AGISTRY DOCUMENTATION
  • Overview
    • Introduction
  • How Agistry works?
  • Roadmap
  • agistry hub
  • Dashboard
  • Create your first Agent
  • Manage your Agents
  • Triggers
  • Adapters & Modules
  • Workflows
  • API Keys
  • Enterprise
  • Framework
    • Core Concepts
    • Getting Started
    • Building and Deploying
  • Execution Model
    • SDK
      • Authentication
      • Adapter Calls
      • Design Flow
    • Adapters
      • Adapter Specification
      • Adapter Schema
      • Adapter Execution
  • Registry
    • Registry Design
    • Capability Matching
  • official links
    • Website
    • GitHub
  • X/Twitter
  • Telegram
Powered by GitBook
On this page
Export as PDF
  1. Execution Model
  2. SDK

Design Flow

Agistry is built to help you create intelligent, LLM-powered workflows by chaining modular adapters together — declaratively and remotely.

Rather than hardcoding logic, you define high-level intent, and Agistry takes care of:

  • Tool orchestration

  • Prompt building

  • Context passing

  • Execution

  • Logging and side-effects

Everything is adapterized, managed through Agistry Hub, and executed from a single line of code.

Core Design Philosophy

  • Intent-first → You describe what should happen, not how

  • Adapters-as-a-Service → Each tool is a standalone, composable function

  • Control → All logic lives in the Hub UI, not in your code

  • LLM-optional → You can use LLMs when needed, or skip them entirely

  • Recursive / Agent-compatible → The system supports tool planning and flow recursion

Agistry gives you a new way to think about building AI-powered systems — not by wiring prompts and APIs manually, but by defining intent and composing intelligent tools. Whether you're building a contract analyzer, support assistant, or automated research agent, Agistry lets you focus on the what and forget the how.

PreviousAdapter CallsNextAdapters

Last updated 17 days ago