Skip to content
#Tutorials / practice
October 1Thursday
  1. Anthropic · Claude.dev60

    Getting started with Claude Code mods: building a context-window forecast

    Claude Code mods are small JavaScript or TypeScript files that run inside a session as hooks shipped in plugins, and can observe events, rewrite behavior or draw custom UI in the terminal or desktop app. The guide builds Token Weather, an roughly 80-line mod that reads $.session.usage() after each turn and draws a weather-style context-window band above the prompt, then tours Blast Radius, which holds risky Bash commands, and Replay Theater, which steps through a turn's edits. Mods require Claude Code 2.1.287 or later and are on by default; finished code for all three is in anthropics/claude-code-playground.

    Why it matters: A hands-on walkthrough of Claude Code mods that builds a working context-window meter in about 80 lines, showing how hooks, state and custom UI fit together.

September 28Monday
  1. Anthropic · Claude.dev72

    Anthropic adds build-eval and hillclimb commands to the claude-api skill in Claude Code

    Anthropic added two commands to the claude-api skill inside Claude Code: /claude-api build-eval builds an evaluation set in your codebase, and /claude-api hillclimb iterates on an application against that evaluation with a held-out set to catch overfitting.

    Why it matters: Anthropic adds build-eval and hillclimb commands to its claude-api skill, showing how Claude Code can design evaluations and iterate against them while guarding against overfitting.

September 23Wednesday
  1. Vapi Blog38

    Vapi tests Jev as a real-time guardrail for voice AI

    Vapi ran early experiments using TypeSafe AI's early-access "System One" model Jev as a guardrail that scores whether a voice assistant's response violates a developer-defined rule before it is spoken. In one early test, Jev caught at least three out of four violating responses, though Vapi says it is not a 100% compliance guarantee and only an additional check on top of prompt guardrails.

  2. Every58

    Every's Mike Taylor on a Writing Workflow With AI That Starts Before the Prompt

    Every head of evals Mike Taylor lays out the writing workflow he uses with AI, from writing the title first and collecting sources to recording a spoken monologue and generating drafts from Claude Opus 5.5, Fable 5.1 and GPT-6 Astra. He says the process cut his time for a 1,200-word piece from a day to under two hours with no drop in traffic or positive reader comments, and he still writes the introduction and conclusion himself and expects 20-30 percent of a draft to change during self-editing.

  3. Modal Blog58

    How Modal serves trillions of tokens for trillion-parameter coding agents

    Modal explains how it optimized Kimi K2.6 inference for coding agents, reaching 2.8x per-user and 5.6x cross-user performance per replica and running services at hundreds of billions of tokens per day. The work combines custom DFlash speculative decoding fine-tuned on coding traces, FP8 KV cache and NVFP4 shared-expert quantization, HiCache CPU-tier caching, and KV cache-aware load-based routing. Modal upstreamed its SGLang patches and released the configuration behind Modal Auto Endpoints.

September 21Monday
  1. Every44

    How to Create Your Own Personal AI Benchmark

    Every's head of evals explains how to build a personal AI benchmark instead of relying on MMLU-Pro and other public tests, drawing on his own experience testing Claude Opus 5, Claude Fable 5, GPT-5.6 Sol, Astra, Luna and Haiku on real work tasks. The approach has three levels and is meant to show when to switch models and whether a smaller, cheaper one suffices.

  2. LiveKit Blog38

    Comparing Open Source Frameworks for Realtime Voice and Video AI Agents: LiveKit Agents vs Pipecat

    This guide compares LiveKit Agents and Pipecat, the two open source frameworks it says matter most for building production voice and video AI agents, across architecture, adoption, developer experience and production readiness. LiveKit Agents runs on LiveKit's open source WebRTC and SIP infrastructure and wires the pipeline for you, while Pipecat assumes no transport and has developers assemble the pipeline stage by stage. It also covers where TEN Framework, Dograh, Vision Agents and Vocode fit in.

September 9Wednesday
  1. LiveKit Blog22

    What "inference is slower than realtime" means in LiveKit voice agents

    LiveKit explains that the "inference is slower than realtime" warning in its voice agents refers to the local VAD model, not the STT, TTS, or LLM models used through LiveKit Inference. Each 32ms audio window must be processed in under 32ms, and the reported delay shows how far the VAD has fallen behind live audio. Blocked event loops and CPU saturation are the main causes, and the fix is to rule out synchronous code rather than add threads.

September 3Thursday
  1. Vapi Blog38

    How AI voice agents tell a live person from a voicemail

    Voicemail detection, also called answering machine detection, decides within roughly three to five seconds whether an outbound call reached a live person or a recording, relying on timing and behavior signals rather than voice audio. A 2026 arXiv preprint found timing features alone can match beep- and keyword-based approaches while avoiding their added latency. Vapi lets users choose a detection provider, tune timing, and switch back to conversation when a human answers.

September 2Wednesday
  1. Modal Blog22

    How Botika runs full-stack generative AI on Modal

    Botika runs its full-stack generative AI operation on Modal, covering a 100-terabyte image data pipeline, in-house foundation models with tens of billions of parameters, and roughly 15 models serving production inference. The pipeline processes that dataset with under a 1% error rate across thousands of concurrent containers, and a single researcher can now run 50 experiments a day instead of one or two.

August 24Monday
  1. LiveKit Blog36

    Debugging Short Utterances in Voice Agents

    LiveKit's blog breaks down why voice agents often go silent after short replies like "yes" or "ok," tracing it to turn detection failures. The most common cause is STT providers missing short speech and never emitting a final_transcript, which blocks end-of-utterance detection entirely. The post also covers overly aggressive or permissive endpointing delays and misconfigured noise cancellation that drops short audio as noise.

August 20Thursday
  1. Vapi Blog22

    Best AI Voice Agents for CX: How to Evaluate Them

    Vapi published a seven-criteria rubric for evaluating AI voice agents in customer experience, covering resolution, real-time voice quality, action-taking, escalation, model flexibility, lifecycle trust, and platform control. The guide argues containment and deflection overcount success, since contained callers may simply hang up, and cites ContactBabel data showing phone preference for complex interactions rose from 28% in 2018 to 47% in 2024. Vapi positions itself as a model-agnostic platform layer with configurable endpointing, interruption handling, and background denoising.

August 18Tuesday
  1. LiveKit Blog40

    LiveKit: multi-participant robotics beyond 1:1 connections

    LiveKit is extending its SFU architecture beyond single peer-to-peer links so robot deployments can run multi-participant sessions, where a Room lets each camera, model, operator, or service join as its own participant. LiveKit describes three architectures: human-in-the-loop data recording with robot, policy, operator, and recorder in one session; VLM-guided skill orchestration where a vision-language model selects skills at roughly 1 Hz while separate policy participants control the robot at tens of hertz; and policy escalation, where a reward model at 30 Hz or higher flags stuck or unsafe states and the robot revokes authority from the specialist policy.

August 14Friday
  1. Vapi Blog22

    How to Choose a Conversational AI Platform for Enterprise Development

    A vendor-neutral guide lays out five criteria for picking a conversational AI platform for enterprise voice agents: developer control, model choice and fallbacks, testing and observability, the full agent lifecycle, and compliance at scale. It cites a Zapier survey of 542 US C-level executives in which 81% worried about depending on a specific AI vendor and only 6% could drop their primary vendor without disruption. The guide argues latency and orchestration matter more than feature lists, noting AssemblyAI's finding that delays past 500–700 ms feel unnatural.

August 4Tuesday
  1. Vapi Blog22

    What Makes a Great Conversational AI Experience: Vapi on Voice Design

    Vapi argues that voice agents are judged on five real-time dimensions: latency, turn-taking, interruption handling, prosody, and a resilient pipeline. It cites research putting human turn gaps near 200ms and notes delays beyond roughly 500–700ms feel unnatural, while naive sequential pipelines can cost about 1.9 seconds versus 600–900ms for optimized ones. Vapi positions its model-agnostic pipeline as tunable and testable via simulated calls.

July 27Monday
  1. Vapi Blog22

    Anthropic and Vapi Webinar Q&A: How the Claude Haiku Ride-Booking Voice Agent Was Built

    Vapi published answers to questions from its webinar with Anthropic on voice AI, detailing the live ride-booking demo agent built on Vapi with Anthropic's Claude Haiku and the Layla v2 voice. The agent used five tools — estimate, book, check status, cancel and end call — plus smart endpointing and a conservative interruption threshold to reach sub-second turns. Agents running Claude on Vapi handled nearly 5M calls in the past 30 days across 50+ languages.

July 24Friday
  1. Vapi Blog22

    How to reduce customer wait times with AI voice agents

    AI voice agents cut customer wait times in two ways: removing work from the queue through self-service deflection, intelligent routing, agent assist, and demand prediction, and answering instantly with no hold. SQM Group found customers abandon calls at 2 minutes 36 seconds on average, while ContactBabel put the UK mean abandonment rate at 8.4% in 2024. Vapi says a first voice agent can be stood up from its dashboard in minutes, then measured on ASA, abandonment, and first-call resolution.

July 13Monday
  1. Every38

    How I Polish Software That Agents Built

    Kieran Klaassen describes "polish," the final step of his compound engineering workflow, where he runs the app himself and tells the agent what feels off until it doesn't. Using the /ce-polish command from the compound engineering plugin, he checks out a branch, starts the dev server, and opens the running app beside the agent in his editor. He cites a Cora email card animation that passed all automated checks and review agents but still slid in from the top of the screen instead of opening from the click point.

July 6Monday
  1. Modal Blog38

    How to price serverless GPUs: Modal's interactive cost model

    Modal published an interactive tool for estimating serverless versus reserved GPU costs, defaulting to current rates for a B200 GPU serverlessly on Modal and via three-year hyperscaler reservation. The model shows that when an application's peak-to-average ratio exceeds the reservation discount rate, serverless GPUs cost less overall, and Modal cites observed discounts of 2-5x against peak-to-average ratios of 5-10x.

June 24Wednesday
  1. Vapi Blog15

    Vapi Answers Top Questions from Its SVG Lead Qualification Webinar

    Vapi published answers to the seven most-asked questions from its webinar with Spring Venture Group, where Homer Kay described how SVG uses Vapi voice agents to qualify Medicare leads before transferring callers to licensed agents. The answers cover outbound calling compliance, API-first integrations, swapping STT, LLM and TTS components independently, human handoff, and HIPAA-eligible configurations with Zero Data Retention.

June 17Wednesday
  1. Vapi Blog30

    Built for the Ear: Designing Conversations for Voice AI

    Voice AI success starts with use-case selection: tasks ending in a link, code, or number belong in chat, while urgent, hard-to-type, or emotionally loaded problems suit voice. Chat scripts must be rewritten for the ear—split long passages into single-idea turns, restate collected details like dates aloud, and limit spoken options to two or three. One staffing company cut downstream placement errors by 30% by confirming each slot as it was collected, and another team trimmed 40 seconds off average call duration by turning open questions into choices.

  2. Vapi Blog40

    How Vapi Bootstrapped 15 Homepage Voice Agents in Code

    Vapi built the 15 voice agents on its homepage — 3 use cases across 5 languages — by generating them from a single ROUGH_DRAFT.md file instead of hand-editing each in the dashboard. The four-phase framework (plan, draft, bootstrap, harden) scaffolds a TypeScript project with OpenAI gpt-4.1 at temperature 0.5, ElevenLabs and Deepgram/Soniox voice stacks, and an idempotent upsert loop that stores assistant IDs in .env.local. The repo is public: clone it, add VAPI_PRIVATE_KEY, and run bun run bootstrap.

June 11Thursday
  1. Modal Blog34

    Modal Makes FlashAttention-4 Faster for LLM Inference

    Modal contributed optimizations to the FlashAttention-4 kernel to speed up decode-heavy LLM inference workloads, where memory bandwidth is the bottleneck. The changes include porting the "split KV" parallelism technique to FA4 and replacing TMA cp.async.bulk loads with cp.async for irregular memory accesses. An FP8 input PR (merged April 17, 2026) delivers up to 1.16x throughput over the bf16 baseline and enables smaller KV caches.

June 1Monday
  1. Modal Blog46

    Modal: Reinforcement Learning for LLM Post-Training Is an Infrastructure Problem

    Modal says the bottleneck in RL post-training of LLMs is now infrastructure, not algorithms, and has released an open-source library drawn from running RL at scale. It details three pain points — glue code, cluster queueing and GPU under-utilization — and reports RDMA weight sync cutting Qwen3 8B update time from 2.62s to 41ms.

May 29Friday
  1. Every22

    Compound Engineering Expands From Four Steps to Eight

    Compound engineering, the AI-native engineering philosophy, has expanded its core loop from four steps to eight, adding Ideate and Brainstorm at the front and Polish at the end. The original loop—brainstorm, work, review, compound—remains the core engineering cycle, but the update reflects where human attention now goes: deciding what to build and judging whether the finished product feels right.

May 15Friday
  1. Every40

    Every Is Redesigning Its Plus One AI Agents as Shared Team Resources

    Every is changing its Plus One product so its AI agents work as shared team resources with defined jobs, rather than one personal assistant per employee. The company says its first iteration, built on OpenClaw, brought more frustration than efficiency, with agents often failing to follow directions. The next version is meant to be more stable, with skills and integrations still part of the plan.

May 12Tuesday
  1. Modal Blog58

    How Modal achieved truly serverless GPUs

    Modal published an engineering account of how it cut AI inference replica spin-up from roughly 2,000 seconds to about 50 seconds using four components: a buffer of idle healthy GPUs, a lazy content-addressed filesystem called ImageFS, host-side checkpoint/restore via gVisor's runsc, and CUDA checkpoint/restore built on Nvidia driver support. Across over ten thousand cold starts, mean vLLM boot latency fell from 95,679 ms to 13,797 ms and SGLang from 83,713 ms to 17,486 ms for a ~1 GiB Qwen 3 0.6B model in bf16. The post also notes limits, including single-GPU-only snapshots and host-environment sensitivity that requires multiple snapshots per deployment.

May 5Tuesday
May 4Monday
May 1Friday
  1. Vapi Blog34

    Open Stack vs Integrated Solution: Key Considerations for Voice AI Builders

    Vapi Blog interviews Cartesia's Iz Shalom on choosing between integrated and open modular voice AI stacks. Integrated stacks suit narrow use cases and fast proofs of concept, while open stacks fit multiple use cases, multilingual support, and swapping components. The piece urges teams to measure P99 latency in their own environment and build tight evaluations before production.

April 29Wednesday
  1. Modal Blog33

    Building an RL Theorem-Proving Workflow on Modal

    AE Studio details how it trained LLMs to prove math theorems with reinforcement learning on Modal, comparing Evolution Strategies against GRPO while keeping the training loop fixed. The setup runs vLLM inference on GPUs, Lean compiler verification in isolated CPU sandboxes, and a lightweight orchestrator, using per-function images, .map() fan-out, and Volumes for base weights.

April 17Friday
  1. OpenAI Developers Blog60

    OpenAI publishes API deployment checklist for GPT-6 workloads

    OpenAI published an API deployment checklist that walks developers through moving workloads onto the Responses API and the GPT-6 model family, including gpt-6-astra, gpt-6.1-sol, gpt-6 Sol and gpt-6 Luna. The guide covers reasoning.effort levels from low to max, text.verbosity, tool_search with deferred tool loading, Programmatic Tool Calling, Multi-agent, compaction, prompt caching and WebSocket mode, which OpenAI says has shown up to roughly 40% faster end-to-end execution for workflows with 20 or more tool calls. It also details reliability and safety steps such as handling 429 and 503 errors, background=True for long jobs, safety_identifier and misalignment monitoring.

    Why it matters: OpenAI's official deployment checklist consolidates model selection, reasoning effort, tool search, compaction and WebSocket mode into one migration guide for GPT-6 workloads.

April 15Wednesday
  1. Modal Blog58

    Modal and OpenAI Agents SDK: building a parallel coding agent harness with sandboxes and GPUs

    Modal published a walkthrough on building a custom coding agent harness on top of the OpenAI Agents SDK, which OpenAI launched today, using Modal Sandboxes to give agents isolated Linux environments and GPUs. The guide starts from a minimal exec-based agent, then adds sessions for memory, an orchestrator plus subagent pool for parallel async work, GPU quotas, filesystem snapshots to deduplicate setup, and a skills subsystem, ending with a harness that runs OpenAI's Parameter Golf challenge across parallel GPU subagents. Modal cites Ramp's fleet of background coding agents on Modal, which it says now produces more than half of the company's PRs.

April 14Tuesday
  1. Vapi Blog27

    Vapi Engineers Share Lessons on Deploying Voice AI at Enterprise Scale

    Vapi's Forward-Deployed Engineers say the demo-to-production gap is where most enterprise voice AI initiatives stall, requiring extensive testing, guardrails and intent-based design rather than exact phrase matching. The team warns of "personality drift," where agents adopt callers' speech styles, and notes LLMs are non-deterministic, so deployments need defined error tolerance and continuous iteration. They advise starting with cost optimization but targeting revenue generation, and benchmark a good interaction at under a minute.

March 25Wednesday
  1. Modal Blog22

    How Doppel cut ML infrastructure overhead with Modal

    Doppel migrated a large portion of its ML workflows to Modal, removing the infrastructure friction that slowed training experimentation and inference deployment. Parallel experiments via map() replaced sequential runs, while image layer caching and persistent volumes cut build times by up to 10x, with complex setups reaching sub-minute warm builds.

March 12Thursday
  1. OpenAI Developers Blog67

    OpenAI updates Sora 2 prompting guide with character references, 20s clips and video extension

    OpenAI updated its Sora 2 prompting guide to cover new API capabilities: reusable character references for objects and animals, 1920×1080 and 1080×1920 exports, a maximum clip length raised from 12s to 20s, video extension that uses the full original clip as context, and a Batch API for asynchronous video jobs. The guide also walks through prompt structure for shot framing, camera motion, lighting and dialogue, and notes that resolution, duration and character IDs must be set as API parameters rather than described in prose. Extensions of up to 20 seconds are supported, and a video can be extended up to 6 times for a total of 120s.

    Why it matters: OpenAI's updated Sora 2 prompting guide details new API capabilities such as character references, 20s clips and video extension, plus reusable prompt templates for controlling shots.

February 25Wednesday
  1. OpenAI Developers Blog62

    OpenAI publishes Codex prompting guide for gpt-5.3-codex

    OpenAI released a Codex prompting guide for developers calling the Codex-tuned gpt-5.3-codex model directly through the API, recommending medium reasoning effort for interactive coding and high or xhigh for the hardest tasks. The guide covers migrating an existing harness to the open-source codex-cli, including the standard Codex-Max prompt, the apply_patch, shell_command and update_plan tools, and first-class compaction via /compact in the Responses API for multi-hour sessions. It also describes the new phase field, supported only on gpt-5.3-codex, which marks assistant items as commentary or final_answer and must be preserved in history to avoid performance degradation.

    Why it matters: OpenAI's official guide details how to tune prompts, tools and compaction for gpt-5.3-codex, giving teams a concrete migration path for their own coding agents.

February 24Tuesday
  1. Vapi Blog38

    Give Your OpenClaw Agent a Voice: Adding Phone Calls with Vapi Skills

    OpenClaw agents can now make and receive phone calls through Vapi's AgentSkills-compatible skills, installed in about five minutes via the npx skills CLI or by asking the agent directly. The Vapi pipeline targets sub-500ms voice responses and supports mid-call tool calling, with eight skills covering assistants, calls, phone numbers, tools, squads, webhooks and workflows.