Workflows

Build complex multi-step AI orchestrations with YAML/JSON. Chain unlimited tools, pass outputs between steps, and create powerful automated reasoning processes.

What are Workflows?

Workflows let you chain multiple AI tools together into automated sequences. Each step can use outputs from previous steps, run in parallel, or branch conditionally. Think of them as recipes for collective intelligence.

Is This Just Agent Chaining?

No, it's MORE sophisticated than simple chaining. Here's the difference:

Simple Agent Chaining (Basic)

TachiBot Swarm (Advanced)

Key Differences

• Parallel execution - 4 models run simultaneously, not sequentially
• Multi-round debates - Models argue and refine for N rounds
• Different modes - Collaborative vs Debate vs Deep-reasoning
• Synchronization - Combines outputs intelligently, not just concatenation
• Adversarial verification - Models challenge each other's outputs

Real-Time Verification with Live Search

TachiBot workflows can verify outputs against real-time information using Perplexity or Grok live search. This prevents hallucinations by grounding AI responses in actual, up-to-date data.

Why This Matters

• Prevents hallucinations - Models can't make up outdated information
• Real-time accuracy - Get information from the past week, day, or hour
• Cross-verification - Compare multiple search sources (Perplexity + Grok)
• Fact-checking - Use verifier tool to validate claims against search results
• Recency filters - Perplexity and Grok both support time-based filtering*

Basic Workflow Structure

Variable Interpolation

Use ${variable_name} to reference outputs from previous steps:

Complete Example: Swarm Intelligence

The swarm-think workflow demonstrates TachiBot's orchestration power:

Running Workflows

Workflow Features

Parallel Execution

TachiBot supports explicit parallel execution. Steps marked with parallel: true run simultaneously, dramatically reducing execution time.

Method 1: Group Parallel Steps (Recommended)

Use a single step with parallel: true and multiple tools:

Method 2: Individual Parallel Steps

Mark individual steps with parallel: true. All consecutive parallel steps run together:

How It Works

• Automatic batching - The workflow engine batches consecutive parallel: true steps
• Wait for completion - The next non-parallel step waits for all parallel steps to finish
• Variable access - Each parallel step outputs to its own variable, accessible in later steps
• Error handling - If one parallel step fails, others continue; errors are collected
• Performance gain - 4 parallel steps take ~1x time instead of 4x sequential time

Output Passing

Each step can save its output to a variable using output: variable_name. Later steps reference it with ${variable_name}.

Unlimited Steps

Chain as many steps as needed. Create complex multi-stage reasoning processes with dozens of steps.

JSON Support

Workflows work with both YAML and JSON formats:

Configuring Workflow Output

Control how step outputs are displayed using the output configuration in your workflow YAML/JSON.

Output Parameters

Examples by Workflow Type

Comprehensive Analysis (Show Everything)

Research Pipeline (Custom Limit)

Quick Brainstorm (Default)

Runtime Override

Override workflow settings at runtime using CLI parameters:

Understanding Truncation Messages

When output is truncated, you'll see informative messages:

This tells you the actual size, applied limit, and how to see the full output.

Best Practices

• Start with diverse perspectives (multiple models)
• Use synchronization steps to combine insights
• Add challenge/debate steps to improve quality
• End with synthesis for final recommendations
• Name variables clearly (research_findings not r1)
• Use parallel steps when inputs don't depend on each other
• Set truncateSteps: false for comprehensive analysis workflows
• Increase maxStepTokens for research-heavy workflows

📝 How to Add Custom Workflows

TachiBot supports multiple ways to add and organize workflows. Choose the approach that best fits your use case.

For Different User Types

🔧 Contributors (Source Code)

If you're running TachiBot from source, add workflows directly to the package:

👥 Teams (Project-Specific)

Share workflows via git - they'll be discovered automatically:

Now everyone on the team can run: workflow run deploy

🧑 Individuals (Personal)

Create personal workflows that work with any TachiBot installation:

✅ Works with Claude Desktop (MCPB) - no rebuild needed!

⚡ Power Users (Ad-Hoc)

Run workflows from anywhere without registration:

Discovery Order (Priority)

When you run workflow run my-flow, TachiBot searches in this order:

1. Project: .tachibot/workflows/my-flow.yaml (checked first)
2. User: ~/.config/tachibot/workflows/my-flow.yaml (checked second)
3. Built-in: <package>/workflows/my-flow.yaml (checked last)

First match wins! This lets you override built-in workflows with your own versions.

Subdirectory Organization

Workflows are discovered recursively (max 4 levels deep):

All found automatically! Organize however you like.

Best Practices by Use Case

Troubleshooting