# www.inferable.ai

> AI-optimized mirror of www.inferable.ai containing 43 pages totalling 25,461 words of clean markdown content, structured data, and semantic HTML. Original source: https://www.inferable.ai/. Last updated: 2026-05-01T13:23:57.127Z.

Each page is available as HTML (with JSON-LD structured data) and Markdown (text-only, ideal for LLMs and RAG).

## Homepage

- [Inferable - Joined Xero](/site-root.html): Inferable has joined Xero to continue our work on durable workflow orchestration. (77 words)

## Articles & Blog Posts

- [What are Sundays for?](/blog/posts/model-temperature-first-principles/index.html): A deep dive into how temperature works in LLMs, with practical examples of different temperature settings and their effects (1,016 words)
- [TL;DR](/blog/posts/functions-as-ai-agents/index.html): Exploring the concept of AI agents as primitive units of execution, similar to functions but with fuzzy contracts, and the challenges Inferable aims to solve. (1,542 words)
- [blog/posts/postgres-nodejs-longpolling/index.html](/blog/posts/postgres-nodejs-longpolling/index.html) (1 words)
- [Tool Calling in Large Language Models](/blog/posts/dynamic-tools/index.html): Learn how to build a TypeScript application that dynamically attaches tools to LLMs for efficient function calling and reduced token usage. (1,102 words)
- [The Challenge of Reliable AI Agent Tool Execution](/blog/posts/distributed-tool-calling-message-queues/index.html): Learn how to implement reliable distributed tool calling for AI agents using message queues. Ensure at-least-once execution with no duplicates. (1,066 words)
- [Prerequisites](/blog/posts/ai-agent-go-inferable/index.html): In this tutorial, we'll build a simple AI agent that manages inventory operations using Go and Inferable. Our agent will be able to check stock levels, process orders, and restock items - all through natural language commands. (837 words)
- [What we're trying to do.](/blog/posts/text-to-sql-agents/index.html): Learn how to build a text-to-sql agent from first principles, including how to get the model to understand your database schema, how to generate SQL queries, and how to add deterministic guardrails. (1,210 words)
- [The Basic Pattern](/blog/posts/you-dont-need-tool-calling/index.html): Implement your own tool calling with LLM structured outputs for fun and profit (1,283 words)
- [The tradeoffs](/blog/posts/semantic-boundary-detection-rag-agents/index.html): Learn how semantic boundary detection can enhance RAG systems for real-time AI agents by improving context management and information processing efficiency. (1,245 words)
- [Setting up](/blog/posts/sqlite-rag/index.html): Learn how to build a local movie recommendation system using on-device RAG with Ollama and SQLite, complete with embeddings and vector search (930 words)
- [Data Connector](/blog/posts/how-we-use-inferable-at-inferable/index.html): Discover how we dogfood Inferable to manage our own infrastructure, analyze data, and automate workflows. Real-world use cases and best practices. (811 words)
- [What if we could run our tools without exposing them to the public internet?](/blog/posts/on-premise-execution/index.html): Learn why traditional synchronous tool calls in AI agents come with high security, operational, and compliance costs, and discover alternative approaches for better scalability. (1,199 words)
- [The Core Components](/blog/posts/ai-agent-bash-inferable/index.html): While most developers reach for Python, JavaScript, or Go when building AI agents, there's something uniquely appealing about using bash. Today, I'll show you how to build AI agents using nothing but bash, curl, and jq. (597 words)
- [Structure Matters: Organizing for AI Understanding](/blog/posts/writing-code-for-coding-agents/index.html): How to help coding agents help you in writing grokkable code. Some practical advice from my own personal experience of getting machines to write code for me. (916 words)
- [Transforming LLM Output into Structured JSON](/blog/posts/llm-json-parser-structured-output/index.html): Learn how to build reliable JSON parsing for LLMs using Zod schemas and recursive retries. A practical guide to getting deterministic structured outputs from any language model. (912 words)
- [The Problem: Distributed Job Processing](/blog/posts/postgres-skip-locked/index.html): Using SKIP LOCKED to distribute work across machines in a distributed system is a popular pattern. We explore why, the alternatives, and a real world example from our own codebase. (709 words)
- [Inferable Data Connector](/blog/posts/announcing-data-connector/index.html): A secure bridge that enables natural language queries for databases and APIs while maintaining data privacy and security. Features PostgreSQL, MySQL, SQLite, OpenAPI, and GraphQL support. (703 words)
- [What is Row-Level Security (RLS)?](/blog/posts/understanding-postgres-row-security/index.html): How to implement multi-user authentication using Postgres Row-Level Security (RLS) with a practical example of building a key-value store (621 words)
- [Common Issues with AI-Driven Workflows](/blog/posts/announcing-durable-workflows/index.html): Inferable Workflows is a way to mix and match agent results and programmatic control flow. (763 words)
- [blog/posts/ai-workflow-go/index.html](/blog/posts/ai-workflow-go/index.html) (1 words)
- [blog/posts/structured-outputs-all-you-need/index.html](/blog/posts/structured-outputs-all-you-need/index.html) (1 words)
- [They are sortable](/blog/posts/ulids-are-awesome/index.html): Learn how ULIDs are a better alternative to UUIDs for unique identifiers, and all the hidden benefits they provide. (653 words)
- [Why .netrc?](/blog/posts/using-netrc/index.html): Learn how to securely store and manage CLI credentials using .netrc files. A comprehensive guide to implementation and best practices. (267 words)
- [A Different Approach: Progressive Context Enrichment](/blog/posts/llm-progressive-context-encrichment/index.html): Learn how progressive context enrichment can improve LLM performance by optimizing attention and context delivery, based on our production experience with GPT-4 and Claude. (692 words)
- [DON'T DO THIS](/blog/posts/understanding-docker-secret-mounts/index.html): A comprehensive guide to using Docker secret mounts correctly, avoiding common mistakes, and implementing secure practices for handling sensitive data in containers. (347 words)
- [Example Use Cases](/blog/posts/zapier-integration/index.html): Connect Inferable to thousands of apps with our new Zapier integration. Automate AI workflows by triggering Inferable Runs from your favorite tools. (159 words)
- [What this means for you](/blog/posts/now-open-source/index.html): Discover how Inferable's open-source release enables self-hosting, customization, and community contributions under the MIT license (243 words)
- [What is Langfuse?](/blog/posts/langfuse-integration/index.html): Introducing our native integration with Langfuse for comprehensive LLM observability, tracing, and evaluation capabilities. (155 words)
- [Common Issues with Data Extraction from LLMs](/blog/posts/announcing-l1m/index.html): L1M is a simple open-source API for extracting structured data from text and images using LLMs. (589 words)
- [Prerequisites](/blog/posts/ai-agent-go-dotnet/index.html): Create a powerful inventory management AI agent using .NET and Inferable. Handle stock checks and orders through natural language commands. (851 words)
- [Features](/blog/posts/assistant-ui/index.html): Build beautiful conversational AI interfaces with Inferable and assistant-ui. Open-source components for chat-based LLM applications. (276 words)
- [Chat with your PostgreSQL, MySQL, SQLite, OpenAPI, GraphQL](/use-cases/data-connector/index.html): Like ChatGPT, but for your Databases and APIs! Chat with your data systems securely without exposing credentials. Supports PostgreSQL, MySQL, SQLite, OpenAPI, GraphQL, and more., Transform how you interact with databases and APIs using Data Connector - the open-source tool that lets you chat naturally with your data sources! 🚀

Data Connector brings natural language understanding to PostgreSQL, MySQL, SQLite, OpenAPI, GraphQL and more. Simply ask questions in plain English and get the data you need.

✨ Key Features:
- Chat with databases and APIs in natural language
- Self-host for complete control of your data
- Secure credential management
- Quick Docker-based setup

🙌 Perfect for:
- Local/staging database management
- Arbitrary queries with 
- Production analytics queries
- Interactive OpenAPI exploration

🔒 Enterprise-Grade Security:
- Credentials stay in your infrastructure
- Privacy Mode for sensitive operations
- Query approval system

Powered by Inferable Agents - The open-source platform for distributed agents.

https://www.inferable.ai/use-cases/data-connector
https://github.com/inferablehq/inferable/tree/main/data-connector (762 words)
- [What if your Support Engineer team had an AI agent that helps do less grunt work?](/use-cases/tier-2-support-with-ai/index.html): Transform your Support Engineer operations with AI tools that connect to your existing systems. Reduce resolution times and eliminate context switching. (528 words)
- [How humans at me&u save 630 hours of busy work per month with Inferable](/case-studies/meandu/index.html): Learn how me&u leveraged Inferable's AI agent platform to save 630 hours of busy work per month and handle 4.5x higher volume with the same team. (818 words)
- [Terms and Conditions](/terms-of-service/index.html): Read and understand the terms of service for using Inferable's AI agent platform, including usage guidelines, responsibilities, and legal requirements. (574 words)
- [Privacy Policy](/privacy-policy/index.html): Learn about how Inferable's AI agent platform handles your data, ensures privacy, and maintains security in AI agent deployments. (487 words)
- [Inferable Blog](/blog/index.html): Stay updated with the latest insights, tutorials, and news about AI agents, deployment strategies, and best practices from the Inferable team. (197 words)
- [Transparent, Consumption-Based Pricing](/pricing/index.html): Explore Inferable's flexible pricing options for our AI agent platform. Choose between our managed cloud solution or self-hosted deployment for your AI agent needs. (149 words)
- [goto/docs/index.html](/goto/docs/index.html) (1 words)
- [Security Without Compromise](/security/index.html): Enterprise-grade security and privacy features for AI agent deployments. Learn about Inferable's security model, data privacy, and compliance measures. (169 words)
- [goto/app/index.html](/goto/app/index.html) (1 words)
- [goto/slack/index.html](/goto/slack/index.html) (1 words)

## Resources

- [Full Page Index](/index.html): Browse all cached pages with rich metadata
- [About This Cache](/content/about.html): Methodology, technical details, and usage guidelines
- [XML Sitemap](/content/sitemap.xml): Machine-readable sitemap for crawler discovery
- [Robots.txt](/content/robots.txt): Crawler directives