Block Agent Basics

This guide describes the benefits and components of Block Agents. Learn more about:

 

Overview

The Block Agent workflow uses a graph data structure, allowing you to build complex agents in a simpler way. You can configure a Block Agent to respond to multiple topics and move through steps within each topic. Built via JSON input defining each component of the workflow, one Block Agent can simplify unwieldy SmartFlows projects and provide overall improved performance.

 

Block Agents vs. Other Agent Types

A Block Agent workflow is ideal for complex use cases and can address some key challenges when building other types of agents.

 

The Block Agent Use Case

Your Block Agent is an intelligent virtual assistant that can handle complex, multi-step conversations—greeting callers, authenticating their identity, scheduling appointments, handling cancellations, and gracefully managing edge cases—all while maintaining context and personality throughout the interaction.

 

Key Differences with a Block Agent

  • Modularity.

    • Complex conversations are broken down into distinct, manageable units (blocks). Each Block handles a specific domain or topic.

  • Two parallel LLM calls at each Turn.

    • One call triggers functions, the second call produces a natural, context-aware AI response.

  • Always fires at least one tool.

    • At least one tool will always be defined for each Block.

    • There will always be a tool triggered.

    • Tools have the ability to trigger multiple tools at a given Turn.

  • Structured prompting approach.

    • Through a standardized approach and format for prompting, higher performing AI agents can be created.

 

Key Challenges Addressed with a Block Agent

  • Prompt Bloat

    • Due to excessive instructions packed into a single prompt, prompt bloat often results in suboptimal outcomes in various forms.

    • The Block Agent system prompt is read-only and cannot be modified. Prompting for the Block Agent is conducted through the Turn content and Edge reprompt properties.

  • Standardized Prompting

    • The lack of a standardized approach to prompting can throw off the delicate balance between creativity and science within prompt design.

    • Block Agents highlight the advantage of a scientific, structured methodology in prompt creation.

  • Function Call Latency and Accuracy

    • Prompt bloat and lack of standardization both directly impact the reliability of function calls, leading to inaccurate outcomes or functions not being triggered as intended.

    • The use of consecutive or double function calls in agent design also introduces additional latency.

  • Rules Based Design Approach

    • For other agent types, rules or tasks are embedded directly in the system prompt, contributing to prompt bloat.

    • Block Agents introduce an alternative method for defining these rules (via blocks), allowing you to enforce operational guardrails and boundaries more effectively. This agent type also opens up the potential to gain insights into turn-based telemetry.

 

Block Agent Features

Block Agents combine some elements you’re probably already familiar with when building other agent types (tools, prompts, etc.), with some powerful new components (Blocks, Turns, and Edges).

 

Main Components

  • Blocks

    • Logical groupings of related tasks, each focused on a specific objective. Think of a Block as a "topic" within a conversation.

  • Turns

    • The individual steps or instructions within a Block.

  • Edges

    • Connections between Turns that define conversational flow. The edges move the conversation on from a Turn.

  • Conditions

    • Criteria that determine when an Edge should be traversed. Conditions determine how the Edge is evaluated (can the conversation move on and where does it go next).

  • Tools

    • Enable your agent to perform a subsequent action based on the user's action. For example, a tool might capture data and detect intents during a conversation.

 

Check out the component pages linked above or the following pages to learn more about Block Agents: