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

# Why is my agent silent?

> The readiness checklist in the studio, and every reason an agent can decline to answer a message — in the order they are checked.

An agent that says nothing looks the same from the inbox whatever the cause. This page is the list of causes, and where each one is fixed.

## The readiness checklist

A panel sits above the studio tabs whenever something is outstanding, listing what is unfinished. Each line is a button that takes you to the tab that fixes it. When nothing blocks the agent and nothing is worth flagging, the panel disappears — a checklist that stays on screen after it is finished is furniture.

Two severities. A **blocker** stops the agent answering anybody, and turns the panel amber. A **warning** is worth fixing but the agent still works.

| Check                               | Severity | What it means                                                                                                    | Fix on             |
| ----------------------------------- | -------- | ---------------------------------------------------------------------------------------------------------------- | ------------------ |
| The workspace can reach a model     | Blocker  | The workspace is set to use its own provider key and none is stored, so no agent can answer                      | Provider & credits |
| It is switched on                   | Blocker  | Nothing is drafted or answered while the agent is off                                                            | Routing            |
| It knows what the business does     | Warning  | With no description it answers from the customer's question alone, which is how an agent invents things          | Persona            |
| It has something to answer from     | Warning  | No documents are selected for this agent, so every answer comes from the persona alone                           | Knowledge          |
| Its Google skills can reach Google  | Warning  | A Google skill is on but Google is not connected, so those tools are withheld and the agent answers without them | Skills             |
| Its selling skill can reach a store | Warning  | **Sell from the chat** is on but no store is connected, so the agent will talk about products it cannot sell     | Skills             |

**Drafts only** and **Test mode** are deliberately not on this list. Both are legitimate ways to run an agent, and a checklist that nags about a choice you made on purpose is one people learn to ignore.

## Every reason a message goes unanswered

These are checked in this order. Any one of them ends the reply, and most of them leave no trace in the inbox beyond the absence of a message.

<Steps>
  <Step title="Something else already handled the message">
    On WhatsApp, a running [flow](/flows/overview) that consumed the message stops the agent being asked. On every channel, a tap on an interactive button or list reply is answered by whatever sent it, and a message with no text at all — a photo on its own — never reaches the agent.
  </Step>

  <Step title="No agent covers this channel">
    No **switched-on** agent's channels include this conversation's channel. There is no fallback to "the only agent you have". Fix in [Routing](/ai-agents/routing).
  </Step>

  <Step title="The agent does not answer automatically">
    **Answer inbound messages automatically** is off — the agent drafts on request only. Fix on Behaviour.
  </Step>

  <Step title="The workspace is out of credits">
    On built-in AI with an empty wallet and no provider key of your own, the conversation is left for a person rather than the customer being told a business is out of AI credits. Fix by [topping up](/ai-agents/credits-and-byok).
  </Step>

  <Step title="A teammate owns the thread">
    A conversation assigned to a member is that member's. Clear the owner in the thread header to let the agent reply.
  </Step>

  <Step title="AI replies are paused on this conversation">
    Set automatically by a handoff, and by the bot button in the thread header. The same button resumes it.
  </Step>

  <Step title="The conversation's reply budget is used up">
    **Max replies per conversation** — three by default — counted over a rolling 24-hour window that opens with the first reply after a quiet period. A customer who comes back the next day gets a full budget; a runaway loop inside one window is stopped at the cap.
  </Step>

  <Step title="Test mode excludes this customer">
    With test mode on, only the listed phone numbers are answered — and Instagram and website conversations have no phone number, so they are never answered while it is on. See [Test mode](/ai-agents/testing).
  </Step>

  <Step title="An automation already answers this message">
    An active automation on a message trigger, scoped to this channel, whose keywords match this text, owns the reply. One message gets one reply, and the automation wins. Check [Automations](/automations/triggers).
  </Step>

  <Step title="A handoff phrase matched">
    One of the **Phrases that always hand off** appeared in the message. The agent stands down without asking the model, and your handoff message is sent if you set one.
  </Step>

  <Step title="The model handed off, or came back empty">
    The agent decided it could not help safely. AI replies are paused on that conversation and it waits for your team.
  </Step>

  <Step title="The provider call failed">
    A bad key, a rate limit or a timeout. Your **Fallback message** is sent if you wrote one; with the field blank the agent stays silent rather than apologising in a voice you did not choose.
  </Step>
</Steps>

## When it replies but seems to have forgotten a skill

The reply arrives, and reads as though the agent never knew it could book a meeting, log a row or send a basket link. That is a **withheld tool**: the agent was never shown it, so it could not mention it.

| Symptom                                   | Cause                                                                                                                                        |
| ----------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------- |
| Never checks the calendar or books        | [Google](/integrations/google) is not connected, or the reply is a draft                                                                     |
| Never sends a basket link                 | No store is [connected](/integrations/store-console)                                                                                         |
| Never sends a payment link                | [Razorpay](/integrations/razorpay) is not connected, the reply is a draft, or **Most it may ever ask for** is unset                          |
| Never uses one of your approved templates | The conversation is not WhatsApp, the reply is a draft, no template is listed in the skill, or every listed template is currently unsendable |
| Never calls one of your API actions       | The action is switched off, or this agent's action selection excludes it                                                                     |

The Skills tab lists the tools each enabled skill can call, and the readiness panel names the two connection gaps it can see.

## When the answer is wrong rather than missing

Open the [test drawer](/ai-agents/testing) and ask the same question. The evidence line under the reply names the documents the answer was built from and every tool that ran.

* **The right document was not retrieved** — split a long document into one topic per document, or check its status is **Ready** rather than **Keyword only** or **Failed**.
* **The document was retrieved and ignored** — a ground rule or an instruction is contradicting it. Ground rules outrank everything below them, including your documents.
* **It invented something** — fill in **What the business does**, and add the fact as a document. The agent is told not to guess, but with nothing to go on it has only the customer's question.
* **It sounds wrong rather than being wrong** — tone, reply length and **Extra voice notes** on [Persona](/ai-agents/persona-and-behaviour).