Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.powabase.ai/llms.txt

Use this file to discover all available pages before exploring further.

Why AI Coding Assistants?

The platform’s REST API is the primary interface for building AI applications. AI coding assistants can help you write integration code faster by understanding the API structure, generating correct requests, and debugging responses. Because every endpoint follows consistent patterns (authentication, error format, streaming protocol), an AI assistant with the right context can produce production-quality integration code with minimal guidance.

Getting Started with Claude Code

Claude Code works particularly well with the Agentic Platform API because it can read this documentation, understand the type system, and generate correct API calls in Python, TypeScript, or cURL. To get the best results, provide Claude Code with your project’s base URL and API key, and reference the specific API section you’re working with.
Share your project contextTell your coding assistant: “I’m building with the Agentic Platform API. My base URL is {BASE_URL} and I’m using the service_role key for authentication. I need to [create a knowledge base / build an agent / set up a workflow].” This gives the assistant enough context to generate correct code.

Common Patterns

These are the most common tasks AI coding assistants help with when integrating the Agentic Platform:
TaskWhat to Ask ForKey API Endpoints
RAG pipeline setupUpload documents, create KB, index, and search/api/sources/upload, /api/knowledge-bases, /api/knowledge-bases//search
Agent creationCreate agent with tools and KB, test with streaming/api/agents, /api/agents//tools, /api/agents//run/stream
SSE stream parsingParse Server-Sent Events in your language/api/agents//run/stream (data: format)
Multi-agent setupCreate orchestration with entity agents/api/orchestrations, /api/orchestrations//entities
Workflow automationBuild workflow graph with blocks and edges/api/workflows, /api/workflows//graph
Webhook integrationDeploy workflow and set up external trigger/api/workflows//deploy, /api/workflows//arm

Upcoming: Skill Framework

We are developing a skill.md framework that will give AI coding assistants deep, structured knowledge of the Agentic Platform API. Instead of relying on general documentation, the skill file will provide the assistant with decision trees, common patterns, error handling strategies, and code templates — enabling it to build complete integrations autonomously. The skill framework will include: API reference in a format optimized for LLM consumption, decision logic for choosing indexing strategies and retrieval methods, end-to-end integration templates for common use cases (RAG chatbot, document processing pipeline, multi-agent support team), streaming event parsers for all three languages, and error recovery patterns.
Coming soonThe skill.md framework is under active development. When released, you’ll be able to add it to your project’s CLAUDE.md or .cursorrules file to give your AI assistant full platform knowledge.

Tips for All AI Assistants

Regardless of which AI coding assistant you use, these practices will improve your results:
TipWhy
Provide your base URL and API key formatThe assistant can generate ready-to-run code instead of placeholder-filled templates
Reference specific API sections”Use the Knowledge Bases API to…” is more effective than “set up search”
Ask for streaming code in your specific languageSSE parsing differs significantly between Python (requests), TypeScript (fetch), and Go
Request error handlingThe API returns consistent error objects — ask the assistant to handle them
Start with the Quickstart patternUpload → Index → Agent → Stream is the canonical flow

Next Steps

Quickstart

The canonical RAG agent flow to give your AI assistant as context.

Streaming & SSE

Understand the streaming protocol for code generation.

Platform Overview

High-level architecture context for your AI assistant.