Beyond the periodic table

Use R to check a language-model system. Learn where evaluation, workflows, LangChain, LangGraph and LangSmith fit.

The table lists separate text tasks. A system can join several tasks. For example, it can find a document, write an answer, and update a record. You must check the whole system as well as each task.

This section starts with one worked lesson: Compare two system versions in R. You will check invented test results. You will not call a model. You do not need an account, an API key, or Python for this lesson.

Start with the right question

An evaluation checks whether a system meets a stated requirement. A higher average score is not enough. A system can answer more questions correctly and still skip a required check before it changes a record.

The worked lesson asks you to decide whether to release version B. Release means allowing people to use a version. You will compare it with version A on the same cases. You will keep missing results in the total and check the rule used to grade each result.

What to read first

You need basic R. You should know data frames and the pipe, |>. You will run the supplied code and read its results. The lesson explains the evaluation terms when you need them. These pages give more detail:

The new lesson only reads local files and computes results in R. Other lessons on this site can run pinned local models.

Where the tools fit

The tool descriptions below were checked on 21 October 2026. They describe documented features. The worked lesson does not run these tools or test a connection between them.

LangChain gives developers model and tool interfaces. It also supports agent loops. An agent loop lets a model choose a tool, read its result, and choose a next step. Its official framework examples use Python or JavaScript/TypeScript.

LangGraph controls a workflow through explicit state and steps. State is the information kept between steps. A graph names the steps and the routes between them. It can support loops, pause for a person, and resume later. It does not require LangChain. The reviewed documentation does not list an official R version of LangGraph.

LangSmith is a separate platform for traces, datasets, and evaluations. A trace records the steps taken during a run. An SDK is a set of code tools for a service. The reviewed SDK list includes Python, JavaScript/TypeScript, Go, and Java. It does not list R. That does not prove that R cannot use its APIs. An R connection through web requests or another runtime needs a separate test. No such connection is tested here.

R also has native tools. The ellmer package supports model calls, tool use, and outputs with named fields. The vitals package organizes evaluation cases, solvers, scorers, and logs. A solver produces a result. A scorer assigns a score. These tools do not prove that R can save and resume workflows like LangGraph.

WarningA local score can still need a network call

In vitals, generate() makes model requests, and $eval() solves and scores. A scorer written in R does not make the solver network-free. The documented default uses the same model to solve and grade unless changed. A separate judge model also needs checks against independent human review.

Choose a workflow only when you need it

A fixed sequence, such as extract, check, and report, can be one R function. Use that simple form when it meets the need.

A different process may pause for a person, keep its state, and resume later. A graph runtime can help with that process. Before you claim that it recovers after a crash, test a real restart. A diagram, saved chat messages, or a checkpoint kept only in memory cannot prove that behavior.

An optional later lesson can compare these designs. This section does not yet provide a Python lab or an R-to-LangSmith connection.

Sources