---
title: "AI feedback — support tickets for AI agents"
locale: en
url: https://tlg.builera.app/en/docs/integrations/ai-feedback
verified: 2026-10-27
app_version: "2.3"
---

# AI feedback — support tickets for AI agents

AI agents report bugs, suggestions or questions to the Telegram-Auto team through the API / MCP; you read, answer and switch it off per connection.


When an AI agent (Claude, ChatGPT, Cursor, n8n…) uses Telegram-Auto through an [AI connection](https://tlg.builera.app/en/docs/integrations/ai-connections) and hits a bug, finds a step cumbersome, misses a capability or has a question, it can file a **support ticket** for the Telegram-Auto team. Every ticket has an id like `TG-FB-XXXXXXXX`.

## When an agent files one

- An operation fails repeatedly, or answers differently from the docs.
- One simple job takes many calls.
- A capability needed for the task you gave it is missing.
- The docs are missing or wrong; it has a question about usage.

Agents do not have to file after every call. They are reminded only after an error, when a tool search finds nothing, or in the first `whoami`.

## What is never sent

Every ticket is checked **before it is stored**. Passwords, login codes, 2FA codes, API keys (`tga_…`), bot tokens, Telegram sessions, cookies, proxies with passwords or card numbers make the whole ticket fail with `feedback_secret_detected` — nothing is stored. Phone numbers, emails, IP addresses, `@handles` and the part of a link after `?` are masked as `[phone]`, `[email]`, `[ip]`, `[handle]`, `[query]`.

Agents must not copy customer messages into a ticket unless you allowed it.

## Who sees tickets

| Who | Sees |
|---|---|
| The AI connection that filed it | Its own tickets, public answers, status |
| Workspace owners and managers | Every ticket of the workspace, public answers |
| The Telegram-Auto team | Every ticket, plus internal notes |

Agents and viewers do not see this tab. Internal notes of the Telegram-Auto team are never shown to the AI or the workspace.

## Read and answer

1. Open **Settings → AI connections → AI feedback**.
2. Filter by status (Open, Waiting on you, Resolved, Closed), category or connection; search by id or title.

   ![The AI feedback tab with its ticket list and status, category and connection filters](https://tlg.builera.app/docs-media/en/ai-feedback-list.webp "AI feedback")

3. Click a row to open the ticket. Text written by the AI is shown as plain text — no links or formatting are created from it.
4. Type in **Add information** and press **Send**. The AI sees it on its next call.
5. No longer needed? Press **Withdraw ticket**: it closes as "Withdrawn".

![One ticket in detail: what the AI sent, the timeline with the support team's question and the reply box](https://tlg.builera.app/docs-media/en/ai-feedback-ticket.webp "Ticket detail")

"Waiting on you" means the team asked for more information. You or the AI can answer; the bell rings when the team answers or asks.

## On / off per connection

- New connections: **Let this AI send feedback and bug reports** is ticked (in the connection dialog and on the OAuth consent screen).
- Existing connections: switched on once when this channel launched.
- Turn it off with that box in the connection editor, or the **Let this connection send feedback** switch inside a ticket. Permission presets never overwrite it.

When off, the AI gets `feedback_disabled` if it tries; older tickets stay.

## Lifecycle

| Status | Meaning |
|---|---|
| New | Just received |
| Triaged / Planned / In progress | The team is working on it |
| Waiting on you | The team asked for more information |
| Resolved | Has an outcome: fixed, answered, declined, duplicate, cannot reproduce |
| Closed | Finished |

- Resolved for 14 days with nothing added → closes by itself.
- Waiting on you for 30 days without an answer → closes as "No response".
- 90 days after closing → the ticket and its timeline are deleted; only an anonymous weekly count stays.
- The AI can read a closed ticket for 30 days; after that only workspace people see it.

## Limits

| Action | Limit |
|---|---|
| Create | 10 / minute and 100 / day (per connection and per workspace) |
| Add information | 5 / minute and 30 / day per connection, 100 / day per workspace |
| Read | 30 / minute per connection |

The same problem sent again within 24 hours does not create a new ticket: the old one counts one more occurrence and the AI gets the old id back. Over a limit → `feedback_quota_exceeded` with `retry_at`.

## Do it with the API / MCP

Four operations: `feedback.create`, `feedback.list`, `feedback.get`, `feedback.append` (MCP: `feedback_create`, `feedback_list`, `feedback_get`, `feedback_append`; REST: `/api/public/v2/feedback`). The agent steps are in the [report-a-problem playbook](https://tlg.builera.app/en/docs/agent-playbooks/report-a-problem).

Every API / MCP error answer carries a `trace_id`; the AI cites up to 5 of them in `related_trace_ids` so the team finds the exact call.