> For the complete documentation index, see [llms.txt](https://docs.dapta.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.dapta.ai/news.md).
# News
What changed in Dapta, one page per month, with a link to the documentation for each change. The last three months are one click away.
What changed in Dapta, one page per month. Each change links to the page where it is documented in full.
October 2026 September 2026 August 2026
***
## October 2026
Inbox alerts you on your desktop when a chat is assigned to you or a customer replies on WhatsApp. You can correct the AI's result on a voice call when it gets one wrong. Dapta Auto, the model Dapta keeps up to date for you, on Text Agents and Voice Agents. Your agents book appointments with Dapta Calendars, post-call analysis sends each call's results to Google Sheets, HubSpot or a flow, and every Text Agent can connect WhatsApp through Meta. Meta also changed how it charges for messages on 1 October.
→ [See what changed in October](/news/october-2026.md)
## September 2026
Campaigns became Sequences and Dapti can set one up for you. WhatsApp lines connect directly through Meta, Agentic Warm Transfer works on every Voice Agent, Text Agents book appointments with Dapta Calendars, and you choose what customers get when a person takes over.
→ [See what changed in September](/news/september-2026.md)
## August 2026
Internal notes and a context panel in the Inbox, Text Agents that reply at a human pace and send files from a Brain, Voice Agents that send WhatsApp templates during a call and get through phone menus, and OpenAI, Claude and Google Gemini nodes in Flow Studio.
→ [See what changed in August](/news/august-2026.md)
***
## Also worth knowing
**Meta has its own AI assistant inside WhatsApp Business.** Meta has been expanding it through 2026, and it is a separate product from Dapta — connecting your line to Meta does not switch it on, and using Dapta does not require it. If it is enabled on a number you want Dapta to answer on, turn it off first: your Dapta agent becomes the AI on that number, and your team can still reply by hand from the app.
Where a Text Agent goes further than an assistant that answers questions: → [Dapta and WhatsApp Business](/ai-text-agents/dapta-and-whatsapp.md)
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.
Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:
```
GET https://docs.dapta.ai/news.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.