Build and publish an AI agent to
Slack

Create an AI agent from an OpenAPI spec or MCP server, automatically optimize it with real-world use cases, and publish it to Slack, Teams, Copilot, and Gemini Enterprise

Book a demo

Slack
Teams
Copilot
Gemini Enterprise

Opportunity

Increase your revenue through untapped channels

Increase conversion to paid and retention with Slack and Teams. Close larger enterprise deals faster with Microsoft and Google Cloud Marketplace

0%

increase in conversion to paid

Zapier disclosed that Slack users are 10% more likely to convert to paid — and 150% more likely if they connect Slack on day one.

0%+

lift in retention

Mural reports a double-digit retention lift for users who engage with Mural inside Teams, Outlook, and Office — translating to more seats and bigger renewals.

Microsoft 365 blog

0%

faster deals

Microsoft Marketplace deals close 75% faster, average 85% larger than traditional sales motions, and 69% of partners report bigger deals.

0%

larger deal sizes

Google Cloud Marketplace deals are 112% larger and close up to 50% faster.

Google Cloud blog

0M

paid enterprise seats

410M paid seats across Slack, Teams, Copilot, and Gemini Enterprise.

^*Slack and Teams paid DAU/MAU are estimates.

How it works

Five steps to four platforms

Create an AI agent from an OpenAPI spec or MCP server, automatically optimize it with real-world use cases, and publish it to Slack, Teams, Copilot, and Gemini Enterprise

01 Step 1

Create an AI agent from an OpenAPI spec or MCP server

Add an OpenAPI spec or an MCP server's URL, along with any custom headers.

Agent Builder
02 Step 2

Test with real-world use cases

Chat to the agent and figure out where it fails. Once you know what's working and what isn't, you can add rubrics.

Playground
03 Step 3

Set rubrics and rate sessions

A rubric can be anything you want: using correct tools and parameters, effectively responding to the user, not hallucinating, etc. Rate each chat against the rubrics, these will be used to optimize the agent.

Rubrics & Scoring
04 Step 4

Automatically optimize the agent

Click 'Optimize Rubrics' to optimize an LLM-as-a-judge. Once you've optimized the rubrics, click 'Optimize Instruction' to optimize the system instruction to any model you want.

Optimisation Run
05 Step 5

Publish to Slack, Teams, Copilot, and Gemini Enterprise

That's it. Continuously improve the agent by rating chats, and optimizing the rubrics and system instruction.

Publish

Features

Build and publish a production-ready agent in a day

A2A Net is a fully-managed platform built specifically to build, optimize, and publish AI agents to Slack, Teams, Copilot, and Gemini Enterprise

Automatic optimization

Automatically optimize your agent to the latest model with state-of-the-art optimization algorithms that have been customized specifically for conversational agents.

Code mode

Code mode is enabled by default, giving agents the ability to write code to call tools, analyze the tool call results, create files, and more.

A2A compatible

Every agent is A2A protocol compatible, meaning you can give your customers access to it via API, Claude Code, Codex, OpenClaw, and more.

Ship it!