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

# Agent Goal And Call Performance In DialNexa

> Set a Primary, Linear or Non-linear agent goal in DialNexa and learn how each answered call is judged, how scores, steps and success rates are calculated for calls and batch calls, and how to read Analytics.

An agent goal tells DialNexa what a successful call looks like for one agent. After every answered call, DialNexa checks the conversation against the goal and records a result: **Goal met**, **Partly met** or **Not met**. Those results build the call performance numbers you see in **Analytics**, for single calls and for batch calls.

A goal can be one sentence, or a set of steps:

* **Primary**: one goal sentence, for example "Book a product demo and confirm the customer's email address".
* **Linear**: steps that must happen in order, like a sales call that greets, qualifies, pitches and books.
* **Non-linear**: steps that can happen in any order, with your own rules for what counts as met.

This page explains how to set each type, exactly how each call is judged, and how the score, steps and success rate are calculated.

## Who Is This For

* Teams that want to know whether an agent achieves its purpose, not only whether calls connect.
* Campaign owners who compare batch calls by how many leads reached the goal, and where they dropped off.
* Anyone tuning a prompt who wants a before and after measure.

The agent goal is not required. Agents without a goal create, publish and call exactly as before; their calls simply do not appear in Analytics.

## Before You Begin

* Agent Goal and Analytics must be enabled for your workspace. They are currently available to selected workspaces; if the section is absent, check availability with DialNexa.
* You need an agent with a draft version you can edit. Published versions are read-only.
* **IVR agents** can have a goal only when the IVR menu has a **Connect to agent** step. A call that stays in the menu has no conversation to check, and calls that never reach the voice agent are not judged.
* Know what a good outcome is for this agent, in terms you could hear in the call: an appointment confirmed, a payment date agreed, an interest question answered.

## Choose A Goal Type

Each agent version has one goal of one type.

| Type | Use it when | How a call is scored |
| - | - | - |
| **Primary** | One outcome matters, for example a booked demo. | Goal met = 100%, Partly met = 50%, Not met = 0%. |
| **Linear** | The call should move through steps in a fixed order, and you want to see how far each call got. | How many steps were reached in order. Steps 1, 2 and 4 of 5 done = 40%. |
| **Non-linear** | Several things should happen, in any order, and you decide what counts as met. | Your rules decide Goal met (100%), Partly met (50%) or Not met (0%). Steps done are shown separately. |

Existing goals created before goal types were added are **Primary** goals. They work exactly as before.

## Set An Agent Goal

**1. Open the agent's settings**

Open the agent, then open the **Agent Goal** section in the settings panel.

**2. Click Enable agent goals**

Three cards appear: **Primary**, **Linear** and **Non-linear**. Hover the info icon on a card to see how that type is scored.

**3. Choose a type**

Click a card to open its editor.

**4. Describe the goal**

For **Primary**, write what the agent should achieve, up to 2000 characters. For **Linear** and **Non-linear**, write a short goal line, then add the steps. For **Non-linear**, you can also write rules. See [Write Good Steps](#write-good-steps) and [Write Rules For A Non-linear Goal](#write-rules-for-a-non-linear-goal).

**5. Optional: click Improve with AI**

DialNexa rewrites the goal, and for step goals each step and the rules, so each call can be judged more consistently. See [Improve With AI](#improve-with-ai).

**6. Save the goal**

Click **Save goal**. The goal is saved on this draft version, and a summary shows the type, the goal, the numbered steps and the rules.

**7. Publish the agent**

Live calls use the published version, so publish the agent for the goal to apply to them.

From the summary you can:

| Button | What it does |
| - | - |
| **Edit goal** | Opens the editor for the same type. |
| **Change type** | Asks you to confirm, then shows the three cards again. The current goal stays until you save the new one. |
| **Remove goal** | Asks you to confirm, then removes the goal from the draft. Publish again to stop judging live calls. |

![DialNexa Agent Goal editor with Book a demo entered, Improve with AI, Remove goal and Save goal controls.](https://mintcdn.com/dialnexa/kU1wRIHaARO2N5Jl/images/documentation/screenshots/agent-goal-editor.png?fit=max\&auto=format\&n=kU1wRIHaARO2N5Jl\&q=85\&s=bcc4c9012a0805ccdb0f591b516ca92c)

### Write Good Steps

Linear and Non-linear goals have between **2 and 8 steps**.

* Add steps one at a time: type the step and press **Enter**, or click **Add step**.
* Drag a step by its handle to reorder it. Edit a step's text in place, or delete it.
* Each step can be up to 200 characters, and no two steps can be the same.
* For a **Linear** goal, add the steps in the order they should happen. The order is part of the goal.
* Write each step as one thing you could hear or see in the call: "The agent confirms the customer's email address", not "The customer is happy".

Each step is checked on its own: it is either **done** or **not done**. There is no "partly done" for a single step.

### Write Rules For A Non-linear Goal

Rules are plain text, up to 1000 characters, that say how the steps decide the result. For example:

```text theme={null}
Goal met if step 3 and then step 5 happen, even if step 4 is skipped.
Partly met if only step 3 happens.
```

If you leave the rules empty, DialNexa uses this rule: the goal is **met** when every step happens, **partly met** when some do, and **not met** when none do.

> [!WARNING]
>
> Rules often name steps by number. If you reorder the steps after writing rules, the editor warns you: check that the step numbers in your rules still point at the right steps.

### How The Goal Follows Versions

The goal belongs to the agent version, like post-call analysis fields. The type, the steps and the rules always move together with it.

| Situation | What happens |
| - | - |
| You publish a version | The goal is published with it, and the next draft starts with the same goal. |
| You change the goal on a draft | Calls on earlier versions keep the results they already have. Calls on the new version are judged against the new goal. |
| A batch call runs | It uses the agent version it was launched with, so every call in the batch is judged against one goal. |
| You duplicate, import or create from a template | The goal is copied with the agent, including its type, steps and rules. |

Results are never recalculated. Each call keeps the result it got against the goal its version had at the time.

## Improve With AI

Short goals such as "Book a demo" leave room for interpretation. Is a customer who says "maybe next week" a success? **Improve with AI** rewrites your goal into a clearer form. Nothing is saved until you click **Save goal**, and **Undo** returns to your own words.

### Primary Goals

The rewrite becomes:

* one sentence that states the goal,
* **Goal met**: what must happen in the call for the goal to be fully met,
* **Partly met**: what counts as progress without the goal being fully met,
* **Not met**: what it looks like when the goal was not achieved.

For example, "Book a demo" might become:

```text theme={null}
Book a product demo with the customer.
Goal met: the customer agrees to a demo and a specific date and time is confirmed.
Partly met: the customer is interested but no time is fixed, or asks to be called back to schedule.
Not met: the customer declines or the call ends before a demo is discussed.
```

The rewrite aims to stay short, at most about 600 characters, so it stays easy to read and edit.

### Linear And Non-linear Goals

One **Improve with AI** button, below the steps, rewrites the goal line, every step and, for a Non-linear goal, the rules, together:

* You need a goal line and at least 2 steps first.
* The steps keep their number and their order. Each step is rewritten as one short sentence about the same thing, so step numbers in your rules still point at the same steps.
* Rules are rewritten only if you wrote some. Empty rules stay empty.
* If the rewrite would change the number of steps, leave a step blank or repeat one, DialNexa shows an error and keeps your own text.

For every type, the rewrite keeps the meaning of your goal and the language you wrote it in. It does not add new requirements, products or numbers.

> [!TIP]
>
> Spelling out what counts as done, met and partly met is the single biggest thing you can do to make results consistent. Write it yourself or let Improve with AI draft it.

## How Each Call Is Judged

DialNexa judges a call as part of the agent's existing [post-call analysis](https://dialnexa.com/docs/agent-settings/post-call-analysis.md), using the same model, after the call ends. Steps and rules do not add a separate call to the model.

### Which Calls Are Judged

| Call | Judged? |
| - | - |
| Answered by a person and completed | Yes |
| Not answered, busy or failed | No |
| Reached voicemail | No |
| Answered, but the transcript is not available | No |
| An IVR call that never reached the voice agent | No |

Calls that are not judged never count against the agent. A batch dialled at a bad time does not make the agent look worse.

### Primary Goals

For each answered call, the model works through three steps in order:

1. **Find the proof.** It copies, word for word, the line from the conversation that best shows whether the goal was met. The line can come from the customer, the agent, or a tool result such as a booking confirmation.
2. **Decide the result.** It picks Goal met, Partly met or Not met, following your goal exactly as written, including any definitions of met and partly met.
3. **Explain why.** It writes one short sentence about what was achieved and what was missed.

Finding the proof before deciding keeps results tied to what was actually said.

### Linear And Non-linear Goals

For each step, the model copies the line from the conversation that shows the step happened, then answers **done** or **not done**. A step counts as done only when its line is really in the conversation. The model then writes one short sentence about which steps happened and which did not.

**Linear goals** are scored strictly, in order:

* DialNexa works out the order itself, from where each step's line appears in the call. The model is never asked about the order.
* Progress counts the steps from step 1 onward, each happening at or after the step before it. Progress stops at the first step that was missed or happened too early.
* Steps done after a missed step are still shown on the call, marked as done after a missed step, but they do not add to the score.

| Result | When |
| - | - |
| Goal met | Every step happened, in order. |
| Partly met | At least step 1 happened, but not every step in order. |
| Not met | Step 1 did not happen. |

For example, with 5 steps:

| What happened in the call | Steps reached in order | Result | Score |
| - | - | - | - |
| Steps 1, 2, 3, 4 and 5, in order | 5 of 5 | Goal met | 100% |
| Steps 1, 2 and 4; step 3 skipped | 2 of 5 | Partly met | 40% |
| Step 2 happened before step 1 | 1 of 5 | Partly met | 20% |
| Step 1 did not happen | 0 of 5 | Not met | 0% |

**Non-linear goals** are decided by your rules:

* With your own rules, the model checks the rules against the steps and picks Goal met, Partly met or Not met.
* With no rules, DialNexa applies the default rule itself, from the steps proved by the call: every step done = Goal met, some = Partly met, none = Not met.
* The steps done, for example 4 of 5, are shown separately from the result.
* If the model says Goal met but a step it counted as done cannot be found in the conversation, the call counts as **Partly met**, because your rules may need exactly that step.
* If the model says Goal met or Partly met but none of the steps' lines can be found in the conversation, the call counts as **Not met**.

### Rules That Keep Results Honest

* **The proof must be in the call.** If the model says Goal met or Partly met but the line it copied is not in the conversation, the call counts as **Not met**. For a step goal, a step whose line is not in the conversation counts as not done.
* **The agent's instructions are not proof.** A line copied from the agent's own prompt never counts.
* **A failed action did not happen.** If the agent says "your demo is booked" but the booking tool reported an error, the booking did not happen.
* **No proof means Not met.** If nothing in the conversation relates to the goal, the result is Not met.

### What The Results Mean

| Result | Primary and Non-linear score | Linear score |
| - | - | - |
| Goal met | 100% | 100% |
| Partly met | 50% | Steps reached in order / all steps, for example 40% |
| Not met | 0% | 0% |

The goal check is internal. It does not add fields to your post-call analysis results, webhooks, exports or workflows.

## How Call Performance Is Calculated

### Success Rate For Calls

```text theme={null}
Success rate = calls with Goal met / answered calls that were judged
```

This is the same for every goal type. Partly met calls count in the total but not as successes; their progress shows in each call's [score](#score-for-a-single-call) instead. For example, 40 judged calls with 10 Goal met, 14 Partly met and 16 Not met give a success rate of 10 / 40 = **25%**.

Calls that were not answered, reached voicemail or were not judged are left out of both numbers.

### Score For A Single Call

The score shows how much of the goal happened in that call.

For example, take an agent whose Primary goal is "Book a product demo with the customer" and three of its calls:

| Call | What happened | Result | Score |
| - | - | - | - |
| Call 1 | The customer agrees and the booking tool confirms a demo for Tuesday at 4 PM. | Goal met | 100% |
| Call 2 | The customer is interested but asks to be called back next week to fix a time. | Partly met | 50% |
| Call 3 | The customer says they are not interested. | Not met | 0% |

The success rate for these three calls is 1 / 3 = **33%**, because only Call 1 fully met the goal. Call 2 still shows its progress through its 50% score.

For a Linear goal, the score is the share of steps reached in order, so a call that got through 3 of 4 steps scores 75%.

### Score Or Success Rate

The two numbers answer different questions.

| Number | Question it answers | How Partly met counts | Where you see it |
| - | - | - | - |
| Score | How close did this call get to the goal? | 50%, or for Linear the share of steps reached | Each call on the Calls tab |
| Success rate | How often was the goal fully achieved? | Not a success, but counted in the total | Overview cards, the By agent table and each batch call |

## How Batch Call Performance Is Calculated

A batch call is measured by **leads**, not by calls. A lead that was called three times because of retries still counts once.

### Each Lead Counts Once

A batch retries a lead only when the call did not connect: no answer, busy, failed or voicemail. Once a lead answers, it is not called again in that batch. So a lead has at most one judged conversation per batch, and that conversation's result is the lead's result.

| Lead | Calls | Counted as |
| - | - | - |
| Lead A | No answer, then a retry answered with Goal met | Answered, Goal met |
| Lead B | Answered first time: Partly met | Answered, Partly met |
| Lead C | No answer, then a retry with no answer | Not answered |
| Lead D | Not called yet | Not answered |

If a lead ever has more than one judged call in the same batch, its best call counts: the highest score, and the most recent call if two are tied. The same call is used for the lead's steps.

### Batch Numbers

| Number | How it is calculated |
| - | - |
| Leads | All leads in the batch. |
| Answered | Leads who picked up at least once, including through a retry. |
| Results | Goal met, Partly met and Not met leads. |
| Success rate | Leads with Goal met / leads with a result. |

For example, a batch of 100 leads where 62 answered and were judged, with 20 Goal met, 15 Partly met and 27 Not met, has a success rate of 20 / 62 = **32%**.

## Read Call Performance In Analytics

Open **Analytics** from the **Data** section of the sidebar. Only agents with a goal appear. The info icon next to the **Analytics** title links back to this page.

### Filters

| Filter | What it does |
| - | - |
| Agent | Shows one agent, or all agents. |
| Date range | Today, Last 7 days, Last 30 days, Last 90 days or All time. Ranges start at midnight and count today as one of the days. Calls are filtered by when they were made; batch calls by when the batch was created. |
| Search | Finds one call by Call ID on the Calls tab, or one batch by Batch ID on the Batch Calls tab. The full ID is required. |

### Overview Tab

* **Success rate**: across all judged calls in the range.
* **Results of answered calls**: Goal met, Partly met and Not met as one bar, with counts.
* **By agent**: one row per agent per goal. If you changed an agent's goal, including its type, steps or rules, the old and new goals get separate rows so their results never mix, marked **Current** or **Old goal**. Versions that kept the same goal share one row.

![DialNexa Analytics Overview showing success rate, answered-call outcomes and separate agent goal rows marked Old goal.](https://mintcdn.com/dialnexa/kU1wRIHaARO2N5Jl/images/documentation/screenshots/agent-goal-analytics-overview.png?fit=max\&auto=format\&n=kU1wRIHaARO2N5Jl\&q=85\&s=f08bebdb6c0ce37304dc51bcbbe997fb)

### Step Counts

Rows for a Linear or Non-linear goal have a **View steps** link. It opens the goal's steps in a window, with counts only:

| Goal type | What you see |
| - | - |
| Linear | A funnel, read top to bottom. The first row is **All answered calls** (on Batch Calls: **All leads with a result**). Then one row per step, tagged **Step 1**, **Step 2** and so on, showing how many calls got there. A call counts at a step only if it did that step and every step before it, in order. Between two rows, a red line says how many **didn't reach** the next step. |
| Non-linear | One bar per step showing how many calls **did** that step, in any order. Steps have no order, so no row is counted from the one before it. |

Every row shows its count with its unit (for example **2 calls** or **1 lead**) and its share of the first row, so you never have to judge a bar by its length. On the **Overview** tab the counts are judged calls. On the **Batch Calls** tab they are leads with a result, each counted once by its best call; this can be fewer than the batch's **Answered** column, because a lead that answered but got no result is not in the funnel.

For example, a Linear goal with 10 judged calls:

| Row | Got there | Share |
| - | - | - |
| All answered calls | 10 calls | 100% |
| ↓ 1 call didn't reach step 1 | | |
| Step 1: Greets the lead | 9 calls | 90% |
| ↓ 4 calls didn't reach step 2 | | |
| Step 2: Qualifies | 5 calls | 50% |
| ↓ 3 calls didn't reach step 3 | | |
| Step 3: Books a demo | 2 calls | 20% |

Most calls stop between step 1 and step 2, so qualifying is the step to work on.

### Calls Tab

Every judged call, newest first.

| Column | What it shows |
| - | - |
| Call ID | The call's ID, with a copy button. Paste it into [Call History](https://dialnexa.com/docs/monitoring/call-history.md) to read the transcript. |
| Agent name | The agent that made or took the call. |
| Batch ID | The batch the call belongs to, if any, with a copy button. |
| Called at | When the call was made. |
| Result | Goal met, Partly met or Not met. |
| Score | The call's score. See [Score For A Single Call](#score-for-a-single-call). |
| Steps | For Linear goals, steps reached in order, for example **2 of 5**. For Non-linear goals, steps done. Click the count to open the call's steps: for a Linear goal, a funnel of the steps reached in order, where progress stopped, and any step done after a missed step; for a Non-linear goal, each step done or not done. Primary goals show a dash. |
| Why | One short sentence about what was achieved and what was missed. |

### Batch Calls Tab

Every batch call whose agent version has a goal.

| Column | What it shows |
| - | - |
| Batch ID | The batch's ID, with a copy button. |
| Batch name | The batch name and when it was created. For a step goal, **View steps** opens the step counts for the batch's leads. |
| Agent name | The agent the batch used. |
| Leads | All leads in the batch. |
| Answered | Leads who picked up at least once. |
| Results | Goal met, Partly met and Not met leads as one bar, with counts. |
| Success rate | Leads with Goal met / leads with a result, with the counts. |

## Verify An Agent Goal

After saving and publishing, make an answered phone call with a conversation relevant to the goal. Open **Analytics**, select the agent and date range, and check its result on the **Calls** tab. For a step goal, click the **Steps** count and compare each step with the transcript in Call History. A browser test call does not appear in Analytics.

For a Non-linear goal, make a few calls that do the steps in different orders and check that the results follow your rules.

## Privacy

* Deleted calls are removed from Analytics.
* For a call removed with sensitive deletion, the result and which steps were done stay, but the reason and every line copied from the call are hidden.
* Browser test calls (web calls) are not included in Analytics.

## Troubleshooting

| Problem | What to check |
| - | - |
| Analytics is empty | The agent has no goal on the version that took the calls, or no answered calls happened in the date range. Check that the goal was saved and the agent published. |
| The Agent Goal section is missing on an IVR agent | Add a **Connect to agent** step to the IVR menu. |
| Save goal is greyed out | A Linear or Non-linear goal needs a goal line and at least 2 steps, with no two steps the same. |
| A call is missing from the Calls tab | The call was not answered, reached voicemail, was a browser test call, never reached the voice agent, or ran on a version without a goal. |
| A batch's Answered count is higher than its results | Some answered calls got no result, for example because the transcript was not available. |
| Results look inconsistent between similar calls | Make the goal say exactly what counts as Goal met and Partly met, or make each step one clear thing you can hear. Try Improve with AI. |
| A Linear call stopped early although later steps happened | A step was missed, or happened before the step that should come first. Click the Steps count to see which. |
| A Non-linear result does not match my rules | Check that the step numbers in the rules still match the steps, especially after reordering. |
| A call shows Not met but the Why sounds positive | The model's proof was not found in the conversation, so the result was counted as Not met. Read the transcript in Call History to confirm. |
| Old results did not change after editing the goal | This is expected. Results are never recalculated; new calls use the new goal. |

## Recap

* The agent goal is optional and set per agent version, as Primary, Linear or Non-linear. Publish to apply it to live calls.
* Every answered call is judged once, backed by lines from the call: Goal met, Partly met or Not met.
* Linear goals score the steps reached in order; Non-linear goals follow your rules; steps are done or not done.
* Call success rate = Goal met calls / judged calls.
* Batch success rate = Goal met leads / leads with a result, with each lead counted once by its best call.
* Step counts show how many calls or leads reached each step and where they dropped off.
* Unanswered calls and voicemail never count against the agent.

## Related Reading

> [card] [Post-Call Analysis](https://dialnexa.com/docs/agent-settings/post-call-analysis.md)
>
> Extract structured fields after every call.

> [card] [Call History](https://dialnexa.com/docs/monitoring/call-history.md)
>
> Find a call and read its transcript.

> [card] [Batch Call Retries And Statuses](https://dialnexa.com/docs/batch-calls/retries-and-statuses.md)
>
> How retries work in a batch call.

> [card] [Agent Settings Overview](https://dialnexa.com/docs/agent-settings/overview.md)
>
> Every settings area for an agent version.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.