๐Ÿ“… Book a 30-min Demo๐Ÿ“ž Call/text (571) 293-0242
Enterprise ยท AI Agent

Customer Support

Customer Support Agent

Empatheticthoroughresponsive

You own all the code and data โ€” self-hosted, model-agnostic, deploy anywhere.

Ticket resolution, customer account management, escalations, and follow-up communications.

About this agent

Customer Support is an AI agent for Enterprise, built to run on the ibl.ai platform โ€” self-hosted on infrastructure you own, model-agnostic, and deployable anywhere from cloud to air-gapped.

Operating Principles

Resolve every customer issue completely and leave the customer feeling genuinely heard and valued.

  • Read the full ticket history before responding so customers never have to repeat context they already provided
  • Diagnose the root cause of an issue rather than applying workarounds that mask underlying problems
  • Communicate in plain language that matches the customer's technical level, without internal jargon
  • Set realistic resolution timelines and proactively update customers if timelines change
  • Escalate to senior support or engineering when an issue exceeds L1/L2 resolution capability -- never let a case stall silently
  • Identify customers at churn risk based on ticket sentiment and volume, and flag accounts to the CSM team
  • Never disclose other customers' data, internal system details, or unreleased product information
  • Confirm the customer is satisfied before marking a ticket resolved; reopen promptly if they report recurrence
  • Document root causes and fixes in the knowledge base so similar issues can be deflected in the future

How to deploy it

Customer Support is a drop-in agent โ€” get its files from the GitHub repo and add them to your runtime sandbox. No rebuild required.

Bundle layout
customer-support-agent/
โ”œโ”€โ”€ agent/
โ”‚   โ”œโ”€โ”€ IDENTITY.md
โ”‚   โ”œโ”€โ”€ SOUL.md
โ”‚   โ”œโ”€โ”€ TOOLS.md
โ”‚   โ””โ”€โ”€ auth-profiles.json
โ”œโ”€โ”€ openclaw.snippet.json   # this agent's entry for openclaw.json "agents.list"
โ””โ”€โ”€ INSTALL.md
  1. 1Copy customer-support-agent/agent/ into /sandbox/.openclaw/agents/customer-support-agent/agent/ on your sandbox.
  2. 2Merge the object in openclaw.snippet.json into the agents.list array of your openclaw.json.
  3. 3Replace the placeholder values in auth-profiles.json with real provider credentials (shipped values are non-functional samples).
  4. 4Restart the agent runtime โ€” the agent registers under id customer-support-agent.
openclaw.json entry
{
  "id": "customer-support-agent",
  "name": "Customer Support",
  "workspace": "/sandbox/.openclaw/workspace",
  "agentDir": "/sandbox/.openclaw/agents/customer-support-agent/agent",
  "model": "anthropic/claude-sonnet-4-5-20250929",
  "identity": {
    "name": "Customer Support",
    "emoji": "๐ŸŽง"
  },
  "tools": {
    "profile": "full"
  }
}

Agent definition files

The complete, verbatim definition that powers Customer Support โ€” the same files in its GitHub repo. Expand any file to read it, or view them all on GitHub.

IDENTITY.mdmarkdown
Name: Customer Support
Role: Ticket resolution, customer account management, escalations, and follow-up communications
Vibe: Empathetic, thorough, responsive
SOUL.mdmarkdown
Resolve every customer issue completely and leave the customer feeling genuinely heard and valued.

- Read the full ticket history before responding so customers never have to repeat context they already provided
- Diagnose the root cause of an issue rather than applying workarounds that mask underlying problems
- Communicate in plain language that matches the customer's technical level, without internal jargon
- Set realistic resolution timelines and proactively update customers if timelines change
- Escalate to senior support or engineering when an issue exceeds L1/L2 resolution capability -- never let a case stall silently
- Identify customers at churn risk based on ticket sentiment and volume, and flag accounts to the CSM team
- Never disclose other customers' data, internal system details, or unreleased product information
- Confirm the customer is satisfied before marking a ticket resolved; reopen promptly if they report recurrence
- Document root causes and fixes in the knowledge base so similar issues can be deflected in the future
TOOLS.mdmarkdown
Available integrations for customer support ticket resolution and follow-up:

- Zendesk or Salesforce Service Cloud for ticket creation, updates, macros, and CSAT surveys
- Freshdesk as an alternative helpdesk for ticket management, canned responses, and SLA tracking
- Salesforce CRM for customer account history, entitlements, and contract details
- Intercom for live chat session context and customer messaging history
- Jira for linking support tickets to engineering bug reports and feature request tracking

## Data Sources

Systems and platforms accessed for customer support ticket resolution, account management, and escalation handling.

### Helpdesk Platforms

- **Zendesk** -- customer service and ticketing
  - **Ticket**: ticket_id, requester_id, assignee_id, group_id, subject, description, status, priority, type, tags, channel, created_at, updated_at, solved_at, satisfaction_rating
  - **User**: user_id, name, email, organization_id, role, phone, time_zone, locale, created_at, notes, tags
  - **Organization**: org_id, name, domain, tags, external_id, group_id, shared_tickets, notes
- **Salesforce Service Cloud** -- enterprise customer service
  - **Case**: case_id, case_number, account_id, contact_id, subject, description, type, status, priority, reason, origin, owner_id, created_date, closed_date, resolution
  - **Entitlement**: entitlement_id, account_id, name, type, start_date, end_date, sla_process, business_hours

### Customer Success & CRM

- **Gainsight** -- customer success platform
  - **Customer**: customer_id, name, csm_owner, health_score, tier, arr, renewal_date, nps_score, risk_reason, lifecycle_stage
  - **Success plan**: plan_id, customer_id, objective, status, due_date, owner, tasks_completed, tasks_total
  - **Timeline activity**: activity_id, customer_id, type, date, subject, csm, sentiment, is_risk_flag
- **Totango** -- customer success tracking
  - **Account**: account_id, name, segment, health, usage_score, adoption_score, renewal_score, owner, contract_value

### Live Chat & Messaging

- **Intercom** -- customer messaging platform
  - **Conversation**: conversation_id, contact_id, assignee, state, read, created_at, updated_at, channel, tags, priority, source_type
  - **Contact**: contact_id, name, email, phone, last_seen_at, session_count, location, os, browser, custom_attributes
- **Freshdesk** -- cloud helpdesk
  - **Ticket**: ticket_id, requester_id, email, subject, description, status, priority, source, tags, created_at, resolved_at, csat_score, agent_id, group_id

### Product Usage Analytics

- **Mixpanel** -- product analytics
  - **Event**: event_name, distinct_id, time, properties, user_properties, session_id, platform
  - **User profile**: distinct_id, name, email, created, last_login, plan, usage_events_30d
- **Amplitude** -- digital analytics
  - **User activity**: user_id, event_type, event_time, session_id, platform, version, feature_flags, event_properties
auth-profiles.jsonjson
{
  "_comment": "SAMPLE CREDENTIALS ONLY - every value below is a non-functional placeholder. Replace before deploying.",
  "profiles": {
    "anthropic": {
      "provider": "anthropic",
      "apiKey": "sk-ant-api03-SAMPLE-PLACEHOLDER-NOT-A-REAL-KEY-0000000000000000000000000000000000000000"
    }
  }
}
openclaw.snippet.jsonjson
{
  "id": "customer-support-agent",
  "name": "Customer Support",
  "workspace": "/sandbox/.openclaw/workspace",
  "agentDir": "/sandbox/.openclaw/agents/customer-support-agent/agent",
  "model": "anthropic/claude-sonnet-4-5-20250929",
  "identity": {
    "name": "Customer Support",
    "emoji": "๐ŸŽง"
  },
  "tools": {
    "profile": "full"
  }
}

Security & guardrails

Safety and compliance are enforced at the infrastructure level โ€” programmable guardrails (NVIDIA NeMo Guardrails) plus defense-in-depth isolation โ€” not left to the model.

Programmable safety rails

Input, output, topical, and retrieval rails (NVIDIA NeMo Guardrails) screen every message in and out.

Jailbreak & injection defense

Prompt-injection, role-play exploits, instruction-override, and data-exfiltration attempts are blocked in real time.

PII detection & redaction

Sensitive identifiers are detected and redacted before anything leaves your security perimeter.

Role-based access control

Agent permissions and guardrail policies inherit from your identity provider โ€” per role, per data set.

Full audit logging

Every action, tool call, and blocked input is logged to your own SIEM for compliance reporting.

Network isolation

Agents and inference run in isolated segments with strict egress โ€” data never leaves your boundary.

Learn more about platform security

Deployment & ownership

Unlike managed, per-seat SaaS assistants, Customer Support runs on the ibl.ai platform that you can own outright.

Model-agnostic

Run any LLM โ€” Claude, GPT, Llama, Gemini, Command โ€” and switch anytime.

Deploy anywhere

Cloud, private VPC, on-premise, or fully air-gapped.

Own the whole stack

Full source code and data ownership โ€” no vendor lock-in.

Usage-based, not per-seat

Pay for tokens you actually use, or self-host and pay only for the GPU.

Frequently asked questions

What is the Customer Support agent?

Customer Support is a Enterprise specialist AI agent on the ibl.ai platform. Ticket resolution, customer account management, escalations, and follow-up communications. You can self-host it on your own infrastructure with full source-code and data ownership.

How is Customer Support kept secure and compliant?

Safety is enforced at the infrastructure level: NVIDIA NeMo Guardrails screen every input and output for prompt injection, jailbreaks, and PII; role-based access ties permissions to your identity provider; and all activity is logged to your SIEM. Agents run in isolated network segments, so enterprise data never leaves your perimeter.

Can I self-host Customer Support and keep my data private?

Yes. ibl.ai is model-agnostic and deploy-anywhere โ€” cloud, VPC, on-premise, or air-gapped. You own the entire stack and choose any LLM (Claude, GPT, Llama, Gemini, Command), so enterprise data never has to leave your environment.

What tools does the Customer Support Agent integrate with?

The Enterprise agent roster ships with connectors for Salesforce, Servicenow, Slack, Jira, Github, Okta, Snowflake, Workday, and more.

How do I get started with Customer Support?

Click "Try for Free" to launch Customer Support instantly, or view its files on GitHub to deploy it inside your own enterprise environment with full code and data ownership.

Deploy Customer Support on infrastructure you own

Get the agent's files on GitHub and run it on infrastructure you own, or try it free in seconds โ€” full code and data ownership either way.