SQLiteSession: Building Persistent Conversations for AI Agents
Learn how to use SQLiteSession in the OpenAI Agents SDK to build persistent multi-turn conversations with automatic history retrieval, storage, and session limits.
9 min read
Archive page 1082 of 1230
AI Voice Agent Insights & Guides
Browse older CallSphere articles on AI voice agents, contact center automation, and conversational AI.
11,066 articlesArchive page 1082
From the blog
Latest articles
Building a Stateful Customer Service Agent with Persistent Sessions
End-to-end tutorial for building a production-ready stateful customer service agent with database integration, order history, multi-turn issue resolution, and persistent sessions.
12 min read
StreamedAudioInput: Real-Time Voice Interaction with Activity Detection
Build real-time voice agents using StreamedAudioInput with continuous microphone streaming, voice activity detection (VAD), turn detection, and lifecycle events for natural conversational flow.
11 min read
Speech-to-Text and Text-to-Speech for Voice Agent Pipelines
Configure STT and TTS models for OpenAI voice agent pipelines — Whisper integration, language and prompt settings, voice selection, streaming TTS, and custom model implementations.
10 min read
Telephony Integration for Voice Agents: Connecting to Phone Systems
Connect your AI voice agents to real phone systems using SIP, Twilio, and WebSocket transport with the OpenAI Realtime API for inbound and outbound call handling.
17 min read
Testing and Red-Teaming Your Agent Guardrail System
Learn how to systematically test and red-team your AI agent guardrails with adversarial prompt injection detection, guardrail bypass attempts, automated test suites, and continuous evaluation pipelines.
11 min read
Tool Filtering and Approval Policies for MCP Servers
Implement secure MCP agents with static and dynamic tool filtering using create_static_tool_filter, ToolFilterContext-based dynamic filters, and granular approval policies for safe tool execution.
13 min read
Tool Guardrails: Protecting Function Execution
Learn how to implement tool input and output guardrails in the OpenAI Agents SDK to validate function arguments, skip dangerous calls, and replace tool outputs before they reach the agent.
11 min read
Tool Namespaces: Organizing Agent Capabilities at Scale
Learn how to use tool_namespace() in the OpenAI Agents SDK to group, organize, and dynamically load agent tools at scale, preventing name collisions and improving maintainability.
10 min read
Subscribe to our newsletter
Get notified when we publish new articles on AI voice agents, automation, and industry insights. No spam, unsubscribe anytime.
Ready to see AI voice agents in action?
Try our live demo -- no signup required. Talk to an AI voice agent right now.