> ## Documentation Index > Fetch the complete documentation index at: https://docs.signalmd.dev/llms.txt > Use this file to discover all available pages before exploring further. # The brief > The short document that says what your agent is for and what a good call is. Signal drafts it, you correct it, and every number is measured against it. The brief is a short document about your agent: what it is for, why people call, how a call goes, what counts as a good one and what it is not meant to do. Signal drafts it from your agent's configuration when you connect, you correct it, and you approve it. Approving a first brief also starts the first import, so no call is read before you have approved. ## Why it matters Your configuration says what the agent does. It cannot say what you want. A transfer to a person is the goal for one business and the failure for another. A caller who asks about billing is a missed call for one agent and correctly turned away by another. The brief is where you settle those questions once. It decides: * **What counts as a defect and what is designed behaviour.** Something the brief says the agent is not meant to handle is not counted against it, and an ending you mark as good is not a failure. * **What a good call is.** Signal reads every call against the purpose and the success line, so "got what they came for" means what you mean by it. * **Which parts matter most.** Issues located at a part you mark **High** move up the board, and issues at a part marked **Low** move down. See [How the board is ordered](/concepts/issues#how-the-board-is-ordered). * **What your tests check.** A test built from a call can point at a line of the brief, such as an intent's **Done when**. Edit the line and every test that points at it changes with it. See [Test a fix](/guides/test-a-fix). ## How Signal drafts it Signal reads the agent's configuration from Retell (its steps, prompts, tools and knowledge bases), writes the document, and asks about whatever the configuration could not settle. The first draft comes before any calls are imported, so it is a hypothesis about your business. Read it as one. The tag on the panel tells you where the text came from: | Tag | Meaning | | - | - | | **Draft** | Drafted by Signal from your configuration | | **From config** | The AI assistant is off for this workspace, so the brief was built from the configuration alone and is plainer. Edit it directly | | **Unsaved** and **Saving** | You changed the text. Signal saves it about a second after you stop typing | | **Approved** | You approved it | | **Demo** | The demo agent's brief, written in advance and read-only | ## What is in it You can edit any section in place. | Section | What it holds | What it changes | | - | - | - | | **What it does** | What the agent is for, in a sentence or two | How every call is read. Required to approve | | **What each call is for** | The reasons people call, each with a **Done when** line | The call reasons you see on calls and in Caller insights. **Done when** can be a test criterion | | **How a call goes** | The journey in numbered steps | For reading | | **How the parts connect** | A diagram of the parts and the hand-offs | For reading | | **The stages** | The parts grouped into a few boxes, one line each | Draws the flow diagram in boxes you recognise | | **The parts** | Each part with **Done when**, **Goes wrong when** and **Matters** (**High**, **Medium** or **Low**, with a reason) | **Matters** moves issues at that part up or down the board. The lines can be test criteria | | **What it asks the caller for** | What the agent collects | For reading | | **How a call can end** | Each way a call stops, marked **Good ending**, **Bad ending**, **Depends** or **Say which** | Whether a transfer counts as a failed call. Can be a test criterion | | **What it can do on the caller's behalf** | The actions the agent takes | For reading | | **A call worked when** | One line that defines success | What counts as success on every call. Required to approve | | **Signs it went well** | Things you can see on a single call | For reading | | **Should never happen** | Rules the agent must not break | How each call's outcome is read, and Caller insights | | **Not this agent's job** | What callers ask for that the agent is not meant to handle | Turning these callers away is not counted as a miss, and Caller insights counts their needs as covered | | **What Signal will watch** | Things to look for once calls arrive | A note for you. It does not change any number | | **Needs your confirmation** | Questions still open | Listed until you settle them | ## What to review before you approve You do not need to polish every section. These carry the most weight: 1. **A call worked when.** If this line is vague, every success rate is vague. Make it something you could check on one call: "The caller leaves with a confirmed appointment, or a booked callback if the clinic cannot take them." 2. **How a call can end.** A transfer stops counting as a failed call only when every transfer ending is marked **Good ending**. One **Bad ending**, **Depends** or **Say which** and transfers stay failures. 3. **Not this agent's job.** List what the agent should turn away, so turning it away is not read as a miss. 4. **The parts.** Set **Matters** to **High** for the parts where a failure costs you most. ## Answer the questions Questions appear in the **Calibrate** panel beside the brief, one at a time, with the reason each one matters and often answers you can select. Your answer is written into the right section of the brief, and that section is highlighted. The footer counts them, such as "2 of 5 questions settled". Questions you have not answered are listed under **Needs your confirmation**. If the assistant is off for your workspace, the panel says so and you edit the brief directly. Each message you send in the **Calibrate** panel counts toward your plan's copilot messages. See [Pricing](/billing/pricing). ## Approve it Select **Approve and import** on an agent with no calls yet, or **Approve and continue** otherwise. Signal needs a purpose and a line on what makes a call successful; without them it says "The brief needs a purpose and a line on what makes a call successful." Approving saves the brief as written, sets the purpose, success line, endings and parts that your calls are measured against, and approves the call reasons under **What each call is for**. On an agent with no calls it also starts the first import. Otherwise it unlocks **Import production calls** on **Agent config**. ## Change it later Open **Agent config**, select **Edit**, change the text, and select **Save and re-approve**. Saving does not change calls already on the board. They were read against the brief as it was at the time. To read every stored call against the new text, select **Re-analyze** on **Agent config** and confirm. Changes to **Matters** and to how endings are marked also reach the order of issues as new calls are analysed and when a new version arrives. * **A new Retell version does not touch your edits.** Signal records the new configuration but does not redraft the brief. * **Draft again replaces everything.** It writes a new brief from scratch and removes your edits and the conversation with them, after asking you to confirm. If calls are already imported, the new draft groups the parts by how those calls moved through your flow. * **Put designed behaviour in the brief.** If Signal flags something your agent does on purpose, answer **No** on the issue, pick **Meant to work that way**, then add the behaviour to the brief so the next reading expects it. ## Next steps Where the brief sits in setup. How the importance you set moves the board. This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.