# LLM & Agent Evaluation labeling interfaces

A gallery of labeling and evaluation interfaces built with Label Studio Enterprise programmable interfaces. Each entry is a starting point to adapt, not a fixed template.

**URL:** https://humansignal.com/use-cases/llm-agent-evaluation

## LLM & Agent Evaluation interfaces (2)

### Multi-Turn Conversation Evaluation

**Category:** LLM & Agent Evaluation  
**URL:** https://humansignal.com/use-cases/multi-turn-conversation-evaluation

Review an assistant conversation one turn at a time, score each turn against a rubric, flag issues, highlight evidence spans, and give a conversation-level verdict.

Multi-turn failures accumulate. A turn that looks fine on its own is wrong given what the user said three turns earlier, so the reviewer needs the whole transcript in view while grading one turn. This interface does that.

Each assistant turn gets four 1 to 5 rubric scores, issue flags, notes, and text spans marked as evidence, claim, or correction; attached assets such as images, code, tables, and audio render inline. A conversation-level rubric at the end computes a verdict (Excellent, Good, Mixed, Poor) and takes summary notes.

### Agent Trace Evaluation

**Category:** LLM & Agent Evaluation  
**URL:** https://humansignal.com/use-cases/agent-trace-evaluation

Read a multi-step LLM agent trace, rate each step correct, partial, or incorrect, score the run against a rubric, tag failure modes, and set an overall verdict, each saved as its own result.

An agent run is not one answer to grade. It is reasoning, tool calls, subagents, artifacts, and errors, and the failure is usually somewhere in the middle. This interface lays the whole trace out so a reviewer can find it.

Steps render in order with their arguments, results, tokens, and latency, and a minimap sized by latency, tokens, or cost shows where the run spent its budget. Reviewers rate each step, set a verdict, score a configurable rubric (helpfulness, faithfulness, efficiency, tool use, and instruction following by default), tag failure modes like hallucination or wrong tool, and write a critique.

Each section saves independently, so partial reviews are fine. Verdicts, step ratings, failure modes, and rubric items are all parameters.

---

Generated from the HumanSignal CMS at build time. HTML version: https://humansignal.com/use-cases/llm-agent-evaluation