ai-actions-platform

A reference for building Freshworks Platform 3.0 AI Actions apps, which are serverless functions exposed for AI-driven tasks. It documents the app files, action definitions, manifest settings, request configuration, and test data.

In plain words
What is it for?
Use it to create or review actions.json, manifest.json, server functions, API request templates, installation settings, OAuth configuration, test data, and the README.
Why use it?
It keeps action names, server functions, platform modules, and configuration files aligned. This avoids structural errors while editing or extending an AI Actions app.

Cursor rule

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add rules/freshworks-developers/fw-dev-tools/ai-actions-platform
Clone the repo
git clone --depth 1 https://github.com/freshworks-developers/fw-dev-tools
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 2,051 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.02051
Opus 5 $0.00000 $0.01026
Sonnet 5 $0.00000 $0.00410
Haiku 4.5 $0.00000 $0.00205

Measured 2d ago against content hash 082d35af8c40, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai-actions-platform scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/fw-ai-actions-app/rules/ai-actions-platform.mdc · 299 lines

How it starts

The opening of the file, as written. The whole thing — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Actions Platform 3.0 - Complete Reference

SELF-CONTAINED: This skill has everything needed for AI Actions app development. No other skill required.

AI Actions App Structure

AI Actions apps are serverless-only - NO frontend, NO locations, NO product events:

app-root/
├── actions.json              # Action definitions (display_name, parameters, response)
├── manifest.json             # Platform 3.0 manifest
├── server/
│   ├── server.js            # SMI function implementations
│   └── test_data/
│       └── actionName.json  # Test payload per action
├── config/
│   ├── requests.json        # Request templates for external APIs
│   ├── iparams.json         # Installation parameters
│   └── oauth_config.json    # Optional: for OAuth-based APIs
└── README.md

CRITICAL: Function names in actions.json MUST match server.js exactly (case-sensitive).


Manifest Structure (Platform 3.0)

{
  "platform-version": "3.0",
  "modules": {
    "common": {
      "requests": {
        "requestTemplateName": {}
      },
      "functions": {
        "actionFunctionName": { "timeout": 20 }
      }
    },
    "support_ticket": {},
    "chat_conversation": {}
  },
  "engines": {
    "node": "24.11.0",
    "fdk": "10.0.0"
  }
}

Rules:

  • platform-version MUST be "3.0"
  • ✅ At least ONE product module required (support_ticket, chat_conversation, service_ticket, deal, etc.) - can be empty {}
  • ✅ All request templates declared in modules.common.requests
  • ✅ All action functions declared in modules.common.functions with timeout (recommended: 20)
  • engines block required with node and fdk versions
  • ❌ NO product block (use modules)
  • ❌ NO whitelisted-domains
  • ❌ NO locations, NO events (AI Actions are serverless-only)

Product Module Mapping

Target Product Include Module
Freshdesk support_ticket
Freshchat chat_conversation
Freshservice service_ticket
Freshsales/CRM deal, contact
Multi-product support_ticket, chat_conversation

Read the full file on GitHub · 299 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 299 lines · 0 tokens per session scan A 082d35af8c40

Subscribe to this mod's changes

ai-actions-platform is a cursor rule published in the GitHub repository freshworks-developers/fw-dev-tools (5 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,051 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.