> ## Documentation Index
> Fetch the complete documentation index at: https://docs.replit.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Answer support questions from your codebase

> Investigate customer questions using your company's GitHub repository, explain product behavior, and prepare a clear reply or an actionable escalation.

Answer customer questions by asking Agent to investigate your company's codebase.
Get plain-language explanations of product behavior, backed by code references,
so you can prepare a clear reply or a focused escalation to engineering.

## Best for

* Support agents answering questions that the help center does not cover.
* Support leads preparing a focused engineering escalation.

## Connectors

## Before you start

You need a Replit Pro or Enterprise plan and access to your company's GitHub repository.

Connect GitHub with access to the relevant repository. Gather the customer's expected
result, actual behavior, reproduction steps, and error message.

## Prompt the agent

Check \[GitHub repository URL] to investigate this report: "After we resent
an invitation, the original link stopped working, even though it hadn't
expired." Is this expected behavior? Draft a short customer reply with code
references and any checks needed to confirm the cause. Do not change any files.

## What to expect

Agent uses the customer's question or report to find the relevant parts of the
codebase and investigate how the product behaves. If details are missing, Agent
asks for clarification or suggests questions to ask the customer.

The response includes:

* **A plain-language explanation:** how the relevant feature works and what could explain the reported behavior.
* **Supporting references:** links to the files and functions behind the findings, so you or an engineer can verify them.
* **Checks to narrow down the cause:** information or reproduction steps needed to distinguish between possible explanations.
* **A draft customer reply:** a concise explanation and next steps based on the findings, ready for you to review before sending.

You can continue in the same chat with additional customer details, ask Agent to
investigate another possibility, or refine the reply. Agent uses the conversation's
context and checks more of the code when needed.

If the evidence does not establish the cause, Agent explains what remains unknown.
You can ask for an engineering handoff with reproduction steps, expected and actual
behavior, relevant code references, and the checks still needed.

## Make it work for you

The customer follows up: "We clicked resend twice. Which invitation link
should our colleague use?" Trace what happens to earlier links and their
expiration times. Draft a short reply with supporting references.

Turn this invitation issue into an engineering escalation draft. Include
the resend sequence, expected and actual behavior, relevant code, and
checks still needed. Do not create an issue or send a message yet.

## Troubleshooting

> **Several causes fit the report**
>
> Ask Agent to rank the next checks by how easily they distinguish between possible causes.

> **The code differs from the customer's experience**
>
> Confirm the deployed version and feature settings with engineering.

> **Runtime evidence is missing**
>
> State what remains unknown and request the specific logs or account checks through approved channels.

## Related

> **[Turn feedback into improvements](https://docs.replit.com/use-cases/turn-feedback-into-improvements.md)**
>
> Take a confirmed problem from investigation to a proposed change.

> **[Push a PR from Slack](https://docs.replit.com/use-cases/push-a-pr-from-slack.md)**
>
> Request a focused change from the conversation where your team works.