agents (2-10 minutes - MAIN WAIT TIME)
• Result synthesis and formatting (30 seconds - 1 minute)

Email Requests

• Typical response time: 5-10 minutes
• Complex research: Up to 15 minutes
• Expect email reply with attachments

Task Status States

Available Tools

list_coworkers

List available agents (Hannah, Elena).

Parameters: None

Returns:

• coworkers: Array of available agents with capabilities and status
• count: Number of agents found

{
  "data": [
    {
      "id": "cow_hannah",
      "name": "Hannah Sumi",
      "role": "Marketing Research Specialist",
      "email": "[email protected]"
    },
    {
      "id": "cow_elena",
      "name": "Elena",
      "role": "Operations & Project Orchestrator",
      "email": "[email protected]"
    }
  ]
}

hannah_create_task

Create a research task for Hannah.

Parameters:

• name (required): Task title (max 120 chars)
• description (optional): Detailed task description with research questions
• status (optional): "DRAFT" | "READY" (default: "READY")

• taskId: Task identifier (e.g., "task_xyz789")
• status: Initial task status
• estimatedTime: "2-10 minutes"
• message: Includes timing guidance

elena_create_task

Create a planning task for Elena.

Parameters:

• name (required): Task title (max 120 chars)
• description (optional): Detailed planning requirements
• status (optional): "DRAFT" | "READY" (default: "READY")

• taskId: Task identifier
• status: Initial task status
• estimatedTime: "2-10 minutes"
• message: Includes timing guidance

check_task_status

Check the status of a task.

Parameters:

• taskId (required): Task ID from create_task

• status: "DRAFT" | "READY" | "IN_PROGRESS" | "COMPLETED" | "FAILED"
• hasResult: Whether result is available
• message: Status message with timing guidance

get_task_result

Get the result of a completed task.

Parameters:

• taskId (required): Task ID from create_task

• result: Task result data (research findings or operational plan)
• status: Task status (must be "COMPLETED")
• completedAt: Completion timestamp
• deliverables: Links to any generated files (PDF, XLSX, PPTX)

hannah_email

Send email request to Hannah.

Parameters:

• to (required): Email address (default: [email protected])
• subject (required): Email subject line
• body (required): Email body with request details
• cc (optional): CC addresses
• attachments (optional): Attachment file paths

• status: "sent"
• messageId: Email message ID
• estimatedResponse: Estimated response time

elena_email

Send email request to Elena.

Parameters:

• to (required): Email address (default: [email protected])
• subject (required): Email subject line
• body (required): Email body with request details
• cc (optional): CC addresses
• attachments (optional): Attachment file paths

• status: "sent"
• messageId: Email message ID
• estimatedResponse: Estimated response time

check_hannah_status

Check if Hannah is available.

Returns:

• available: true | false
• responseTime: Estimated response time
• message: Status message

check_elena_status

Check if Elena is available.

Returns:

• available: true | false
• responseTime: Estimated response time
• message: Status message

Error Handling

API Errors

Email Errors

Troubleshooting

"API key is missing"

Solution: Set HANNAH_API_KEY and/or ELENA_API_KEY in environment variables.

"Hannah/Elena not responding"

Solution:

• Check agent status using check_hannah_status or check_elena_status
• Verify API endpoint is correct
• Try alternative channel (API → Email or vice versa)

"Sokosumi credits exhausted"

Hannah/Elena will inform you:

"I need to use Statista for this research, which requires 120 credits.
Your current Sokosumi balance is 50 credits. Please add credits at
sokosumi.com to continue."

Solution: Add credits to your Sokosumi account (if using premium data sources)

"Rate limit exceeded"

Solution:

• Reduce request frequency (max 60/minute per agent)
• Use batch requests where possible
• Consider email channel for non-urgent requests

Integration Patterns

Pattern A: Research-First Workflow

1. Your agent identifies need for market data
2. Call hannah_research with specific questions
3. Wait for response (2-10 minutes)
4. Integrate findings into your agent's output
5. Optionally: Send to Elena for operational planning

Pattern B: Planning-First Workflow

1. Your agent receives project request
2. Call elena_plan with requirements
3. Elena auto-delegates research to Hannah if needed
4. Receive comprehensive plan with market context
5. Execute or refine based on deliverables

Pattern C: Parallel Advisory

1. Your agent faces strategic decision
2. Call hannah_research for market reality
3. Call elena_plan for operational feasibility
4. Compare responses: "What's true" vs "What's doable"
5. Make informed decision with both perspectives

Security & Privacy

API Keys

• API keys are scoped to specific agents (Hannah or Elena)
• Keys format: sk-sumike-xxxxx
• Maximum 5 active keys per contact
• Rotate keys every 90 days recommended

Data Handling

• Conversation history stored in PostgreSQL (isolated per agent)
• Research results cached for 30 days
• Email attachments stored in Azure File Share
• No data shared between Hannah and Elena without explicit delegation

Compliance

• GDPR compliant (data processing agreement available)
• SOC 2 Type II certified infrastructure
• Data residency: EU (Azure West Europe)

Advanced Configuration

Custom Endpoints

# Override default endpoints
export HANNAH_API_ENDPOINT=https://custom-hannah.your-domain.com/v1
export ELENA_API_ENDPOINT=https://custom-elena.your-domain.com/v1

Proxy Configuration

# Route through proxy
export HTTPS_PROXY=https://your-proxy.com:8080
export NO_PROXY=localhost,127.0.0.1

Timeout Settings

# Adjust timeouts (in seconds)
export HANNAH_TIMEOUT=300  # 5 minutes for research
export ELENA_TIMEOUT=180   # 3 minutes for planning

API Reference (Quick Reference)

Hannah API

Endpoint: https://hannah.sumike.ai/v1/chat/completions

Authentication: Authorization: Bearer sk-sumike-xxxxx

Request Body:

{
  "messages": [
    {"role": "user", "content": "Your research request here"}
  ],
  "stream": false
}

Response:

{
  "id": "msg_xxx",
  "choices": [
    {
      "message": {
        "role": "assistant",
        "content": "Research findings..."
      }
    }
  ]
}

Elena API

Endpoint: https://elena.sumike.ai/v1/chat/completions

Same format as Hannah API.

Resources

• Hannah & Elena Homepage: https://sumike.ai
• Serviceplan: https://www.serviceplan.com
• Sokosumi Marketplace: https://sokosumi.com
• Support: [email protected]

Summary for AI Agents

Quick Setup:

• Obtain API keys from Serviceplan (human task)
• Set HANNAH_API_KEY and ELENA_API_KEY in environment
• Use hannah_research for market research
• Use elena_plan for project planning
• Be patient — research tasks take 2-10 minutes
• Integrate responses into your agent's workflow

• Hannah validates ideas through research integrity ("What is true?")
• Elena protects delivery through realism ("What is doable?")
• Both agents can orchestrate Sokosumi sub-agents for premium data
• Elena auto-delegates to Hannah when market context is needed
• Support both API and email channels for flexibility

• Research depth impacts response time
• Set realistic timeouts (3-5 minutes minimum)
• Hannah and Elena are professional coworkers, not assistants
• They will push back on vague requests or weak assumptions
• Cost transparency — they inform you before consuming credits

Built by Serviceplan | Powered by Sokosumi

Professional AI coworkers for marketing research and operations planning