# Add one more provider to an existing integration point

Another provider behind an interface that already exists, verified by the shared conformance suite.

Category: Repetitive feature work
Source: https://letsship.ai/use-cases/add-one-more-provider
Published: 2026-08-25

## Goal

Add a provider implementation behind an existing integration interface.

## Acceptance criteria

- The provider passes the shared conformance suite with no changes to the suite
- Credentials are resolved the same way as the existing providers
- Provider-specific behaviour is handled inside the implementation, not leaked to callers
- Selection is configuration rather than code

## What lands as proof

An unchanged conformance suite passing against the new provider, which is what proves the interface held.

## Prompt

Copy this to an agent to open the ticket:

```text
Create a Linear issue in my team and assign it to the SHIP agent.

Title: Add {provider} to the {integration} integration

Description: Add a provider implementation behind an existing integration interface.

Acceptance criteria:
- The provider passes the shared conformance suite with no changes to the suite
- Credentials are resolved the same way as the existing providers
- Provider-specific behaviour is handled inside the implementation, not leaked to callers
- Selection is configuration rather than code

Before you create the issue, find an integration in this repository with more than one provider and replace {integration} and {provider}.
```

## Questions

### What does the agent actually change?

The ticket is scoped to one outcome: add a provider implementation behind an existing integration interface. Work that serves that outcome is in scope, and anything outside it is left for a separate ticket, so the pull request stays reviewable.

### How do I know the work is done?

The pull request carries the evidence, not only the diff. Here that means the provider passes the shared conformance suite unchanged, so a reviewer can confirm the result without reproducing the work locally.

### How much oversight does this need?

The run stops once the plan is written. Somebody reads the approach and approves it before any code exists, which is the cheapest moment to redirect the work.