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

# Developers

> A developer's own scores, why they are what they are, cost and quality by project, and how they use AI.

The **Developers** tab is for everyone who writes code. It shows **your own work**: your scores and what drives them, which of your projects cost the most and need the most rework, and how you use your AI tools.

**Who sees whose work:**

* **Developers** see only their own numbers.
* **Engineering managers and executives** can pick any developer they may see, or **All developers**, from the picker at the top of the tab. It starts on **You**.

The picker shows each person's team and "nOps agent" when they run the [AI ROI Agent](https://help.nops.io/ai-roi/agent/overview.md), so typing "agent" lists everyone who has it installed.

## What's on the tab

| Section | Answers |
| - | - |
| [Developer scores](#developer-scores) | How am I doing on Velocity, Productivity and Efficiency? |
| [Why this score](#why-this-score) | What raised or lowered each score, and what can I do about it? |
| [Where you stand](#where-you-stand) | What do I spend, and how does it compare? |
| [Projects](#projects) | Which projects cost the most per PR or needed the most rework? |
| [How you use AI](#how-you-use-ai) | What kinds of work do I use AI for, what drives my cost, and how could I save? |

## Developer scores

Your three [scores](https://help.nops.io/ai-roi/scores.md), each out of 100, compared with the organization. A person needs at least 5 PRs that reached production in the range for a score; otherwise the tile says why it has none.

Your scores are visible to you and to the people who manage you. Other developers never see them.

## Why this score

Pick a score to explain. The card lists the figures behind it, for example lead time, PRs per week and output for Velocity, each with your value, the organization's value and **how many points it moves your score**. The points add up to the difference between your score and the organization's.

Below the figures, **How to raise it** gives up to three tips, starting with the figure that costs you the most points.

No prompt text is read for any of this. The figures come from your code host, your AI tools' billing and, if installed, the AI ROI Agent.

## Where you stand

Four tiles and a chart of your AI coding spend by tool over the range:

| Tile | Meaning |
| - | - |
| **AI spend** | Your AI coding spend (Claude Code, Cursor, Copilot), with the organization's per-engineer figure beside it. |
| **PRs to production** | Your PRs that reached production. |
| **Cost per PR** | Your AI cost per PR that reached production. |
| **Rework** | The estimated share of your AI-assisted PRs that needed rework. |

## Projects

A project is a Linear project or Jira epic when your PR names a ticket, otherwise its repository. Every merged PR lands in exactly one project.

### How projects compare

A scatter chart. Each dot is a project: further right means a higher median AI cost per PR, higher up means more estimated rework, and a bigger dot means more AI cost. The dashed lines mark the median project. **Lower left is better.**

### Project by project

| Column | Meaning |
| - | - |
| **Project** | The project, and its mix of work types by AI cost. |
| **AI cost** | AI cost of the project's merged PRs. |
| **PRs** | Merged PRs. |
| **Cost / PR** | Median AI cost per PR. |
| **Rework** | Estimated rework rate. |
| **Merge** | Median time to merge. |
| **Vs similar** | How the project compares with the median project. |

The **Vs similar** verdict is one of:

| Verdict | When |
| - | - |
| **Too few PRs** | Fewer than 3 PRs with a cost. Medians say little yet. |
| **Rework** | Rework of 15% or more, and at least twice the median project's. |
| **Cost per PR** | Median cost per PR at least 1.5× the median project's. |
| **Better** | No worse than the median project on either. |
| **In line** | Anything else. |

Use it to find the projects worth copying (what works there?) and the ones worth a second look.

## How you use AI

Three cards about one person's AI use over the selected range. Engineering managers and executives see the developer picked at the top of the tab; everyone else sees their own. When **All developers** is picked, this section shows your own.

### Work types

Your prompts as the [AI ROI Agent](https://help.nops.io/ai-roi/agent/overview.md) labelled them (Build, Fix, Understand, Docs, Ship, Other), and the Claude Code cost that followed each type. A follow-up prompt keeps the type of the one before it. Cursor prompts are counted, but Cursor bills per hour with no work type, so its cost isn't split here.

Needs the AI ROI Agent with prompt labels turned on.

### Cost drivers

What shaped your Claude Code cost, each compared with the previous period:

| Driver | What it shows |
| - | - |
| **Cache** | Input read from the prompt cache, at a tenth of the price. Higher is cheaper. |
| **MCP tools** | Turns that called an MCP tool, and their share of cost. Large MCP results make every following turn more expensive. |
| **Background requests** | Requests nobody typed, such as prompt suggestions and conversation summaries. |
| **Effort** | How much of the cost ran at a high reasoning effort setting. |
| **Tool calls** | How many tool calls ran, and how many failed. |
| **Stuck sessions** | Sessions that repeated the same command or hit a run of failing tool calls. |

These come from Claude Code's own telemetry, priced at list price, through the AI ROI Agent.

### Recommendations for you

Open nOps [recommendations](https://help.nops.io/inform/recommendations) about your own AI use, such as a cheaper model for the same work or prompt caching, largest saving first. Ignored recommendations and ones already in progress or done are left out.

## Related

* [Scores](https://help.nops.io/ai-roi/scores.md)
* [How the numbers work](https://help.nops.io/ai-roi/how-the-numbers-work.md)
* [Install the AI ROI Agent](https://help.nops.io/ai-roi/agent/install.md)


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