Browse older CallSphere articles on AI voice agents, contact center automation, and conversational AI.
From the blog
Build a production RAG agent with LangChain, then measure faithfulness, answer relevance, and context precision with RAGAS. The four metrics that matter and how to wire them up.
Non-deterministic agents break silently when prompts, models, or tools change. Build a regression pipeline with frozen datasets, semantic diffing, and gate thresholds.
How to build a safety eval pipeline that runs known jailbreak corpora, prompt-injection attacks, and tool-misuse scenarios on every release — and gates merges on it.
How to stream tokens, tool-call deltas, and intermediate steps from an agent — with code for both the OpenAI Agents SDK and LangChain — and the gotchas that bite in production.
A practical guide to running SWE-bench (and it Verified / Lite) on your own coding agent, plus the cheaper internal benchmarks that actually move the needle.
Streaming changes the eval game — final-answer correctness isn't enough when users perceive the answer one token at a time. Here's the metric set that matters.
Your agent picked the wrong tool 12% of the time and the final answer was still right. That's a latent bug. Here's the eval pipeline that surfaces it.
A real workflow: user complaint → LangSmith trace → reproduce in dataset → fix → ship → re-eval. Principal-engineer notes, real numbers, honest tradeoffs.
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.
Get notified when we publish new articles on AI voice agents, automation, and industry insights. No spam, unsubscribe anytime.
Try our live demo -- no signup required. Talk to an AI voice agent right now.
