Email Helpdesk
End-to-end email support with IMAP polling, auto-reply filtering, and intent classification. Drafts contextual replies from the configured retrieval.
connic init my-project --templates=email-helpdeskOverview
Polls an IMAP mailbox for new emails, filters auto-replies and spam with StopProcessing middleware, classifies by intent/urgency/department, and drafts contextual replies using the full retrieval CRUD (query, store, and delete). Replies are sent automatically via the SMTP outbound connector. Middleware extracts sender metadata into context for personalized responses. Supports multilingual replies matching the sender's language.
Use cases
Support inbox automation
Automatically triage and respond to support emails from a shared mailbox, filtering noise and drafting helpful replies.
Retrieval maintenance
Auto-update the retrieval as new solutions are discovered; remove outdated entries using retrieval_delete.
Multilingual support
Detect the sender's language and draft replies in the same language for international customer bases.
Architecture
Main template files
Install these files with connic init my-project --templates=email-helpdesk. The CLI places agent definitions in a folder named after the template under agents/.
email-helpdesk/
agents/
email-classifier.yaml
email-responder.yaml
helpdesk-pipeline.yaml
tools/
helpdesk_tools.py
middleware/
email-classifier.py
schemas/
email-classification.json
email-reply.json
requirements.txt
README.mdGet started
Install the template, create a Connic project, and deploy through a connected Git repository or the CLI.
Prerequisites
- Python 3.10+
- A Connic account (create a project first)
- Project credit for a connic/* model, or credentials for a BYOK provider
Install and scaffold
Install the SDK and create a project from this template.
terminalpip install connic-composer-sdk connic init my-project --templates=email-helpdeskThen cd my-project
Deploy
Choose a deployment method. A connected Git repository deploys on push; use the CLI for projects without a connected Git repository.
Git integration
In Connic: Project Settings → Git & Environments, connect the GitHub repository
On the same page, map a branch (e.g. main) to the Production environment
Push the scaffolded project to that repository
terminalgit add . git commit -m "Add Email Helpdesk template" git push origin mainCLI deploy
In Connic: Project Settings → API Keys & MCP Auth, create an API key and copy project ID
Run connic login in the project folder
Use connic dev to try with hot-reload, connic test to run suites, or connic deploy for production
terminalconnic login connic dev # Ephemeral dev env with hot-reload connic test # Run declarative test suites connic deploy # Deploy to productionConnect and configure
Add an Email inbound (IMAP) connector to poll the mailbox and an Email outbound (SMTP) connector to send replies. Provide the mail server credentials for both. Use a connic/* model, or add BYOK credentials under Project Settings → LLM Provider.
Template source
Browse the full template, contribute improvements, or fork it for another use case.
connic-org/connic-awesome-agents/tree/main/email-helpdeskInformation
- Publisher
- By Connic
- Category
- Agent Templates
- Difficulty
- Intermediate
- Works with
- Source
- GitHub
More agent templates
Browse the marketplaceCompliance Auditor
Scheduled compliance scanning combining web search for regulatory updates, MCP docs, and retrieval history. Produces scored summaries.
Invoice Processor
Extract structured data from invoices with AI, validate totals via a deterministic tool agent, and output auditable JSON with retry support.
Browser Automation Demo
Ask for a Connic email, password, and project title, then sign in and create the project through the dashboard.
Lead Enricher
Enrich and qualify new signups by researching their company and scoring fit against the ideal customer profile. Saves qualified leads.
S3 Document Pipeline
Auto-process documents uploaded to S3 with text extraction, classification, and routing. Handles PDFs, images, and text files with retries.
Kafka Fraud Detector
Score transactions for fraud in real-time on Kafka streams. Uses velocity analysis, geo-anomaly detection, and pattern matching per customer.