How Can AI Agents Use Zendesk Custom Fields? Reading and Writing Field Values
Zendesk custom fields hold order numbers, product categories, customer tiers and brands, and that data is often more useful than the message itself. Macha's Zendesk connector gives AI agents a tool that reads those values with their labels, so the agent can act on them without asking the customer.
Key takeaways
- Macha's Get Ticket Custom Fields tool lets AI agents read Zendesk custom fields such as order number, product category and customer tier, instead of asking the customer to type them.
- Zendesk's API docs recommend staying under 400 ticket fields per account, and Macha resolves each field ID to its label, returning values like "Bestellnummer: 013724827106".
- Macha caches the Zendesk field schema per connector, so field definitions are fetched once and later calls resolve labels from the cache.
- Macha's Zendesk connector can also write custom field values, checking dropdown options first, and asks for confirmation before any write in interactive chat.
- AI agents can use Zendesk custom fields for order lookup, language detection, tier-based routing, brand routing and form validation.
An AI agent can use Zendesk custom fields when it calls a tool that reads the ticket's field values and resolves each field ID to its label, which is what Macha's Get Ticket Custom Fields tool does. The agent then sees "Order Number: 013724827106" instead of a bare field ID, and can look up the order without asking the customer for it.
Why do AI agents miss custom field data?
Zendesk accounts can carry a lot of custom fields: Zendesk's own API docs recommend staying under 400 ticket fields per account for performance. Customers fill some through ticket forms; integrations, bots and triggers set others. Fields like "Order Number", "Product Category", "Customer Tier" and "Language" are critical for routing and resolution, but they live in the ticket's field schema, not in the message text.
When an AI agent only reads the ticket subject and description, it misses this data entirely. The customer sends "Where is my order?" and the agent has to ask for the order number, even though it's sitting right there in a custom field.
How does Macha read Zendesk custom fields?
Macha's Zendesk connector (17 tools in total) includes a dedicated Get Ticket Custom Fields tool. When called, it:
- Fetches the ticket's custom field values (the raw
{id, value}pairs from Zendesk's API) - Fetches the field schema (field definitions with titles, types and allowed values), which is cached per connector to avoid repeat API calls
- Joins them and returns
{id, title, value}for every field, so the agent sees "Bestellnummer: 013724827106" instead of "field_1900003089273: 013724827106"
The agent never needs field IDs; it acts on labeled values immediately.
Can the agent write custom fields back to Zendesk?
Yes. The same connector can update custom field values (dropdown, text and checkbox), and dropdown options are checked against the field's allowed values before the write. In interactive chat, Macha asks you to confirm before any write tool runs.
What can an agent do with custom fields?
- Order lookup: extract the order number from a custom field, call a shipping API, respond with status
- Language detection: read the language field, respond in the customer's language
- Tier-based routing: check the customer tier field, escalate VIP customers automatically
- Brand routing: read the brand field, apply brand-specific response templates
- Form validation: check required fields, ask the customer to fill in missing values
How do custom fields work with triggers?
In an autonomous workflow, the agent reads custom fields as part of its first action on a new ticket. A typical flow:
- Trigger fires on "New Ticket"
- Agent calls Get Ticket to read the subject, description and conversation
- Agent calls Get Ticket Custom Fields to read the order number, brand and language
- Agent uses the custom field data to decide what to do next: look up the order, route to a team, or respond directly
Because the field schema is cached per connector, later calls resolve labels from the cache.
Add AI agents to your Zendesk
Macha reads the ticket, drafts the reply and takes the action, inside the Zendesk you already run.
Intercom
Shopify
Stripe
Slack
Notion
Google Workspace
Confluence

