Applications
Every ticket triaged, every answer grounded in your own data
Planned. This suite is not available to install yet; the tables, agents, apps and connectors below are its design, not a running system.
Support queues grow faster than support teams. The same twenty questions arrive every day in slightly different words, the answer to "where is my order" lives in a different system from the ticket, the knowledge base was last updated when the product looked different, and the one person who knows the refund policy is on holiday.
The Customer Support Supercube installs a support operation where the agents do the looking-up, the drafting and the sorting, and people do the conversations. It seeds tables for customers, tickets, messages, knowledge articles, macros, products and known issues, returns and satisfaction. It declares agents that triage every incoming ticket, draft a reply grounded in the knowledge base and the customer's own records from the other supercubes, answer the routine cases outright where the company allows it, escalate the rest with context attached, keep the knowledge base current from resolved tickets, and review a sample of conversations for quality. It publishes apps for the queue, the customer view, the knowledge base and the quality dashboard.
After installation, a customer emails to ask where their order is. The Triage agent identifies the customer, finds the order in the Supply Chain Supercube, sees the parcel is delayed by the carrier, drafts a reply with the tracking link and the new date, and, because the company allows auto-reply on order status, sends it and closes the ticket. The next email is a complaint about a damaged item; the Triage agent classifies it, pulls the order and the photos, drafts a reply offering the replacement the policy allows, and puts it in front of a person with everything they need. That person spends their time on the complaint, not on finding the order.
Any company that answers customers, from a founder answering a shared inbox to a support team of twenty. Roles that use it are support agents (the human kind), the support lead, product and engineering people who receive escalations, and operations staff who process returns.
| Agent | Role | Owns | Harness preference |
|---|---|---|---|
| Triage | general | Classification, priority, customer identification, routing, context assembly | Claude Code |
| Responder | general | Drafted replies from the knowledge base and customer records; auto-replies where permitted | Claude Code, then pi |
| Knowledge Curator | general | Articles, macros, gaps found from tickets, retirements when the product changes | Claude Code |
| Escalation Coordinator | general | Bugs and product issues to engineering; known-issue tracking; customer updates when fixed | Claude Code, then Hermes |
| Quality Reviewer | analyst | Sampled conversation review, satisfaction trends, first-contact resolution, the weekly report | Claude Code |
| Table | Purpose | Key fields |
|---|---|---|
customers | Customer identity across channels, shared with Sales and Finance | name, emails, phones, account, tier, language |
tickets | One per conversation | customer, channel, subject, category, priority, status, assignee, opened, first_response, resolved |
messages | Every message in a ticket, inbound and outbound | ticket, direction, author, body, at, drafted_by |
categories | The taxonomy and the routing and auto-reply rules per category | name, parent, route_to, auto_reply_allowed, sla_hours |
articles | The knowledge base, versioned | title, body, category, audience, version, last_verified, source_tickets |
macros | Reusable reply templates | name, body, category, variables |
known_issues | Product problems in progress with affected customers | title, status, tracker_ref, affected_tickets, workaround, fixed_at |
returns | Returns, refunds and replacements | ticket, order, reason, decision, policy_rule, approver, status |
satisfaction | Survey responses | ticket, score, comment, at |
quality_reviews | Sampled reviews against the quality rubric | ticket, reviewer, scores, notes |
| Group | Target systems | Flows in | Flows out |
|---|---|---|---|
| Help desk | Zendesk, Freshdesk, Intercom, Help Scout | Tickets, messages, customers | Replies, status, tags, where the external desk is the record |
| Email and chat | Gmail, Outlook, WhatsApp Business, website chat | Inbound messages | Replies |
| Commerce and billing | Shopify, Stripe, via the Supply Chain and Finance Supercubes | Orders, shipments, refunds, subscriptions | Refunds and replacements on approval |
| Engineering | Jira, Linear | Issue status, fix versions | Escalated issues with context |
| Chat | Slack, Microsoft Teams | Internal answers to escalations | Escalations, daily queue summary, known-issue alerts |
Triage on arrival Trigger: a message arrives on any channel. Steps: the Triage agent identifies the customer, matches to an open ticket or opens one, classifies category and priority, checks for a known issue, assembles the customer's orders, invoices and history, and routes per the category rules. Checkpoint: none. Output: a ticket with context, in the right queue, within a minute.
Draft or auto-reply Trigger: a ticket is triaged. Steps: the Responder finds the relevant articles and macros, reads the customer's records, drafts a reply, and either sends it if the category allows auto-reply and confidence is above the threshold, or attaches it to the ticket for a person. Checkpoint: a person sends every reply outside the auto-reply categories. Output: routine questions answered immediately; everything else answered faster.
Return and refund Trigger: a ticket is classified as a return or refund request. Steps: the Responder checks the order, the return window and the policy rule, proposes a decision, and drafts the reply and the return label. Checkpoint: a person approves refunds above a value and every exception to policy. Output: decision recorded, refund or replacement raised in Supply Chain and Finance, customer informed.
Escalation to engineering Trigger: a ticket is classified as a bug or a person marks it. Steps: the Escalation Coordinator links it to an existing known issue or creates one, files the issue in the tracker with reproduction details, and tells the customer it is being looked at. When the tracker marks a fix released, it drafts an update to every affected customer. Checkpoint: engineering triages the issue; a person approves the fix announcement. Output: bugs reach engineering with context; customers hear when they are fixed.
Knowledge upkeep Trigger: routine, weekly. Steps: the Knowledge Curator finds resolved tickets whose answer had no article, drafts the article, flags articles unused for 90 days or contradicted by a release note, and proposes retirements. Checkpoint: the support lead approves new and retired articles. Output: a knowledge base that matches the product.
Quality review Trigger: routine, daily. Steps: the Quality Reviewer samples resolved conversations per person and per category, scores them against the rubric, notes coaching points, and rolls up the weekly report with satisfaction and resolution trends. Checkpoint: the support lead reviews before anything reaches an individual. Output: coaching notes and a report, never an automatic verdict on a person.
E-commerce brand. Order status, returns and damaged items dominate; auto-reply on order status alone removes a third of the queue. The returns desk enforces the return window and flags serial returners. Peak season volume is forecast from the Marketing calendar.
SaaS company. Tickets are how-to questions, bugs and billing; the Responder reads product docs and the customer's plan and usage. Escalations to Linear or Jira carry logs the customer attached. Known issues are surfaced to the Sales Supercube's account managers.
Subscription box service. Pauses, skips, address changes and delivery problems; the Responder acts on the subscription in Stripe within policy and confirms; the Triage agent groups tickets by delivery batch to spot a carrier problem early.
Utilities and telecoms reseller. Billing disputes and outage reports; the known-issues board becomes the outage board and the Escalation Coordinator drafts status updates by area. Regulatory complaint handling timescales are SLAs on the category.
Education provider. Students and parents ask about enrolment, fees and timetables; audiences on articles separate the two; the People and Finance Supercubes supply staff and fee records under strict scoping.
Local services business. Booking changes and quotes by WhatsApp and phone; the Responder drafts confirmations and reschedules against the Operations Supercube's job calendar.
Suites share tables and compose, so the ones next to this one are the ones it works with.
The operating rhythm of the company, run by agents, owned by the leadership team
Goals, KPIs, meeting cadence and decisions in one place, with agents that prepare every review and chase every action so leaders spend their time deciding, not collecting.
Books that close themselves, cash you can see, approvals that stay with people
Accounts payable, receivable, month-end close, cash forecasting and management reporting run by agents against your own ledger data, with every payment and every journal approved by a person.
A pipeline that works itself while your people talk to customers
Lead qualification, CRM hygiene, quoting, follow-up and forecasting handled by agents in your own customer tables, so salespeople sell and managers see a forecast they can trust.
