WEBINAR:
Less time, fewer tokens, better effects
The official CKEditor support for AI coding agents
CKEditor AI Chat appears as a sidebar or overlay directly inside the editor. It reads your document as context, so you can ask questions about your own content and request changes without explaining what you're working on first. You can also start from a blank page and generate content from scratch, drafting and shaping it without leaving the editor.
Understanding the entirety of the document editor context, it edits in the same HTML the editor uses. Anything it produces arrives fully formatted, with no cleanup needed afterwards.
Operational Summary – Second Half of 2025
This report summarizes customer support performance during the second half of 2025. It focuses on ticket volumes, response efficiency and common issue categories, based on internal operational data across all support channels.
The information below should be treated as an overview of observed trends rather than a detailed performance evaluation.
The diagram outlines our internal customer support process, showing how incoming requests are handled across multiple support tiers based on complexity.
Customer inquiries are initially managed by Tier 1: Frontline Support, which is responsible for triage and resolution of common issues. More complex cases are escalated to Tier 2: Technical Support, where deeper technical investigation is performed.
High-impact or unresolved issues are handled by Tier 3: Escalation Team, which coordinates with internal experts as required. Specialist Teams support Tier 2 and Tier 3 by providing domain-specific expertise, while typically remaining non-customer-facing.
The process is designed to allow flexible movement between tiers, supporting efficient resolution and appropriate escalation when needed.
During the reporting period, the support team processed 184,600 tickets, representing an increase of 11% compared to the previous period. Ticket volume peaked in September and gradually stabilized towards the end of the year.
The increase was primarily driven by onboarding-related questions and product configuration requests.
| Channel | Share of Tickets | Change vs. Previous Period | Avg. First Response Time |
|---|---|---|---|
| 54% | -3% | 3.1 hours | |
| Live Chat | 31% | +5% | 1.2 hours |
| In-App Support | 15% | -2% | 2.4 hours |
Email remained the dominant support channel, although live chat usage continued to increase, particularly among larger accounts.
Average response and resolution times showed minor improvement compared to earlier in the year.
More complex cases, especially those related to integrations, required additional follow-up and were not consistently resolved within standard timeframes. While faster response times were generally appreciated, qualitative feedback indicates that communication consistency played an equally important role in overall customer perception.
"Faster responses were helpful, but consistency in follow-up communication had a bigger impact on our overall experience."
— Enterprise customer, post-resolution survey
The most frequently reported issues were:
Billing-related requests declined slightly, while integration-related inquiries increased towards the end of the period.
Customer satisfaction was measured through post-resolution surveys. The overall response rate remained stable throughout the reporting period.
Feedback most often referenced response time and clarity of follow-up communication as areas for improvement, particularly in cases involving multiple handovers or escalations.
Internal review identified several operational areas that may require further attention:
While these issues did not materially impact aggregate performance metrics, they were visible in individual case handling and customer feedback.
"The issue was eventually resolved, although it was not always clear who was responsible for the case during escalation."
— Key account feedback, quarterly review
Overall support performance remained within expected operational ranges. Most key indicators were stable, with moderate improvements observed in response efficiency. At the same time, the data suggests that further improvements in communication clarity and escalation handling could positively impact customer experience in future reporting periods.
Open the demo in fullscreen to comfortably explore the editor and its features.
Read more about the AI capabilities in the documentation.
Check the source code for this demo.
Start from a blank document and think out loud. Ask for different approaches, draft a section, react to it, refine, all in one place. Since the AI assistant works on the actual output, good ideas become formatted content immediately.
Every time you leave your editor to use a standalone AI tool, it costs losing your flow. You copy text out, generate something, copy it back, reformat it, and try to remember where you were. CKEditor AI Chat eliminates that loop. The conversational AI assistant is already available where you create and format content . You ask, you get a ready-to-insert response, you keep writing.
AI output is a starting point, not a final draft. Track Changes feature integration means every AI suggestion is visible, attributable and reversible. Accept what works, reject what doesn't. The AI writes in the same HTML format the editor uses, so accepted suggestions carry all the formatting — bold, headings, lists — without a need for manual cleanup.
AI Chat is a plugin. Your job is to configure it, not to build it from scratch. You are not building a chat UI, and you are not building the layer that turns AI output into correctly formatted, reviewable editor content neither. The chat panel, conversation threading, history, context passing, and the suggestion-and-review flow are all handled.
It works in all editor types, including multi-root editors, and multiple editors sharing a single context. Whatever your architecture, you don't need to rethink it to add an AI chat for content creation.
CKEditor AI Chat supports the models your team already uses. You connect your own API key. No vendor lock-in. You choose the model, control the cost, and swap providers without rebuilding your integration. If a better model ships next month, you update a config value.
Need a custom or fine-tuned model? The on-premises deployment lets you connect any LLM - including private models running entirely within your own infrastructure.
You can extend system prompts, the available chat actions, and the behavior of the assistant within your application. Serving a specific vertical such as legal, technical, or support content? Configure the assistant to match it, so content authors get a focused tool and you ship a product that fits your use case.
CKEditor AI Chat is a part of an industry-tested system that was built to create
quality content. It is full of features aimed at making content creation easier and
consistent. AI integrates into that system rather than being bolted on top of it, and
this difference shows up in a few specific ways.
The conversational AI assistant is embedded in the editor. Your writers never leave their workspace. Ideation, drafting, editing, and reviewing all happen in one environment.
CKEditor AI generates native HTML output. Bold stays bold. Tables stay structured. Lists stay formatted. You accept a suggestion and it lands in the document exactly as intended — no cleanup, no conversion layer.
Track Changes feature support means AI output enters your document as a reviewable suggestion, not a blind paste. Authors can see what the AI contributed, evaluate it, and approve or reject it. That's a meaningful difference for organizations that care about content quality and accountability.
On-premises deployment for full data sovereignty, SOC 2 Type 2 certification, and GDPR compliance — and you have an AI content workflow automation tool that meets enterprise security requirements without compromising on capability.
CKEditor AI Chat is part of a broader CKEditor AI features suite that includes AI Review for automated document review and AI Quick Actions for inline, single-shot text operations. You can use them independently or together, depending on how your writers work.
A conversational AI assistant is a chat-based interface that maintains context across multiple exchanges with an AI model. You ask a question, get a response, ask a follow-up, and refine — all in a single thread the AI remembers. Unlike single-turn tools, a conversational assistant lets you iterate without re-explaining your context every time.
CKEditor AI Chat is embedded inside your editor. It reads your document as context, generates changes as suggestions you review before accepting, and outputs native HTML — not markdown. Standalone tools like ChatGPT or Claude require you to copy content out, generate text, paste it back, and reformat it. AI Chat removes that entire loop.
Yes. CKEditor AI Chat generates HTML output natively. Your bold text, headings, tables, and lists survive the AI's response intact. When you accept a suggestion, it lands in your document with full formatting. No reformatting required.
Yes. With the Track Changes plugin enabled, every AI-generated document edit appears as a reviewable suggestion. You accept or reject each change individually. Nothing applies to your document automatically. You stay in full editorial control.
Yes. CKEditor AI Chat connects to OpenAI, Anthropic, and Google Gemini via your own API key. You pick the model — GPT-4.1, Claude Sonnet 4, Gemini 2.5 Pro, or any other supported option — and you can swap providers without rebuilding your integration. No vendor lock-in. With MCP support you can connect any custom LLM.
Chat history is saved per conversation thread and is visible only to the author. Conversations are private by default — other document collaborators cannot see your AI Chat history. You can pin threads, rename them, and search across your history at any time.
CKEditor AI Chat supports OpenAI (GPT-4.1, GPT-5, GPT-5 Mini), Anthropic (Claude Sonnet 4, Claude 3.5 Haiku), and Google Gemini (2.5 Pro, 2.5 Flash). You connect your own API key and choose the model that fits your use case and cost requirements.