# Core concepts How project data, recorded behavior, and evaluations fit together. A trace and its spans become a curated dataset case; the case and a versioned scorer feed an evaluation whose saved evidence can be compared across app changes. ## Organizations and projects [#organizations-and-projects] An **organization** owns projects and controls membership. A **project** contains traces, datasets, scorers, prompts, dashboards, and evaluation runs. Choose the project before investigating or changing data. A project slug identifies its browser route; API requests use the project ID. ## Traces and spans [#traces-and-spans] A **trace** records an execution with its input, output, timing, and status. **Spans** describe operations inside that execution, such as a model call, tool call, or function. Parent relationships preserve the execution tree. An operation's kind describes what happened. Its optional **group** associates it with a named agent or workflow. Group membership is explicit and does not change its kind or automatically apply to its children. ## Sessions, agents, and workflows [#sessions-agents-and-workflows] A **session** connects related traces, such as multiple turns of a conversation. **Agents** and **Workflows** collect operations with an explicit group name and optional version. Their operation counts are not necessarily counts of complete end-to-end workflow executions. ## Datasets and scorers [#datasets-and-scorers] A **dataset** holds cases with inputs, expected outputs, and metadata. A **scorer** evaluates trace evidence, optionally against a dataset case. It can use code or a language model. A numeric score and a pass decision are separate values. Execution errors and missing evidence must be read alongside the score; they are not automatically equivalent to a score of zero. ## Evaluation runs [#evaluation-runs] An **evaluation run** applies scorers to cases and recorded evidence. Connected runs invoke an app for each case. Re-scoring evaluates saved evidence again. Saved snapshots and scorer versions help explain what produced a result even after a dataset or scorer changes. [Send your first trace](/docs/get-started/first-trace), then follow the [evaluation guide](/docs/evaluation/runs).