> ## Documentation Index
> Fetch the complete documentation index at: https://hubify.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Agent Configuration

> Configure your multi-agent team, choose models, define specialties, set up cross-model review, and tune routing.

# Agent Configuration

Every lab has an agent team that you can customize to match your research domain. This guide covers how to add, remove, and configure agents.

## Default Agent Team

When you create a lab from a template, you get a pre-configured team:

| Agent           | Role                  | Default Model | Specialty                         |
| --------------- | --------------------- | ------------- | --------------------------------- |
| Orchestrator    | Router + manager      | Claude Opus   | Task routing, priority management |
| Research Lead   | Research strategy     | Claude Opus   | Domain-specific research          |
| Paper Lead      | Manuscript management | Claude Opus   | Writing, citations, claims        |
| Analysis Worker | Data analysis         | Claude Sonnet | Statistics, data processing       |
| Figure Worker   | Visualization         | Claude Haiku  | Plot generation, formatting       |
| Data Worker     | Data management       | Claude Haiku  | Ingestion, transformation, wiki   |

## Adding Agents

<Tabs>
  <Tab title="Web UI">
    1. Go to your lab's **Agents** view
    2. Click **Add Agent**
    3. Configure:
       * **Name**, Descriptive name (e.g., "Cosmology Lead")
       * **Role**, Lead or Worker
       * **Model**, The AI model this agent uses
       * **Specialty**, Free-text description of the agent's domain expertise
    4. Click **Create**
  </Tab>

  <Tab title="CLI">
    ```bash theme={null}
    # Add a specialized lead
    hubify agent add \
      --role lead \
      --name "Cosmology Lead" \
      --model claude-opus \
      --specialty "MCMC analysis, CMB power spectra, dark energy, bounce cosmology"

    # Add a worker
    hubify agent add \
      --role worker \
      --name "LaTeX Worker" \
      --model claude-haiku \
      --specialty "LaTeX compilation, bibliography management, figure placement"
    ```
  </Tab>
</Tabs>

## Choosing Models

Select models based on the reasoning level required:

| Reasoning Level | Recommended Models                               | Cost   |
| --------------- | ------------------------------------------------ | ------ |
| **High**        | Claude Opus 4.8, GPT-5.5, Gemini 3.1 Pro, Grok 4 | \$\$\$ |
| **Medium**      | Claude Sonnet 5, GPT-5.5 Mini, Gemini 3.1 Flash  | \$\$   |
| **Low**         | Claude Haiku 4.5                                 | \$     |

<Note>
  Leads can do work themselves (not just delegate). A Claude Opus 4.8 lead can handle complex analysis directly, while a Haiku 4.5 worker handles formatting tasks. Match the model to the agent's responsibilities.
</Note>

## Cross-Model Review Setup

Cross-model review is mandatory. Configure which external models participate:

```bash theme={null}
# Enable GPT-5.5 as a reviewer
hubify agent review-config --add-reviewer gpt-5.5 --api-key $OPENAI_API_KEY

# Enable Gemini 3.1 Pro as a reviewer
hubify agent review-config --add-reviewer gemini-3.1-pro --api-key $GOOGLE_API_KEY

# Enable Grok 4 as a reviewer
hubify agent review-config --add-reviewer grok-4 --api-key $XAI_API_KEY

# Enable Sonar Pro for live fact-checking
hubify agent review-config --add-reviewer sonar-pro --api-key $PERPLEXITY_API_KEY

# View review configuration
hubify agent review-config --show
```

The system automatically assigns reviewers from different model families:

* Claude output is reviewed by GPT-5.5, Gemini 3.1 Pro, or Grok 4
* GPT-5.5 output is reviewed by Claude Opus 4.8, Gemini 3.1 Pro, or Grok 4
* Gemini 3.1 Pro output is reviewed by Claude Opus 4.8, GPT-5.5, or Grok 4
* Grok 4 output is reviewed by Claude Opus 4.8, GPT-5.5, or Gemini 3.1 Pro

## Updating Agents

```bash theme={null}
# Change an agent's model
hubify agent update "Analysis Worker" --model claude-sonnet

# Update specialty
hubify agent update "Research Lead" --specialty "Galaxy surveys, anomaly detection, statistical methods"

# Disable an agent temporarily
hubify agent update "Figure Worker" --status inactive

# Remove an agent
hubify agent remove "Data Worker"
```

## Viewing the Team

```bash theme={null}
# List all agents
hubify agent list

# Tree view showing hierarchy
hubify agent list --tree

# View agent metrics
hubify agent metrics "Research Lead"
```

```
AGENT             ROLE      MODEL         STATUS   TASKS   QC RATE
Orchestrator      orch      claude-opus   active   342     N/A
Research Lead     lead      claude-opus   active   128     94%
Paper Lead        lead      claude-opus   active   87      97%
Analysis Worker   worker    claude-sonnet active   203     91%
Figure Worker     worker    claude-haiku  active   156     88%
Data Worker       worker    claude-haiku  active   189     95%
```

## Standup Configuration

Configure the orchestrator's standup schedule:

```bash theme={null}
# Set standup times (3x daily recommended)
hubify agent update orchestrator --standup-schedule "8:00,12:00,18:00"

# Set timezone
hubify agent update orchestrator --timezone "America/Los_Angeles"
```

Standups summarize what happened since the last check-in, flag blockers, and recommend next actions.

## Auto-Scheduling

Enable auto-scheduling so the orchestrator picks the next experiment when pods are idle:

```bash theme={null}
hubify agent update orchestrator --auto-schedule true
```

When enabled, the orchestrator monitors pod utilization and automatically deploys queued experiments to idle pods. This ensures GPUs are never sitting idle.

## Best Practices

* Use **Opus** for orchestrator and leads that make strategic decisions
* Use **Sonnet** for workers that do analysis and code generation
* Use **Haiku** for workers that do formatting, data transformation, and wiki updates
* Always have at least **two external model providers** for cross-model review
* Start with the default team and add specialists as your research demands grow