# Read the Profiler Overview

Read an agent's answer quality, latency, spend and per-node breakdown on the Profiler's Overview, and follow the trade-off card to the node that costs the time.

The **Overview** is the Profiler's answer to "how is this agent doing?". It leads with quality, because a fast cheap agent that answers badly is not doing well, and then shows what that quality costs in time and money.

**Who can use it:** the **Builder** role or higher, in a tenant licensed for agents.

## Answer quality

![The Profiler Overview: an Answer quality card with a mean judge score out of five and a bar split into helpful, partial, wrong and refused, latency percentiles, spend and request counts beside it, and a Trade-off card naming a node.](https://docs.katonic.ai/img/agents/profiler-overview/profiler-overview.png)
*The Overview leads with answer quality, then what that quality costs in latency and spend, and names the node that dominates the run.*

**Answer quality** is the first card. It shows the mean judge score out of five with its change against the previous window, how many traces were evaluated out of how many exist, and a bar splitting those answers into **Helpful**, **Partial**, **Wrong** and **Refused**. Where the judge reports them, hallucination and refusal rates follow.

If no judge has run, the card says auto-eval is not configured and that the Profiler cannot tell you whether the answers are good until a judge runs, and offers **Enable auto-eval**, which opens Evaluations.

Beneath it sit the figures that quality costs: the latency percentiles **p50**, **p95** and **p99** with the change on p99, total spend with the average per request, and the request count. A sample too small to be meaningful is marked as such rather than printed.

## The trade-off

When one node dominates, a **Trade-off** card appears, marked auto-detected. It names the node, says what share of latency and of output tokens it takes, and then says whether that is worth it: either the node drives a measurable share of the helpfulness uplift over the previous version, in which case the card explains that the ways to get the time back (a smaller model, a lower token cap, a shorter prompt) will also cost quality, or it drives none, in which case the card calls it a probable regression.

Its three actions are to tune that node in the Optimizer, to compare with the previous version, and to accept the trade-off, which dismisses the card for the session.

## Anatomy

![The per-node breakdown listing each node with its kind, a bar, its average latency, its share of the total, tokens per call and call count, the bottleneck marked, beside a latency distribution histogram with p50, p95 and p99 markers.](https://docs.katonic.ai/img/agents/profiler-overview/profiler-anatomy.png)
*Anatomy breaks the agent into its nodes by time or by cost, marking the bottleneck; a row opens that node. Latency distribution buckets the window's traces with the percentile markers.*

**Anatomy** breaks the agent into its nodes. **Time** and **Cost** switch what the rows are sorted and sized by; the **Quality** view is present but dimmed, and a note explains that per-node quality needs prompt-section tagging and per-node judge scores.

Each row names the node, its kind, a bar, the average latency or the spend, the share of the total, the tokens per call and the number of calls, and marks the bottleneck and any node with errors. Selecting a row opens [that node's page](/agents/profiler-node).

**Latency distribution** beside it buckets the window's traces with the p50, p95 and p99 markers, and gives the mean and standard deviation where the service supplies them.

**Recent answers** closes the page with the latest traces, the filters **All**, **Low quality**, **Slow** and **Errors**, and **View all**, which opens [Traces](/agents/profiler-traces).

## Before the first trace

![The Profiler for an agent with no traces: a heading saying no traces yet for that agent, an explanation that traces appear as soon as it handles a conversation, the buttons Run a sample trace, Copy decorator and Docs, and a collapsible section headed Building your agent in code.](https://docs.katonic.ai/img/agents/profiler-overview/profiler-empty.png)
*An agent with no traces yet gets instructions instead of figures: how to produce the first trace, a copyable snippet, and a four-step guide to wiring tracing into an agent you build in code.*

An agent that has never been traced gets a different page. It says no traces yet, explains that an agent starts emitting them the moment it handles a conversation, and offers three things: **Run a sample trace**, which opens the agent so you can send it a message, **Copy decorator**, which copies a working code snippet, and **Docs**.

Below that, **Building your agent in code? Wire tracing in 4 steps** expands into installing the SDK, sending a real turn through it, sending the first trace, and setting an optional latency SLO, with a quickstart snippet you can copy.

If no agent in the tenant has been published at all, the page says so instead and points at **My agents**.

## Troubleshooting

- **Couldn't load profiler data.** The observability service returned an error. The message says this is a service error and not an absence of traces, and **Retry** repeats the request.
- **The score is a mean over very few traces.** The evaluated count sits beside it. Run more conversations, or widen the window.
- **Export is dimmed.** The window has no traces to export.

## Related

- [Profiler](/agents/profiler)
- [Look at individual answers](/agents/profiler-traces)
- [Look at one node](/agents/profiler-node)
- [Compare two versions](/agents/profiler-compare)

Source: https://docs.katonic.ai/agents/profiler-overview
