At its Forge 2026 conference on September 29, 2026, Braze unveiled three agentic tools — Decisioning Studio Go, Agentic Standards, and Operator Connect — that automate the setup, quality assurance, and decisioning work around a campaign, not just the copy inside it.
2026-09-30 · by Moe Ameen
On September 29, 2026, at its Forge conference in Las Vegas, Braze — the customer engagement platform brands use to run email, push, SMS, in-app, and web messaging to a known user base — announced a set of AI tools that move its automation past content creation and into campaign operations: the setup, quality assurance, and decisioning work that surrounds a campaign rather than the copy inside it. Braze framed the shift as turning marketers from hands-on builders into decision-makers who set guidelines and supervise AI agents.
Three products anchor the release. BrazeAI Decisioning Studio Go is a lighter, self-service version of Braze's AI decisioning that picks the best combination of creative, copy, and timing for each individual recipient — Braze says the agent can test more than a billion combinations across a large audience — aimed at teams without dedicated data scientists; it is in beta with general availability slated for October 14, 2026. Agentic Standards is an AI review layer that checks every campaign and Canvas against rules a team sets once — spanning setup, copy, links, personalization logic, and brand or regulatory compliance — and returns a pass, warning, or fail with suggested fixes; it is in beta with GA expected in October 2026. BrazeAI Operator Connect makes Braze "headless" through the Model Context Protocol, letting marketers build and launch campaigns from external AI tools including Claude, ChatGPT, Snowflake Cortex Code, and Microsoft Copilot without leaving them; it is in beta.
Braze also introduced Conversational Agents — brand-configured agents that hold two-way conversations across WhatsApp, SMS, RCS, and the web, grounded in guardrails and knowledge sources such as product catalogs and FAQs — and announced a strategic collaboration with Amazon Web Services that brings Amazon Bedrock into its AI Agent Console. The through-line is a build-to-supervise model: agents handle the operational grind — variant testing, QA, per-person decisioning — while marketers set the rules and approve the output. Treat exact GA dates, beta scope, and pricing as launch-window specifics and confirm them on Braze's own pages.
Braze's release draws a line that is easy to lose in the hype: it is automating campaign operations for the channels you own — email, push, SMS, in-app, and web, to a customer list already in your database. It does not generate your organic social content, and it does not post to TikTok, YouTube, or Instagram. The build-to-supervise shift Braze describes for lifecycle messaging is the same shift already running on the organic side, and [Kompozy](/) is where a creator or brand gets it for the content and channels Braze never touches.
Read them as two halves of one creation-to-distribution engine. Braze decisions and sends to the audience in your database; Kompozy generates the content that builds that audience in the first place and publishes it across the open social web. Hand Kompozy one source asset and it produces [Persona Shorts](/glossary/persona-shorts) and avatar video, brand-exact [Carousels](/glossary/hyperframes), Photo Posts, Quote Graphics, Blog Articles, and Email Newsletters — every piece held to one voice by a written [Persona Brief](/glossary/persona-brief) — then [Autopilot](/glossary/autopilot) sizes each output per platform and schedules it across the eight social platforms plus blog and email, each post through a review gate you approve before it ships. You set the rules; the engine executes. It is the same agentic operating model Braze just brought to campaigns, pointed at the organic-growth layer that feeds the very list Braze then engages.
On September 29, 2026, Braze unveiled AI tools extending its automation from content creation into campaign operations: BrazeAI Decisioning Studio Go (self-service per-person decisioning, general availability slated for October 14, 2026), Agentic Standards (an AI review layer that QAs campaigns against your rules, GA expected October 2026), and BrazeAI Operator Connect (headless Braze via the Model Context Protocol). It also launched Conversational Agents and announced an AWS collaboration. All three headline tools are in beta.
Operator Connect makes Braze "headless" through the Model Context Protocol, so marketers and developers can build and launch Braze campaigns from external AI tools — including Claude, ChatGPT, Snowflake Cortex Code, and Microsoft Copilot — without switching into the Braze dashboard. It extends the in-platform BrazeAI Operator assistant into the tools teams already use. It was in beta at announcement.
No. Braze is a customer engagement platform for owned channels — email, push, SMS, in-app, and web — sent to a customer list you already have. Its new AI automates campaign operations like QA and per-person decisioning; it does not generate branded social video, carousels, or graphics, and it does not publish to organic platforms like TikTok, YouTube, or Instagram. A content engine such as Kompozy covers that generation-and-publishing side.
Decisioning Studio Go was in beta with general availability slated for October 14, 2026; Agentic Standards was in beta with GA expected in October 2026; and Operator Connect and Conversational Agents were introduced in beta at the September 29, 2026 announcement. Confirm current availability on Braze's own pages, as beta scope and dates can shift.