Blog

Feedback API: your AI agent can now report bugs and feature requests

Thomas SchiavoneThomas SchiavoneUpdated
Feedback API blog cover

Your AI agent works with Courier more than you do. It writes the sends, builds the templates, wires up the journeys, and reads every error along the way.

That makes it the first to hit a rough edge: an error that doesn't say what went wrong, a response that doesn't match the docs, a missing feature that would have saved a step. It tells you about it, then works around it and moves on. The workaround ships, the rough edge stays, and the next agent loses the same time.

With the Feedback API, your agent has somewhere to put what it finds. It files a short report and gets back to work. Courier's team and their agents read every report in real time, so what your agent runs into reaches the people who can fix it.

AI agents catch what people miss

Your agent is better at finding rough edges than most people. An agent reads every field in a response and checks it against the docs. It tries the edge cases a person would skip, and it doesn't give up on a confusing error after the third try.

We built Courier so people and agents work on the same platform. Everything in the dashboard is on the API, so an agent can build anything a person can. Hearing from those agents is the other half of that. If your agent burns ten attempts on one payload shape, we want to know.

What the Feedback API does

Courier's Feedback API lets your AI agent report bugs, confusing behavior, and feature requests straight to Courier's team, and you can file your own the same way. It's one endpoint, POST /feedback, with four ways in:

Every report has a category (possible_bug, confusing_behavior, feature_request, or other), the surface where it happened (api, sdk, mcp, ui, docs, or other), a title, and a description. Optional fields carry the endpoint or page involved, what should have happened, the request ID of the call that shows the problem, and the model and agent that sent it.

Courier Skills tells your agent what to report, what to put in the report, and to tell you once it's sent. Here's what a good report looks like:

JSON
{
  "category": "confusing_behavior",
  "surface": "api",
  "title": "Template metrics return 200 with an empty series for an unknown template ID",
  "description": "GET /notifications/{id}/metrics returns 200 with an empty series when the template ID doesn't exist. The template metrics docs call this out as indistinguishable from a real template that has sent nothing. Every other template endpoint in the public spec returns 404 for an unknown ID: GET, PUT, and DELETE /notifications/{id}, and GET and PUT /notifications/{id}/content. In practice a typo in a template ID makes a dashboard show a template that stopped sending.",
  "location": "GET /notifications/{id}/metrics",
  "expected_behavior": "A 404 for an unknown template ID, matching the other template endpoints.",
  "model": "claude-opus-5-5",
  "harness": "Claude Code"
}

It states what happened, shows why it matters, and names the change it wants.

How we designed the Feedback API

Report anything that slows your agent down

Small things count, down to one unclear sentence in the docs. Repeats are welcome too, because hearing the same thing from a dozen agents tells us what to fix first.

Reports turn into pull requests

Reports don't wait in a queue. Our agents review each one and check it against our code. When there's a fix to make, they stage a pull request for our team to review, approve, and build on. A clear report from your agent can become a fix without anyone writing a ticket.

Your agent keeps working

Your agent doesn't stop to ask permission, because a prompt for something this small would pull you out of your work. It files the report, tells you in one line with the title and ID, and goes back to the task.

Model and harness point us to the right fix

Each report can name the model and the harness, the agent or tool that sent it, such as claude-opus-5-5 and Claude Code. Seeing which agents trip on the same parameter tells us whether the fix belongs in our API, our docs, or Courier Skills. Agents leave these out rather than guess.

Safe to leave on

You can turn it on and stop thinking about it:

  • Only an API key with no scope restrictions can send a report, so your end users can't report in your name.
  • Your agent sends each issue once per session, and resends a rejected report once at most.
  • It never sends messages or changes data to reproduce a problem.
  • Reports describe problems with IDs, never API keys, customer data, or your source code.

Start using the Feedback API

To let your agent report on its own, install Courier Skills:

Terminal
npx skills add trycourier/courier-skills

Then connect the MCP server so your agent can send reports with submit_feedback. In Claude Code:

Terminal
claude mcp add --transport http courier https://mcp.courier.com --header api_key:YOUR_COURIER_API_KEY

The MCP server docs have setup for Cursor, Codex, and 12 more clients. Use an API key with no scope restrictions.

To file a report yourself, ask your agent to send one through the MCP server, or run the CLI:

Terminal
courier feedback create \
  --category feature_request \
  --surface api \
  --title "Return rendered content in the send response" \
  --description "Goal: confirm template variables rendered after each send. POST /send returns only a requestId, so checking the output takes a second call to GET /messages/{message_id}/output." \
  --location "POST /send"

Wrapping up

Your agent was already finding the rough edges in your Courier integration. Now it can report them to us as it works.

Install Courier Skills, connect the MCP server, and let your agent tell us what it runs into. The Feedback API docs cover every field and limit.

Frequently asked questions

What is the Courier Feedback API?

The Courier Feedback API is an endpoint, POST /feedback, that lets your AI agent report bugs, confusing behavior, and feature requests to Courier's team, and lets you file your own. Your agent sends reports through the Courier MCP server's submit_feedback tool, the Courier CLI, or the server SDKs, and Courier Skills tells it when and how to report.

What happens after my agent sends a feedback report?

Courier's team and their agents read every report in real time. When a report points to a fix, their agents check it against Courier's code and stage a pull request for the team to review.

Does my agent need the MCP server to send feedback?

No. The MCP server is one of four ways to send a report. Your agent can also use the Courier CLI, any of the seven server SDKs, or a POST /feedback request.

What shouldn't go in a feedback report?

API keys, secrets, customer data such as recipient emails or message content, and your own source code don't belong in a report. Describe the problem with IDs instead.

Which AI agents can report to Courier?

Any agent that can call an MCP tool, run the CLI, or make an HTTP request can send a report. Courier Skills installs in Claude Code, Cursor, Codex, and other coding agents that load agent skills.