# Agentic Workflows in Practice

This chapter puts agents to work on common research tasks. Each page shows the task, what the agent does, the guardrails that keep it safe on a shared cluster, and how to check the result:

- {doc}`SLURM Jobs and Cluster Workflows <slurm_jobs_and_cluster_workflows>`: writing, submitting, monitoring, and debugging jobs.
- {doc}`Experiment Management with Agents <experiment_management_with_agents>`: logging, sweeps, and checkpoints, building on {doc}`SLURM Jobs and Cluster Workflows <slurm_jobs_and_cluster_workflows>`.
- {doc}`Working with Unfamiliar Research Codebases <unfamiliar_codebases>`: getting oriented in a new codebase, with [KempnerForge](https://github.com/KempnerInstitute/KempnerForge) as the example.
- {doc}`Refactoring Research Code into Packages <refactoring_into_packages>`: turning scripts into a tested package without changing results.
- {doc}`Literature Review and Data Exploration <literature_review_and_data_exploration>`: finding and checking sources, and exploring datasets.
- {doc}`Multi-Agent Orchestration <multi_agent_orchestration>`: chaining and coordinating several agents, and when one agent is the better choice.