# Email & Support Reply Checker - ReplyGuard (`dravara/replyguard-checker`) Actor

Paste a customer conversation and your draft reply. Get missed questions, unsupported claims, accidental promises, tone findings, and a conservative corrected draft. ReplyGuard never sends it.

- **URL**: https://apify.com/dravara/replyguard-checker.md
- **Developed by:** [Dravara LLC](https://apify.com/dravara) (community)
- **Categories:** AI, Business, Automation
- **Stats:** 2 total users, 1 monthly users, 72.4% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $0.10 / reply analysis created

This Actor is paid per event and usage. You are charged both the fixed price for specific events and for Apify platform usage.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

Actors are web data automations that power AI and operations. They run on the Apify platform to scrape websites, process data, connect APIs, and automate workflows.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.
Actors are written with capital "A".

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.
The best way to integrate Actors is as follows.

- **AI agents and MCP clients** — the [Apify MCP server](https://docs.apify.com/integrations/mcp.md) at `https://mcp.apify.com` (remote, streamable HTTP, OAuth on first use).
- **Agentic workflows and local Actor development** — [Agent Skills](https://apify.com/.well-known/agent-skills/index.json) with the [Apify CLI](https://docs.apify.com/cli/docs.md): `npm install -g apify-cli`, then `apify login`.
- **JavaScript/TypeScript projects** — the official [JS/TS client](https://docs.apify.com/api/client/js/docs.md): `npm install apify-client`.
- **Python projects** — the official [Python client](https://docs.apify.com/api/client/python/docs.md): `pip install apify-client`.
- **Any other language** — the [REST API](https://docs.apify.com/api/v2.md).

For usage examples, see the [API](#api) section below.

For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt).

# README

## ReplyGuard

**Check a draft against the conversation before you send it.**

ReplyGuard compares a draft reply with the conversation it answers. It flags
missed questions, accidental commitments, unsupported factual claims,
ambiguous wording, repetition, and avoidable tone problems. A successful run
returns structured findings plus a conservative corrected reply.

### Why use it

- Add a pre-send quality gate to support, sales, or operations workflows.
- Catch promises and dates that the received thread does not support.
- Receive both JSON findings and copy-ready corrected text.
- Run one bounded analysis through the Apify API, schedules, webhooks, or MCP.

### Input

Provide `thread`, `proposed_reply`, and an optional tone of `preserve`, `warm`,
`direct`, or `concise`. Questions in the thread do not establish their proposed
answers as facts.

### Output

The default dataset contains one item with `status`, `summary`, `findings`, and
`corrected_reply`. Evidence is constrained to exact fragments from the input.
When a generated correction cannot be validated, ReplyGuard supplies a neutral
holding reply instead of guessing.

### Self-service run and recovery

No separate Dravara account, API key, integration, or support handoff is
required. Complete the Actor input, start one run, and open its default dataset
to read the result. ReplyGuard never sends the draft or updates another system.

If input validation fails, correct the named field and start a new run. If the
analysis service is temporarily unavailable, wait a few minutes and start one
new run; a failed run does not continue in the background. If a charge or
dataset state ever looks unclear, do not loop automatic retries: inspect that
run's **Charges**, default dataset, and **Self-service failure details** output
first. The failure output is the sanitized key-value-store `OUTPUT` record with
the stable error code, retry guidance, and next action.

### Billing

Dravara's creator charge for a successful run is $0.20005: the $0.00005
`apify-actor-start` event plus $0.20 for `reply-analysis-created`. Apify
separately passes its variable platform usage to the customer and determines
the final displayed total; Dravara does not reduce its creator charge to absorb
that usage. The result event is captured only after a result is available in
the run dataset. Invalid inputs and provider failures skip the result charge,
but the Actor-start charge and Apify platform usage can still apply. The
synthetic sample input is billed like any other run.

### Privacy and limits

Inputs are processed by Dravara, LLC's private service and the OpenAI API using
`store: false`; applicable provider abuse-monitoring retention may still apply.
Apify retains normal run input/output under the runner's plan and retention
settings. Do not submit passwords, API keys, payment data, health data, or
unrelated customer content.

Maximum input sizes are 20,000 characters for the thread and 10,000 for the
draft. No message is sent on the user's behalf.

Optional defect contact:
<support@dravarahq.com>. Send only the Apify run
ID and safe error text, never the input. Support does not complete or deliver
failed runs.

# Actor input Schema

## `thread` (type: `string`):

The conversation context ReplyGuard should treat as the source of truth.

## `proposed_reply` (type: `string`):

The draft that has not been sent.

## `tone` (type: `string`):

Choose whether the corrected reply should preserve the draft's tone or shift toward a warm, direct, or concise style.

## Actor input object example

```json
{
  "thread": "Can you confirm the final price and whether it will ship Friday?",
  "proposed_reply": "Yes, it will definitely ship Friday.",
  "tone": "preserve"
}
```

# Actor output Schema

## `results` (type: `string`):

No description

## `failure` (type: `string`):

On a failed run, open the sanitized machine-readable error, retry guidance, and next action.

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "thread": "Can you confirm the final price and whether it will ship Friday?",
    "proposed_reply": "Yes, it will definitely ship Friday."
};

// Run the Actor and wait for it to finish
const run = await client.actor("dravara/replyguard-checker").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {
    "thread": "Can you confirm the final price and whether it will ship Friday?",
    "proposed_reply": "Yes, it will definitely ship Friday.",
}

# Run the Actor and wait for it to finish
run = client.actor("dravara/replyguard-checker").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "thread": "Can you confirm the final price and whether it will ship Friday?",
  "proposed_reply": "Yes, it will definitely ship Friday."
}' |
apify call dravara/replyguard-checker --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,dravara/replyguard-checker"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/Kh8wCiD59fGaKzVq5/builds/ejbwM6nDfARHwF1Q6/openapi.json