Changelog

We’ve improved the AI credit tracking system and released a new usage page to provide greater transparency and give you clearer, more accurate insight into where, when, and how your AI credits are being used.

You can access the new page by going to your account → Usage → AI credits .

From this page, you can:

• View usage as a chart or daily list
• Filter by date, agent, category, AI model, and channel
• Break down usage by agent, category, or model

• Audit usage logs

• Open related conversations from log entries
• Track fractional credit usage more accurately

Some older usage is shown as aggregated historical data, so detailed filters and logs are only available for usages after August 7.

This release improves transparency and reflects our ongoing effort to give you clearer, more accurate insight into how your AI credits are used

We’ve expanded our supported AI models with the latest releases from OpenAI, Anthropic, and Google:

• GPT-5.6 Sol, Terra, and Luna
• Claude Opus 5 and Sonnet 5
• Gemini 5.6 Flash

These new models give you more flexibility to balance response quality, speed, and cost based on your use case.

You can select them now from your agent’s AI settings. We recommend testing different models with your existing knowledge base and instructions to find the best fit for your workflows.

We’ve rebuilt Analytics to make it easier to understand performance, identify trends, and take action.

Analytics is now organized into three focused sections:

Chats

Track conversation volume and audience behavior with:

• New conversations
• Total, sent, and received messages
• Unique users
• New contacts
• Conversation channels for AI agents
• Open, resolved, and closed conversations
• Top countries and starting pages
• Engagement heatmaps showing the busiest days and hours

AI performance

Understand how effectively your AI handles conversations:

• Helpful and unhelpful rating percentages
• Deflection rate
• Escalation rate
• Total conversations escalated to humans
• AI credit usage

Human support

Measure the speed of your support team:

• First reply time
• Customer wait time
• First resolution time
• Final resolution time

A more actionable dashboard

The main dashboard now surfaces what needs attention immediately:

• Open conversations
• Conversations waiting for a human
• Unassigned conversations
• Unread conversations
• The oldest conversations requiring attention
• Knowledge base sources with errors or stalled processing
• A seven-day performance overview

We also rebuilt the reporting infrastructure behind Analytics, resulting in faster loading, more reliable historical data, and more consistent totals across charts and breakdowns.

Open your AI agent and visit Analytics to explore the new dashboard.

Starting today, you can connect your Chatling AI agent to Facebook Messenger. The same AI that powers your website chat will now answer DMs on your Facebook Page, around the clock, in any language you support.

• One click connection. Authorize once, pick the Page you want to connect, and you're live in under a minute.
• Real time replies. Incoming Messenger DMs are answered by your agent within seconds, day or night.
• Same brain, same knowledge. Your agent uses the exact same instructions, knowledge base, and actions you've already set up. No retraining, no duplicate configuration.
• Unified inbox. Every Messenger conversation lands in your Chatling Conversations dashboard right next to your chats from other channels. Reply manually whenever you want to take over or set up automatic handoff.

How to connect

Connecting your AI agent to Messenger is simple and effortless.

1) Open your AI agent dashboard.

2) Head to Deploy .

3) Click the Setup button for Messenger and follow the on-screen instructions to connect a page.

It’s as simple as that! Give it a try today and let us know your feedback.

Support is fastest when answers are already at your fingertips. So we built Copilot : an AI assistant that lives right inside the conversation view and helps you reply better and faster, without ever leaving the chat.

Only you see Copilot. It's your sidebar, scoped to the conversation you're working, so you can ask, draft, and refine in private before anything goes to the customer.

What you can do with Copilot

• Draft replies in one click - Ask Copilot to write the response, then hit Use draft to drop it straight into the composer.

• Grounded in your knowledge base - Copilot searches your docs and answers from them, so replies are accurate instead of guessed.
• Summarize long threads - Catch up on a back-and-forth conversation instantly before you jump in.
• Read intent & sentiment - Know what the customer actually wants and how they're feeling, at a glance.
• Translate on the fly - Understand and respond across languages without switching tools.

Polish your reply before you send it

Right from the composer, Copilot can rewrite your reply:

• Adjust tone to be professional, friendly, empathetic, casual, or concise
• Expand for more detail and warmth
• Shorten to keep it tight
• Fix grammar without changing your meaning
• Rephrase for a cleaner, more natural read

Getting started

Copilot is available to all users on the Standard , Ultimate , and Plus plans.

To learn more about Copilot and how you can use it, refer to our documentation .

We’ve added three new frontier AI models to Chatling:

1. GPT-5.5 : OpenAI's new flagship. Stronger reasoning and instruction-following than GPT-5.4, with noticeably fewer hallucinations on knowledge-base grounded answers. Best pick when you need the most accurate, reliable responses and action calling for complex support flows.
2. Claude Opus 4.8 : Anthropic's most capable model yet. Excels at long-context understanding (great for large knowledge bases), nuanced tone, and following detailed brand/persona instructions. Choose this when conversation quality, safety, and handling of long or ambiguous queries matter most.
3. Gemini 3.5 Flash : The speed option. Near-instant responses, while improving on Gemini 3 Flash in reasoning and multilingual quality.

All three models are now available on Chatling paid plans.

We shipped three improvements that to improve your live chat experience.

1. Canned responses

Create a library of saved replies your team can drop into any conversation in one click from Settings → Canned Responses .

To insert canned responses when chatting, click the bookmark icon in the reply composer and choose a response.

2. Teams

Group agents into teams so you can route conversations, scope visibility, and keep large support orgs tidy. Manage teams under Settings → Teams .

3. Quick actions

Press / in the reply box to bring up a searchable menu of everything you can do without leaving the keyboard:

• Insert a canned response
• Attach a file
• Add an emoji
• Switch between reply and private note
• Pause or resume your AI agent
• Send message
• Clear the current draft

You can now connect Notion as a knowledge source for your AI agents. Sync your existing Notion pages directly into your knowledge base - no more copy-pasting content or maintaining duplicate docs.

To get started, head to your knowledge base and select Notion as a source. Connect your Notion account, select the pages you want to include, and Chatling will import them automatically.

You can now cap how many AI credits an individual AI agent or chatbot is allowed to use each month. Once the cap is reached, the Agent stops generating responses until the next monthly cycle, or until you raise the limit.

This is useful when you want to allocate budgets across multiple AI agents, prevent any single Agent from depleting your project's quota, or build an Agent for a client without giving them unlimited spend.

To set it up, head to your chatbot or AI agent's settings and open the new Limits tab.

Read the docs →