Skip to content
Only How-to
  1. LangChain Blog67

    LangChain's Restock agent shows how to build a payment-capable AI agent

    LangChain built Restock, a sample office-supply agent that runs in Slack on Managed Deep Agents and pays through Stripe's Link wallet. The agent searches products, builds a cart, and pays over the Machine Payments Protocol, with the user approving the purchase in Slack and the payment in Link. The post uses a pens order at $22.18 to show the flow from request to confirmed order.

    Why it matters: The post walks through how an agent handles search, budget limits, Slack review, and Link approval, showing where each control sits outside the model.

  1. Hugging Face Blog66

    How one developer built six custom models with ML-Intern for about USD 103

    A Hugging Face blog author used the ML-Intern agent in HuggingChat to build six small models by writing detailed prompts that specify datasets, base models, baselines, smoke tests, and spending limits. The projects include a citrus disease vision-language model, a Huggy character LoRA, a camera-angle LoRA, a doodle-to-object LoRA, a 0.8B prompt rewriter, and a 4-step distilled Agate model, with total compute cost of about USD 103. Each project's prompts and public models are linked from the post.

    Why it matters: The author shows how prompt structure, baselines, smoke tests, and budget caps shape an agent-driven training workflow, with per-project costs given.

  2. Claude Blog66

    Claude skill commands build evals and hillclimb them against overfitting

    Anthropic added build-eval and hillclimb commands to its claude-api skill for designing evaluations and iteratively improving applications against them. The article covers eval design principles, including production-representative tasks, headroom and low variance, and guards against overfitting through train/test splits. Two examples report results: a customer support benchmark where cost fell to under half while accuracy rose, and a claude-api skill eval that rose from 66% to 88%.

    Why it matters: The article gives a concrete workflow for designing evals and hillclimbing without overfitting, with two worked cost and performance examples that show the tradeoffs.

  1. vLLM Blog62

    vLLM Speeds Up DeepSeek-V4.1-Flash Agentic Serving Through Kernel and Replay Optimizations

    Inferact and the vLLM community reported a 1.9× low-concurrency speedup and about 5.3× throughput under a 150 TPS constraint for DeepSeek-V4.1-Flash over three weeks. Gains came from SWA bounded replay with CUDA graphs, which cut TTFT by about 30%, and from integrated DeepSeek kernels such as MegaAttention, Mega-mHC, Mega-Gate, and DeepSelect. The post measures these results on the SemiAnalysis AgentX benchmark.

    Why it matters: The post breaks down how SWA bounded replay and fused kernels cut prefill and decode costs, a reusable engineering pattern for long-context agentic serving.

  2. Claude Blog62

    Comcast and Booz Allen use Claude Mythos to find exploit chains in codebases

    Comcast and Booz Allen used Claude Mythos Preview to find vulnerabilities that arise from interactions across code, configuration, and deployment rather than single-file bugs. Comcast identified a critical authentication flaw across 258 systems and about 170 million lines of code before any exploitation was observed. Booz Allen reported that one analyst reviewed eight production systems across 138 repositories in twelve days, a review its team estimated would have taken several months without the model.

    Why it matters: The case studies show how security teams validate and remediate model-found exploit chains, a workflow relevant to anyone managing large codebases.

  1. Google Developers Blog62

    EmbeddingGemma 2 releases multimodal embeddings with modular encoder loading

    Google released EmbeddingGemma 2, an open embedding model under the Apache 2.0 license that maps text, code, images, video, and audio into a shared 768-dimensional space. Developers can load a 270M-parameter text and code setup, or add vision and audio encoders up to a 740M-parameter full multimodal model. Matryoshka truncation to 256 or 128 dimensions reduces vector storage, with the guide noting quality losses on image, video, and speech retrieval at lower dimensions.

    Why it matters: The guide gives concrete encoder sizes and dimension-storage tradeoffs, showing how to choose a configuration for text, code, image, video, and audio retrieval.

  1. Lovable Blog80

    How Lovable's Chats connect conversations to agent work on projects

    Lovable describes how its Chats feature lets a workspace-level chat agent hand work to project builder agents and receive progress back. The design records each agent's history as an append-only, forkable trajectory, and passes messages through durable inboxes that activations wake. Agents can suspend at iteration boundaries and resume on freshly deployed nodes without killing long-running runs.

    Why it matters: The post details how trajectories, inboxes, and activations let agents share work and resume after deploys, useful for designing comparable agent systems.

  1. Microsoft Research60

    Microsoft Research shows offloading robot AI inference improves performance and battery life

    Microsoft Research reports that running physical AI inference on onboard GPUs can limit robot performance and battery life, while offloading inference to edge or cloud GPUs improved results in mobile manipulation tests. In its evaluation, smaller onboard GPUs slowed mapping and planning by up to 383% compared with an A100, and large onboard GPUs such as Jetson Thor drained robot batteries by up to 160%.

    Why it matters: The study measures how offloading robot inference to edge or cloud GPUs changes task success, battery life, and model size, offering evidence for infrastructure design.

  1. vLLM Blog62

    How vLLM Speculators trained a DSpark draft model for Kimi K3 on GB300 NVL72

    The vLLM team trained a DSpark speculative decoding draft model for Kimi K3, a 2.8T-parameter model, using the Speculators library on GB300 NVL72 hardware. They added a MooncakeHiddenStatesConnector to stream hidden states from disaggregated vLLM inference nodes to training nodes across multiple machines. The released speculator raises single-stream interactivity from about 110 to about 435 tokens per second per user on math reasoning, with up to about 3.5x higher output throughput under concurrent load.

    Why it matters: The post shows how hidden-state extraction and Mooncake transfers let a 2.8T-parameter model's speculator be trained across multiple nodes, a reusable pattern for similar setups.

  1. Augment Code Blog80

    Augment Code details how its software factory raised output per developer 4.5×

    Augment Code reports that size-adjusted output per active developer rose from 12.3 to 55.7 between November 2025 and July 2026, while median time to merge fell from 11.2 to 3.1 hours. The post says the company added specialized agents wherever work was piling up, across planning, review, verification, feedback, and incident response, and kept engineers responsible for product decisions, architecture, and production risk.

    Why it matters: The post pairs internal productivity and quality metrics with the order in which agents were added, showing how review and verification bottlenecks shaped a software delivery pipeline.

  1. Anthropic Engineering78

    How Anthropic built Claude Code auto mode to replace skipped permissions

    Anthropic describes Claude Code auto mode, which delegates approval of agent actions to model-based classifiers instead of manual prompts or skipped permissions. The classifier reviews tool calls before execution and a separate probe screens tool outputs for prompt injection. Anthropic reports a 0.4% false positive rate on real internal traffic and a 17% false negative rate on real overeager actions.

    Why it matters: The post explains the layered classifier design and its measured tradeoffs, showing how autonomous coding agents can cut approval fatigue without fully removing risk.

  1. Anthropic Engineering78

    Anthropic shows a three-agent harness for long-running app development

    Anthropic's Labs team describes a three-agent harness with planner, generator, and evaluator agents for building full-stack applications over multi-hour autonomous coding sessions. The evaluator uses Playwright to test the running app against sprint contracts, and a retro game maker built with the harness worked end to end where a single-agent run's core feature did not. The author later removed the sprint construct and kept only the components still needed on Opus 4.6.

    Why it matters: The post shows how a generator-evaluator loop, with explicit grading criteria and a tuned QA agent, turned a solo run's broken output into a working app, and how the harness was pruned as models improved.

  1. Anthropic Engineering75

    Anthropic details how parallel Claude agents built a 100,000-line C compiler

    Nicholas Carlini of Anthropic's Safeguards team describes an agent-team setup where 16 Claude instances worked in parallel on a shared codebase without human intervention to write a Rust-based C compiler. Over nearly 2,000 Claude Code sessions costing about $20,000 in API fees, the team produced a 100,000-line compiler that can build Linux 6.9 on x86, ARM, and RISC-V. The post focuses on harness design, including high-quality tests, lock files for task claiming, GCC as a reference oracle for the kernel, and the limits the project reached.

    Why it matters: The post shows concrete harness design choices for long-running agent teams, including test design, locking, and parallel work division, that readers can adapt to their own autonomous projects.

  1. Anthropic Engineering67

    Anthropic redesigns its performance engineering take-home as Claude models improve

    Anthropic's performance engineering lead Tristan Hume describes how a take-home test for hiring performance engineers was repeatedly defeated by successive Claude models. Claude Opus 4 outperformed most human applicants within the 4-hour limit, and Claude Opus 4.5 matched the best candidates in 2 hours. Anthropic is releasing the original take-home as an open challenge, with the best known Claude result at 1487 cycles.

    Why it matters: The post traces how each Claude model defeated the take-home test, showing concrete redesign tradeoffs for evaluating engineers when AI assistance is available.

That’s everything