Claude Sonnet

Voice Agents That Handle Interrupts - Chintan Agrawal and Daniel Wirjo, AWS

Jul 20, 2026 · 32:57

AWS Solutions Architects Chintan Agrawal and Daniel Wirjo argue that the hardest problem in production voice agents is audio engineering—not AI—specifically turn-taking, the decision of when an agent should stop speaking or start responding. They present three levels of turn detection: Level 1 uses Silero VAD with a silence timeout (e.g., 300ms default), Level 2 delegates to STT providers like Cartesia or Deepgram for built-in endpointing (p50 ~250-300ms), and Level 3 combines Silero VAD with SmartTurn, an open-source 8MB model achieving 58.9% recall and 68.4% precision while falling back to VAD on low confidence. They show how interruption handling (barge-in) flushes TTS/LLM in ~15ms and distinguish real interruptions from backchannel acknowledgments. Latency budgets are tight: 40ms mic encoding, 52ms network/jitter, 300ms STT+endpointing, 500-650ms LLM time-to-first-byte (dominant bottleneck), and 120-190ms TTS playback, totaling 800-1300ms in standard cloud setups. Co-locating models in one GPU cluster can achieve ~500ms voice-to-voice. For LLMs, Nemotron 3 Ultra and GPT-4.1 achieve ~530ms p50 but GPT-4.1 spikes to 1.7s p95, and multi-turn drift (>15 turns) can break prompt…

Your Agent Is Wasting Tokens and You Don't Know It - Erik Hanchett, AWS

Jun 28, 2026 · 5:55

Erik Hanchett, a Senior Developer Advocate at AWS, presents five specific techniques to reduce token costs in agent workflows without changing prompts or models. He demonstrates caching system prompts with 'cachePrompt' to avoid resending full context, and routing tasks by difficulty using cheaper models like Claude Haiku for simple requests. He advises offloading large tool results by storing them externally and sending only summaries, capping tool loops with a max iterations setting to prevent infinite loops, and trimming conversation history using a sliding window that keeps only the last 10 messages while optionally summarizing older context. These methods directly address common cost pitfalls, such as using expensive models for trivial tasks and letting context windows grow unchecked.

Ship Real Agents: Hands-On Evals for Agentic Applications — Laurie Voss, Arize

May 14, 2026 · 2:04:18

Laurie Voss, head of developer experience at Arize AI, delivers a hands-on workshop on evaluating agentic applications using Arize Phoenix, demonstrating that choosing the right eval matters more than tuning it: a correctness eval scored 0 out of 13 on the same financial analysis agent that a faithfulness eval scored 13 out of 13, because the model doesn't know the current year and cannot verify forward-looking data. He walks through building a complete eval pipeline from scratch—starting with tracing a Claude Haiku-based financial agent, reading and categorizing traces to identify root causes, then implementing code evals, built-in LLM-as-a-judge evals, and a custom actionability rubric with labeled examples. Voss emphasizes the importance of meta-evaluation to validate judge accuracy and introduces Phoenix experiments to prove prompt changes actually improve scores, not just vibes. Practical tips include using the impact hierarchy (data quality > prompting > model selection > hyperparameters) and the value of regression evals for safe model upgrades. The workshop closes with cost-aware evaluation, pairwise evaluation, and reliability scoring as next steps beyond the foundations…

Ralph Loops: Build Dumb AI Loops That Ship — Chris Parsons, Cherrypick

May 4, 2026 · 1:48:26

Chris Parsons argues that dumb loops—simple while loops where an AI agent repeatedly executes the same task, evaluates its output, and iterates—outperform complex multi-agent orchestration and planning graphs. In this hands-on workshop, he builds a Pomodoro timer using Claude Code, implementing tickets one by one in a loop that self-corrects with each pass. He demonstrates the 'loop' command in Claude Code for scheduled, continuous execution and shows how to use sub-agents for adversarial validation to avoid self-confirmation bias. The talk covers real-world applications such as a worker loop that processes project steps overnight and a morning loop that generates daily briefings, all designed to offload routine work while keeping human oversight for irreversible decisions. Parsons emphasizes that the bottleneck in AI-augmented teams is often the review process, not coding speed, urging teams to identify and fix their biggest constraint first.

Vibe Coding at Scale: Customizing AI Assistants for Enterprise Environments - Harald Kirshner,

Jun 27, 2025 · 15:26

Harald Kirshner, a Principal Product Manager at Microsoft working on VS Code and GitHub Copilot, argues that 'vibe coding' must evolve from ad-hoc experimentation to structured, spec-driven approaches for enterprise environments. He breaks vibe coding into three stages: YOLO (rapid prototyping with auto-accept and voice dictation), structured (using templates, custom instructions, and tools like MCP for consistency), and spec-driven (iterating from a plan for scale and reliability). Kirshner demonstrates VS Code Insiders' agent mode, new workspace flow, and auto-approve features, emphasizing that developers should commit often, review agent pauses, and leverage workspace instructions to maintain quality. He advocates for standardizing AI usage through team-defined prompts and modes, preserving developer autonomy while ensuring maintainable code even in complex, polyglot codebases.

Why the Best AI Agents Are Built Without Frameworks (Primitives over Frameworks) — Ahmad Awais, CHAI

Jun 3, 2025 · 27:06

Ahmad Awais, founder of LangBase/CHAI, argues that production AI agents like Perplexity, Cursor, v0, Lovable, Bolt, and CHAI itself should be built using AI primitives rather than frameworks. He demonstrates live coding a 'Chat with PDF' agent using LangBase primitives (memory, parser, chunker, threads). Awais presents eight agent architectures—augmented LLM, prompt chaining, agent router, parallel agents, orchestrator-worker, evaluator-optimizer, tool-calling, and memory-based—all built with plain code and no framework. He claims frameworks are bloated and slow, while primitives offer flexibility and automatic scaling (e.g., memory storing terabytes). Awais shows how to compose multiple LLMs (Gemini, DeepSeek Llama, Claude) in a router agent, and notes that his team has built agents for OCR, image analysis, and deep research using primitives and external tools like Mistral OCR.

Code Generation and Maintenance at Scale: Morgante Pell

Oct 17, 2024 · 18:54

Morgante Pell, founder of Grit, argues that AI agents for code generation must be built for modifying large existing codebases rather than generating new apps, and that combining static analysis with AI enables reliable migrations at scale. Grit has merged more PRs than any other company by focusing on supercharging top engineers, using GritQL to precisely find code via syntactic and semantic queries, and relying on compilers like TSC to catch errors that LLMs miss. They overcome slow enterprise builds (10 minutes for type checking) by precomputing in-memory indexes and using Firecracker to snapshot and fork environments for parallel agent execution, achieving PRs with only a few iterations. For editing, they developed a custom 'loose search and replace' format to avoid expensive full-file generation and LLM laziness. This approach allowed one customer to complete a multi-year OpenTelemetry migration in a week with under 100 developer hours. Morgante envisions future UIs that let engineers manage entire codebases like SimCity.