September’s Zendesk News roundup covers GPT-5 adoption, AI Agent instructions, Copilot upgrades, omnichannel routing with department spaces, generative search in Help Center, translation exclusions, security updates, 2SV rollout, and the deprecation of SunCo API wrappers.
Zendesk’s new trigger-based redaction automates the removal of personal data, solving the privacy risks of manual oversight. Combined with Redaction Suggestions from the ADPP add-on, this update enables safer workflows, fewer manual steps, and smarter data hygiene for customer support teams.
Not all tickets are equal. Some are simple and repetitive, others complex but strategic. Zendesk’s AI tools help map automation effort to business value — automating FAQs, guiding tasks, integrating live data, and supporting high-value human-led conversations where it counts most.
Zendesk’s Agent Copilot gets a major upgrade with Instructions—a new feature guiding agents through manual steps when automation isn’t viable. Combined with suggested replies and next actions, Copilot now supports hybrid workflows, streamlining both digital and physical processes.
Zendesk’s summer updates bring sweeping changes: a revamped Resolution platform, deep AI integrations, and major product rebrands. I reorganized my blog into 10 new categories and reflected on my content—strong in automation, but lacking coverage of analytics, QA, and workforce management.
Zendesk’s Help Center evolves with AI tools like Generative Search, Article Summaries, and Translation. Writing tools help teams expand, simplify, or rephrase content, while Knowledge Builder (announced at Relate 2025) promises future automation of knowledge creation from tickets.
Agent Copilot’s auto-assist only triggers on customer-created requests. If tickets are created via the Zendesk API or by agents (e.g. Employee Service), Copilot may not respond. The fix? Use the /requests.json endpoint to ensure proper behavior across email, messaging, and API-generated tickets.
Zendesk’s Custom Objects just got more practical with small but powerful updates: sortable views, renamable fields, auto-naming, event logs, and image support. These fill key gaps from the initial launch, making the feature far more usable in real-world workflows.
This article showcases a custom Zendesk AI Agent use case: enabling callback requests via Messaging. By combining Voice, API integrations, and phone validation, it bridges native gaps and lets customers request a call—fully automated, no agent needed to start.
Zendesk continues its summer rollout with major updates across AI, Messaging, Agent Workspace, Help Center, triggers, and platform tools. Highlights include generative email replies, context-aware workspaces, redaction via triggers, and API/UI overhauls. Omnichannel Routing evolves fast.
Zendesk’s generative replies for email allow AI Agents to send tailored, inline responses to customer emails using Help Center and custom knowledge sources. Unlike static article suggestions, these smart replies automate support while preserving tone, pacing, and fallback options for complex issues.
Zendesk Messaging now includes native wait time and queue position indicators, plus automated customer reminders for pending replies. These enhancements simplify setup, improve responsiveness, and help manage asynchronous conversations more effectively across all messaging channels.