# Agents

Tutorials for building agentic workflows and autonomous LLM-powered systems.

### [Autoresearch agent](https://www.union.ai/docs/v2/union/tutorials/agents/autoresearch/page.md)

Run an autonomous research loop that drives Claude Code in a GPU container to run experiments, then commits results and opens a pull request.

### [Coding agent](https://www.union.ai/docs/v2/union/tutorials/agents/code-agent/page.md)

Securely execute and iterate on LLM-generated code using a code agent with error reflection and retry logic.

### [Competitive intelligence agent](https://www.union.ai/docs/v2/union/tutorials/agents/competitive-intelligence-agent/page.md)

Fan out across competitors, extract source-cited market deltas with the You.com Search API, and build a knowledge-graph-ready intelligence table.

### [Compliance monitoring agent](https://www.union.ai/docs/v2/union/tutorials/agents/compliance-monitoring-agent/page.md)

Monitor trusted regulatory sources with the You.com Research API and route citation-precise findings to the right team.

### [Deep research](https://www.union.ai/docs/v2/union/tutorials/agents/deep-research/page.md)

Build an agentic workflow for deep research with multi-step reasoning and evaluation.

### [Field data enrichment agent](https://www.union.ai/docs/v2/union/tutorials/agents/field-data-enrichment-agent/page.md)

Enrich geo-tagged operational events with real-world public context using the You.com Search API with country and freshness targeting.

### [MLE Bot: autonomous ML engineer](https://www.union.ai/docs/v2/union/tutorials/agents/mle-bot/page.md)

An autonomous ML agent that designs, runs, and iterates on experiments using Flyte's durable sandbox for safe LLM-generated code execution.

### [Support resolution agent](https://www.union.ai/docs/v2/union/tutorials/agents/support-resolution-agent/page.md)

Ground support tickets in fresh public sources via the You.com Research API and draft cited, customer-ready replies for human review.

## Subpages

- [Autoresearch agent](https://www.union.ai/docs/v2/union/tutorials/agents/autoresearch/page.md)
  - Define the container image
  - Define the task environment
  - What changed
  - All changed files
  - Model the result
  - What changed
  - All changed files
  - The autoresearch task
  - What changed
  - All changed files
  - What changed
  - All changed files
  - Run the agent
  - Create secrets
  - Prepare the research repository
  - Run remotely
- [Coding agent](https://www.union.ai/docs/v2/union/tutorials/agents/code-agent/page.md)
  - What this example demonstrates
  - Setting up the agent environment
  - Retrieve docs
  - Code generation
  - Running the code agent
- [MLE Bot](https://www.union.ai/docs/v2/union/tutorials/agents/mle-bot/page.md)
  - TL;DR
  - The problem with LLMs and ML pipelines
  - How it works
  - What to expect
  - Declaring task environments
  - Building durable tool functions
  - Guiding the LLM with domain knowledge
  - Dataset context
  - General ML best practices
  - The agent loop: profile, design, execute, iterate
  - Dataset context
  - General ML best practices — apply these based on the dataset context above
  - Available tools
  - Monty sandbox restrictions
  - Critical patterns for using tool results
  - When fixing a previous error
  - Pipeline design — you decide the structure
  - Response format
  - Reasoning
  - Code
  - Running LLM-generated code in Flyte's sandbox
  - Dataset context
  - General ML best practices — apply these based on the dataset context above
  - Available tools
  - Monty sandbox restrictions
  - Critical patterns for using tool results
  - When fixing a previous error
  - Pipeline design — you decide the structure
  - Response format
  - Reasoning
  - Code
  - Streaming results to a live report
  - Dataset context
  - General ML best practices — apply these based on the dataset context above
  - Available tools
  - Monty sandbox restrictions
  - Critical patterns for using tool results
  - When fixing a previous error
  - Pipeline design — you decide the structure
  - Response format
  - Reasoning
  - Code
  - Running it
  - Why Flyte?
- [Deep research](https://www.union.ai/docs/v2/union/tutorials/agents/deep-research/page.md)
  - Setting up the environment
  - Generate research queries
  - Search and summarize
  - Evaluate research completeness
  - Filter results
  - Generate the final answer
  - Orchestration
  - Run the deep research agent
  - Evaluate with Weights & Biases Weave
- [Competitive intelligence agent](https://www.union.ai/docs/v2/union/tutorials/agents/competitive-intelligence-agent/page.md)
  - Setting up the environment
  - Data types
  - Search with the You.com Search API
  - Extract deltas with Claude
  - Watch one competitor
  - Orchestration
  - Run the agent
  - Create secrets
  - Run locally or remotely
- [Compliance monitoring agent](https://www.union.ai/docs/v2/union/tutorials/agents/compliance-monitoring-agent/page.md)
  - Setting up the environment
  - Data types
  - Research with the You.com Research API
  - Triage findings with Claude
  - Monitor one watch item
  - Orchestration
  - Run the agent
  - Create secrets
  - Run locally or remotely
- [Field data enrichment agent](https://www.union.ai/docs/v2/union/tutorials/agents/field-data-enrichment-agent/page.md)
  - Setting up the environment
  - Data types
  - Search with the You.com Search API
  - Enrich one event
  - Orchestration
  - Run the agent
  - Create secrets
  - Run locally or remotely
- [Support resolution agent](https://www.union.ai/docs/v2/union/tutorials/agents/support-resolution-agent/page.md)
  - Setting up the environment
  - Data types
  - Ground answers with the You.com Research API
  - Ground one ticket
  - Draft a customer-ready reply
  - Resolve one ticket
  - Orchestration
  - Run the agent
  - Create secrets
  - Run locally or remotely

---
**Source**: https://github.com/unionai/unionai-docs/blob/main/content/tutorials/agents/_index.md
**HTML**: https://www.union.ai/docs/v2/union/tutorials/agents/