Load Zendesk - Conversations data to DuckDB

Zendesk Conversations (formerly Sunshine Conversations) is a messaging API platform for building conversational experiences across various channels. Everything needed to build a working Zendesk - Conversations → DuckDB pipeline is on this page: the API's base URL, authentication, endpoints, pagination and incremental field — plus a prompt that hands the whole job to your coding agent.

---

Build your Zendesk - Conversations to DuckDB pipeline

Paste this prompt into Claude, Codex, or Cursor. The agent does the rest.

PromptCopy prompt
Run uvx dlthub-init@latest to build a pipeline from Zendesk - Conversations to DuckDB and run it on dltHub

That scaffolds a dltHub workspace and installs the dltHub AI harness — the project rules, the secrets-management skill, and the dlt MCP server your agent needs to work safely. From there it reads the Zendesk - Conversations API, proposes the endpoints to load, then writes, runs and validates the pipeline while you review rather than type. Credentials are inspected through MCP tools, so your agent never reads secrets.toml itself. How the LLM-native workflow works →

Prefer to write it yourself? Every fact the agent uses is below.

---

Zendesk - Conversations API at a glance

These values come from the Zendesk - Conversations API reference — the authoritative source if anything here looks out of date.

---

How do I authenticate with the Zendesk - Conversations API?

The API supports Basic authentication using a Key ID as the username and a secret key as the password, as well as Bearer token authentication using a JWT signed with an API key. Credentials for Basic auth are provided via the Authorization header using the 'Basic' scheme with a base64-encoded '{key_id}:{key_secret}' string, while Bearer auth requires a 'Bearer {your-jwt}' string.

1. Get your credentials

To obtain credentials for the Conversations API (Sunshine Conversations), follow these steps in the Zendesk Admin Center: 1. Log in to your Zendesk account. 2. Navigate to 'Apps and integrations' in the sidebar. 3. Select 'APIs' > 'Conversations API'. 4. Click 'Create API key'. 5. Copy the provided Key ID and Secret Key carefully, as the secret will not be displayed again.

2. Add them to .dlt/secrets.toml

Copy
[sources.zendesk_conversations_source]
key_id = "your_key_id_here"
secret = "your_secret_key_here"

dlt reads this file automatically at runtime. With the harness, the setup-secrets skill prompts you for the values and never handles the raw credential in chat. For production, see setting up credentials with dlt.

---

What Zendesk - Conversations data can I load into DuckDB?

These are the Zendesk - Conversations endpoints dlt can load into DuckDB:

---

How do I load only new Zendesk - Conversations records?

Zendesk - Conversations exposes page[after] on v2/apps/{app_id}/conversations, so dlt can request only the records that changed since the last run. Set it as the cursor_path and dlt tracks the high-water mark for you between runs.

Copy
{"name": "conversations", "endpoint": {
    "path": "v2/apps/{app_id}/conversations",
    "data_selector": "conversations",
    "incremental": {"cursor_path": "page[after]", "initial_value": "2024-01-01T00:00:00Z"},
}}

On the first run dlt loads everything from initial_value; on every run after that it requests only what changed and appends with write_disposition="merge" if you set a primary key. See incremental loading.

---

What does the generated Zendesk - Conversations pipeline look like?

A standard dlt REST API pipeline — the same code you would write by hand, loading apps and conversations from the Zendesk - Conversations API into DuckDB:

Copy
import dlt
from dlt.sources.rest_api import RESTAPIConfig, rest_api_resources

@dlt.source
def zendesk_conversations_source(api_key=dlt.secrets.value):
    config: RESTAPIConfig = {
        "client": {
            "base_url": "https://{subdomain}.zendesk.com/sc",
            "auth": {"type": "http_basic", "username": "REPLACE_ME", "password": api_key},
        },
        "resources": [
            {"name": "conversations", "endpoint": {"path": "v2/apps/{app_id}/conversations", "data_selector": "conversations"}},
            {"name": "messages", "endpoint": {"path": "v2/apps/{app_id}/conversations/{conversation_id}/messages", "data_selector": "messages"}}
        ],
    }
    yield from rest_api_resources(config)


def load_zendesk_conversations_to_duckdb() -> None:
    pipeline = dlt.pipeline(
        pipeline_name="zendesk_conversations_pipeline",
        destination="duckdb",
        dataset_name="zendesk_conversations_data",
    )
    load_info = pipeline.run(zendesk_conversations_source())
    print(load_info)


if __name__ == "__main__":
    load_zendesk_conversations_to_duckdb()

Run it with python zendesk_conversations_pipeline.py. The agent iterates on this until it loads cleanly — you review and approve, rather than write it from scratch.

---

How do I query Zendesk - Conversations data in DuckDB?

dlt creates one table per resource. Query the loaded data with Python or SQL — or ask your agent to, through the MCP server's execute_sql_query tool.

Python (pandas DataFrame):

Copy
import dlt

data = dlt.pipeline("zendesk_conversations_pipeline").dataset()
df = data.conversations.df()
print(df.head())

SQL:

Copy
SELECT * FROM zendesk_conversations_data.conversations LIMIT 10;

See querying your data with dataset and exploring it in marimo notebooks.

---

How do I deploy the Zendesk - Conversations to DuckDB pipeline in production?

The pipeline runs locally, which is ideal for prototyping and one-off analysis. When you need it on a schedule, monitored on every load, and shared with your team, deploy the same dlt code on the dltHub platform — no infrastructure to maintain. The prompt above already ends with "run it on dltHub", so your agent can take it there directly.

• Deploy & schedule — run the pipeline as a managed job with automatic retries.
• Monitor — observable job queues, alerting, and load metrics for every run.
• Transform — promote raw Zendesk - Conversations loads into governed, documented models.
• Visualize & share — explore data in notebooks and publish live dashboards instead of static screenshots.

Book a demo →

---

What other destinations can I load Zendesk - Conversations data to?

dlt loads into any of these — only the destination argument changes:

Set dlt.pipeline(destination="snowflake") and add credentials in .dlt/secrets.toml. On the dltHub platform the same pipeline runs against a managed Iceberg lakehouse. See the full destinations list.

---

Next steps

• Ready for production? Book a demo of the dltHub platform →
• dlt LLM-native workflow docs
• REST API source reference
• Join the dlt community on Slack