How to Build a Golden Dataset for Production AI Agents
A principal engineer's playbook for curating, versioning, and growing a golden dataset for an agent — from production trace mining to annotation queues in LangSmith.
12 min read
Archive page 464 of 1224
AI Voice Agent Insights & Guides
Browse older CallSphere articles on AI voice agents, contact center automation, and conversational AI.
11,016 articlesArchive page 464
From the blog
Latest articles
Evaluating Multi-Step Tool-Using Agents: Why End-to-End Metrics Lie
A 'did the agent answer correctly?' pass/fail hides broken tool calls, wasted tokens, and silent retries. Here is how to evaluate intermediate steps.
13 min read
Anthropic's 10 Pre-Built Finance Agent Templates: Pitchbooks, KYC, Close
Anthropic unveiled 10 pre-built finance agent templates on May 5, 2026 across pitchbook building, KYC screening, and month-end close. What each template does and the hours it replaces.
8 min read
After-Hours Voice AI vs ServiceNow Project Arc: How They Stack
This week's NVIDIA + ServiceNow Project Arc news is about desktop agents for employees. CallSphere After-Hours covers the phone line. Here is how the two fit together.
7 min read
Browser Agents with LangGraph + Playwright: Visual Evaluation Pipelines That Don't Lie
Build a browser agent with LangGraph and Playwright that does multi-step web tasks, then ground-truth its work with visual diffs and DOM-based evaluators.
13 min read
Building Your First Agent with the OpenAI Agents SDK in 2026: A Hands-On Walkthrough
Step-by-step build of a working agent with the OpenAI Agents SDK — Agent class, tools, handoffs, tracing — plus an eval pipeline that catches regressions before merge.
13 min read
OpenAI B2B Signals: Frontier Companies Use 3.5x More AI Per Employee
OpenAI's new B2B Signals research finds frontier companies use 3.5x more AI intelligence per employee — what it means and how to close the gap.
7 min read
LangGraph Checkpointers in Production: Durable, Resumable Agents with Eval Replay
Use LangGraph's checkpointer to make agents resumable across crashes and human-in-the-loop pauses, then replay any checkpoint into your eval pipeline.
13 min read
IT-Team-Governed AI Agents: mrc's May 2026 Move
mrc shipped IT-team-governed AI agents in May 2026 — what it means for who owns agents in the enterprise, and where customer-facing voice fits.
7 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.