Skip to content
#Tutorials / practice
November 13Friday
  1. LiveKit Blog62

    LiveKit tests Gemini 4 Hydrogen vs 3.8 Flash in a voice agent with deliberately broken tools

    LiveKit ran Gemini 4 Hydrogen and Gemini 3.8 Flash through the same Google plugin in a voice travel-concierge agent with deliberately failing tools, and Hydrogen made 0 false booking reports across 54 transcripts versus 2 for 3.8 Flash. With Hydrogen at high and 3.8 Flash at default, Hydrogen's first sentence arrived 1.2 s sooner (4.0 s vs 5.2 s), and at low on both it was 1.7 s sooner (2.8 s vs 4.6 s). The author recommends medium or high thinking for voice agents, noting xhigh's median 7.8 s to first sentence and a 52 s worst case.

    Why it matters: LiveKit's hands-on test shows Gemini 4 Hydrogen reporting every deliberately broken tool call and starting replies sooner than 3.8 Flash, with per-thinking-level latency data for voice agents.

  2. Hacker News · AI58

    A Deep Dive into Decision Models: How Perplexity Decider v1.2 Works

    This post dissects Perplexity Decider v1.2, an open decision model built on Qwen-3.8 27B that converts a decoder-only LLM into a non-causal encoder and answers all classification questions in a single prefill step via a 255-option readout head. It covers the /v1/decisions API's yes_no, choice and score question types, training on harmonized datasets such as tasksource with synthetic data and choice shuffling, and post-hoc calibration at temperature T=1.32. The author argues the main case for decision models over autoregressive LLMs is token efficiency, and notes the 9B Decider Flash variant is trained with a distillation loss.

  3. Hacker News · AI22

    How Microsoft Principal Engineering Manager Tarik Guney Uses AI to Remove Bottlenecks

    Tarik Guney, a Principal Software Engineering Manager on Microsoft Teams, treats AI as a tool that extends engineers' physical and cognitive limits rather than a capability to chase. He focuses on leading indicators and bottlenecks across culture, goals, and tooling, arguing that process changes alone raise cognitive load instead of reducing it.

  4. Hacker News · AI40

    Let an AI agent query your production database safely with read-only SQL over MCP

    This tutorial shows how to let an AI agent answer plain-language questions about a production database on Railyard using the list_tables and query_database MCP tools. Every query passes five guard rails: write-scoped connections, admin/owner-only role caps, read-only transactions that always roll back, a statement timeout, and a 200-row cap flagged as truncated. The SQL text is never written into the MCP audit entry.

  6. Hacker News · AI8

    Show HN: Carton Clock — A Working Pendulum Clock Built from Empty Drink Cartons

    A maker built "Carton Clock," a working pendulum clock made from empty drink cartons plus BBQ skewers, paper straws, string and metal nuts as weights, all held together with hot glue. The gear train displays seconds, minutes and hours, and a full wind runs for a little over an hour. A custom browser tool, "Cartontick," written with Claude, simulated the carton escapement and generated cutting stencils and 3D-printable gluing jigs.

  7. Hacker News · AI58

    Tests as data: a method for keeping AI-generated code verifiable

    Martin Fowler proposes writing tests as data rather than code so that AI-generated production code stays verifiable when coding agents also refactor the tests. The approach combines customer tests, black-box testing, tabular or YAML test cases, and an AI-generated test runner, with the test data kept in text files that are easier to review and protect from unexpected edits. The article draws on interviews with 26 Thoughtworks developers in early 2026 who said they no longer fully trust their tests once AI refactors them, and it pairs the method with mutation testing, property-based tests, and human exploratory testing.

  8. Hacker News · AI62

    How to design effective tools for AI agents: guidance from OpenAI, Anthropic, Google and MCP

    This post consolidates what OpenAI, Anthropic, Google and the MCP spec recommend for designing tools for AI agents, and covers what their guides leave out. It argues tools should be built around workflows rather than API endpoints, that names, descriptions and schemas act as a contract the model reads literally, and that responses and errors are part of the prompt.

  9. Hacker News · AI40

    Stanford CS 329Z: Engineering AI Agents Course Covers Agent Design, RAG, Tools and Multi-Agent Systems

    Stanford's CS 329Z, Engineering AI Agents, walks through the anatomy of agentic systems — LLM core, reasoning, memory, tools and environment — and the gap between compound AI systems and true agents. The course covers RAG pipelines, tool use and function calling with MCP, DSPy and LangGraph orchestration, memory architectures such as MemGPT, and multi-agent orchestration patterns. It closes with optimization methods including GEPA, PPO and GRPO, plus a guest lecture from the Terminal-Bench creators.

  10. Hacker News · AI36

    AI Security Wiki: An Implementation Reference for Enterprise AI Security

    The AI Security Wiki is a reference for securing enterprise AI adoption, covering governance, risk management, secure engineering, operational monitoring, vendor evaluation and assurance in reusable template pages. It maps control objectives, audit evidence and test cases onto frameworks including ISO/IEC 42001, NIST AI RMF, NIST SSDF, PCI DSS v4.0.1, the FINOS AI Governance Framework and CERT-In's AI security auditing guidelines. It also includes a 682-case test library drawn from OWASP lists, MITRE ATLAS and NIST AI 100-2.

  11. Hacker News · AI58

    Sovereign: a router that learns which model to trust without labels

    Solibra built Sovereign, a router that sits between an application and model providers and learns per-request model choice from grades of its own finished work, with no answer key and no prior knowledge of the models. Across eight public benchmarks run against Claude Opus 5.5 and Claude Haiku 5.5, Sovereign spent 43% to 81% less than Opus on every benchmark, matched or beat Opus accuracy on USACO, LiveCodeBench and SATBench, and was more accurate than Haiku everywhere, by up to 55 points on USACO. On USACO its accuracy rose from 88% over the first 25 tasks to 97.7% by the end, passing Opus around task 150, and its grader agreed with the hidden answer key 95% of the time.

  12. ElevenLabs Blog18

    7 customer service skills every human and AI agent needs

    ElevenLabs outlines seven customer service skills — communication, problem-solving, conflict resolution, empathy, adaptability, personalization and product knowledge — that both human and AI support agents need. It cites a Zendesk study finding over 50% of customers switched to competitors after one bad experience, and a Gartner forecast that at least 70% of customers will start their journey with an AI interface by 2028. The guide stresses evaluating conversational metrics during training and after deployment, plus seamless handoff to humans for de-escalation.

  13. Databricks Blog36

    Detecting credential-driven attacks on Databricks with verbose audit logs and Genie

    Databricks details how credential-driven attacks unfold on its platform and how verbose audit logs plus Genie can detect the behavioral shift after a stolen PAT, session cookie, or service-principal credential is used. The post maps adversary activity into six stages, from initial login through environment reconnaissance, and covers response steps and controls that limit what a stolen credential can reach.

  14. Databricks Blog36

    Bright Machines uses Debezium and Iceberg to give customers live dashboards from air-gapped factories

    Bright Machines now gives customers live, governed dashboards of factory data from air-gapped plants without opening any inbound access. It captures PostgreSQL changes at the edge with Debezium, writes them as Apache Iceberg, pushes them out over one auditable outbound path, and reads them in place in Databricks via Unity Catalog federation. The first customer-visible dashboard went live about two months after kickoff, with committed rows queryable in one to two minutes and dashboards refreshing every ten minutes.

  15. OpenRouter Announcements58

    OpenRouter tests 11 rerankers on a 274-question RAG benchmark

    OpenRouter benchmarked 11 rerankers on a 274-question synthetic RAG dataset and found that reranking the top 30 vector-search candidates with voyageai/rerank-3-lite raised precision@1 from 81.0% to 97.1% at about $0.10 per 1,000 queries. The guide recommends retrieving roughly 30 chunks, reranking them, and sending only the top 3 to the LLM, which in its test lifted answer accuracy to 99.3% while cutting answering cost from $0.22 to $0.16 per 1,000 questions. It also flags failure modes: omitting the input_type parameter cost 7 to 12 points of precision@1, and cohere/rerank-v3.5 silently ignores content beyond its 4,096-token limit.

  16. Hacker News · AI38

    LessonFolk: Open-Source AI Tutor That Teaches AI via MCP

    LessonFolk is a free, open-source AI tutor that teaches AI topics through the AI chat app you already use, connected via MCP. It offers 15 courses, from an hour-long AI Foundations track to Context Engineering for Long-Running Agents, with a short level check and progress tracking. Courses and code are open source, and users can download or delete their data anytime.

  17. Hacker News · AI35

    Reverse Engineering a Coway Air Purifier to Ditch the Cloud

    A developer reverse-engineered the Wi-Fi-enabled Coway Airmega IconS air purifier to cut its dependence on Coway's IoCare cloud, using a man-in-the-middle setup built with LLM assistance. The existing Home Assistant integration impersonates Coway's phone app but breaks repeatedly—server bans, an IoCare to IoCare+ rebrand, HTML layout changes, and outages—prompting the effort. A weak-key incident at certificate authority eMudhra in October 2026 opened a possible foothold for intercepting the device's traffic.

  18. GitHub Blog · AI & ML58

    GitHub guide explains how to build agent skills that run across Claude Code, Cursor and Copilot

    GitHub published a practical guide to agent skills, versioned directories centered on a SKILL.md file that describe when and how to perform a repeatable task. The guide uses two examples, Proof Agent for adversarial verification of AI-generated code and Data Forge for a multi-skill data pipeline, to show how skills share a project manifest, reuse one execution path, and place human approval at each phase. It also describes a packaging script that generates client-specific files for Claude Code, Cursor and GitHub Copilot from a single skills source.

  19. AWS Machine Learning Blog40

    How Natera built SWARM, an agentic AI system for lab ops on Amazon Bedrock AgentCore

    Natera built SWARM, an agentic AI system for lab operations, on Amazon Bedrock AgentCore, cutting first response time by about 130x and automating 96.2 percent of support tickets. The system pairs a swarm-agent that drafts diagnostic reports before engineers open a ticket with a swarm-hive for real-time engineer interaction, both sharing one skill library. It addresses over 65 daily Jira tickets across three queues that previously averaged 17.4 hours for first response.

  20. Databricks Blog30

    Databricks Debunks Four LTAP Myths About Lakebase Architecture

    Databricks responds to four common misreadings of LTAP, the Lakebase architecture that keeps one governed copy of operational data serving both Postgres and analytics without CDC. The post argues LTAP is not replication: layers in front of the lake are caches, not a second database with its own catalog. It also says heap pages and Parquet are two lossless encodings of the same rows, so point lookups and scans each read the layout fast for them.

  21. AWS Machine Learning Blog38

    Tokenomics at Scale: Tracking and Capping Amazon Bedrock Spend per IAM Principal with CUR 2.0 and AWS Budgets

    AWS shows how to track and cap Amazon Bedrock generative AI spend per IAM principal using only native features: Bedrock automatically records the IAM user or role on every inference request, and those tags become cost allocation tags readable in Cost Explorer or CUR 2.0 exports. An AWS Budget scoped to Bedrock and filtered to one identity or tag value can attach a budget action that applies a Deny IAM policy once a threshold is crossed, with no application code for the common case.

  22. AWS Machine Learning Blog36

    Four Amazon Bedrock inference choices that affect cost

    Amazon Bedrock's cache duration, service tier, reasoning effort, and maxTokens settings can change inference cost without altering the model or prompt. A 5-minute cache write on Claude Sonnet 5 and Claude Opus 5 costs 1.25x the input rate, a 1-hour write costs 2x, and cache reads cost 0.1x; Flex tier requests to unsupported models fail with a ValidationException.

  24. LangChain Blog45

    What Is Eval-Driven Development? How to Improve AI Agents

    LangChain explains eval-driven development (EDD), a three-step process for building AI agents: define what good looks like, write the eval before you build, and compare results after each change. Because agents are non-deterministic, evals score runs across a dataset of examples and can use LLM-as-a-judge, with real agent runs in LangSmith as a source of test inputs.

  25. Databricks Blog22

    How Constellation is building a governed data foundation on Databricks

    Constellation, the largest US nuclear fleet operator, is building a governed Enterprise Data Platform on Databricks to give the business one shared meaning for its data. The platform uses Unity Catalog for lineage, fine-grained access and a single permission model, plus Data Vault modeling for critical reusable entities. Early use cases include a nuclear engineering assistant built with Databricks Genie and outage planning.

  26. Databricks Blog25

    Eclipse Aerospace uses Databricks PySpark custom data sources for flight-data ingestion

    Eclipse Aerospace is using Databricks PySpark custom data sources to ingest nearly 20 years of proprietary flight data, over 3TB spanning more than a million flight hours, without always-on dedicated compute. The Rust-backed Python package delivered twice the benchmarked performance of a similar PyArrow-based pure-Python data source and nearly 20x that of a native Python implementation without Arrow. The API, introduced in Apache Spark 4.0 and available in Databricks Runtime 15.4 LTS, replaces the prior Lambda-to-Avro pipeline.

  27. AWS Machine Learning Blog34

    Building a self-service LLM gateway with Amazon Bedrock and LiteLLM

    A self-service LLM gateway built on Amazon Bedrock Application Inference Profiles and LiteLLM running on AWS Fargate exposes Bedrock foundation models behind an OpenAI-compatible API, giving developers a single base URL and per-user key. The setup adds per-user spend controls, per-model quota isolation, and CloudWatch RPM/TPM observability, with Langfuse for prompt-level telemetry. Self-service key issuance requires LiteLLM Enterprise, since the free tier is limited to five users.

  28. AWS Machine Learning Blog34

    Optimizing cost per task and proving agent ROI on Amazon Bedrock

    This AWS post argues that Amazon Bedrock spend should be judged by cost per task rather than cost per token, since tokenizer efficiency, output verbosity, agentic loop count and reasoning overhead can make a lower-priced model cost more. A worked example shows a model with 2x the list price finishing 65% cheaper per task, and the post adds caching, routing and output constraints plus a five-dimension scorecard for measuring agent ROI against human baselines.

  29. Claude YouTube35

    Building the Claude API for the Frontier: Inside Claude Platform's Release and Safety Decisions

    Claude Platform engineers Jake Dejno and Lucca Siaudzionis explain how the Claude API evolves alongside each model launch, covering feature release decisions, model versioning and migrations, and cost management. They detail best practices for changing effort mid-conversation without breaking prompt caching, and how Claude Mythos and Fable share the same model weights with different safeguards. Claude Managed Agents and mid-conversation effort changes are in beta, and Mythos access runs through the Cyber Verification Program.

  30. Databricks Blog22

    How H6.ai builds AI-powered financial automation with Lakebase Postgres

    H6.ai automates accounts payable on top of customers' existing ERPs, using a dedicated Lakebase Postgres database per customer as its system of record. Because invoice data keeps changing, the team uses Lakebase copy-on-write branches to freeze snapshots of customer databases and run each regression test on its own short-lived branch, so the live database is never written to. Each run is judged by deterministic assertions plus a panel of AI judges from different model providers.

  31. AWS Machine Learning Blog38

    Amazon Bedrock AgentCore Evaluations: Built-in, DeepEval and AutoEval evaluators

    Amazon Bedrock AgentCore Evaluations now lets teams run AWS built-in evaluators alongside managed DeepEval and AutoEval metrics, plus custom evaluators derived from either. The built-in catalog spans 15 evaluators across response quality, goal completion, tool use, skills and safety, with three trajectory checks for expected tool paths. DeepEval adds multi-turn metrics such as ConversationCompleteness and KnowledgeRetention, while AutoEval contributes specialized signals including security.

  32. AWS Machine Learning Blog36

    Building a Daily Dependency Watcher with LangGraph and Amazon Bedrock AgentCore Web Search

    The Web Search API in Amazon Bedrock AgentCore is now available, giving agents current web results through a single SigV4-signed API call served from a web index Amazon operates. A walkthrough builds a daily dependency watch as a LangGraph graph that researches npm, PyPI, and container base images in parallel, with date windows, blocklists, and search budgets enforced in code. In testing, the three branches finished in 36 seconds versus 99 seconds run sequentially.

  33. AWS Machine Learning Blog36

    AWS Quick AI-PDLC: Six Agents for AI-Driven Product Development

    AWS Quick introduces AI-PDLC, a framework of six specialized agents—led by an Orchestrator covering Discovery, Prioritize, Working Backwards, Spec Generator, and Designer—that turns scattered enterprise signals from Slack, Jira, Salesforce and SharePoint into a traceable prototype_spec.md. Every phase requires human approval, and the spec can be handed to coding agents like Kiro or Claude Code via the open Agent Client Protocol (ACP).

  34. AWS Machine Learning Blog40

    AWS opens catalog of 23 reusable generative AI assets from its Innovation Center

    AWS has published a catalog of 23 production-ready, open source generative AI assets from its Generative AI Innovation Center, now part of AWS Frontier AI Engineering & Services. The building blocks cover RAG pipelines, document processors, agent scaffolding and evaluation frameworks, and AWS says they can cut development from months to weeks. DoorDash reported a 50x increase in testing capacity and Ricoh a 7-fold throughput increase after building on the assets.

  35. AWS Machine Learning Blog38

    How DXC Technology built a multi-model AI substrate on Amazon Bedrock

    DXC Technology built the model substrate for its DXC OASIS IT-operations harness on Amazon Bedrock, reaching Anthropic Claude, Amazon Nova, Meta Llama and open-weight models through one managed interface. Amazon Bedrock Guardrails apply content filtering, PII redaction and denied-topic policies uniformly across every model, while AWS PrivateLink keeps inference traffic inside the customer VPC. DXC OASIS has been generally available since March 2026 and cut resolution time by 95% on average across 56 measured use cases.

  36. AWS Machine Learning Blog40

    Agent DLC: Engineering AI Agents from Prototype to Production

    AWS introduces the Agent Development Lifecycle (Agent DLC), a framework with one lifecycle, two loops, and a single explicit standard for judging every agent change. It addresses three agent properties that break conventional CI/CD: non-determinism, prompts as source code, and independently moving dependencies. A reference HR policy assistant shows chunk-level retrieval precision of 1.00 across all three test questions while fact-level precision fell to 0.09 and retrieval coverage hit 0.00 on one question.

  37. AWS Machine Learning Blog36

    Fine-grained access control for Amazon Bedrock Managed Knowledge Base tools

    AWS shows how to give a shared AI agent per-user document access on Amazon Bedrock Managed Knowledge Base by exposing search as MCP tools through AgentCore Gateway. A request interceptor injects the verified user's email from the Cognito JWT into userContext, and ACL awareness returns only documents that user may view. A Cedar policy in AgentCore and a resource-based policy on the knowledge base add secondary defenses against spoofed or unauthorized searches.

  38. AWS Machine Learning Blog58

    AWS walks through building cross-organization multi-agent systems with A2A

    AWS published a reference architecture in which a LangChain-based enterprise orchestrator on Amazon ECS calls a Strands Agents-based compliance SaaS agent on Amazon Bedrock AgentCore over the A2A protocol, with the two sides in separate AWS accounts and no shared secrets. Each side authenticates with tokens from its own Amazon Cognito user pool, and the SaaS agent calls back to an enterprise context agent for account metadata, so the agents act as peers rather than client and server. The system deploys from three Jupyter notebooks that provision five CloudFormation stacks and run an end-to-end test plus seven trust boundary checks.

  39. AWS Machine Learning Blog34

    Migrating to Amazon Bedrock Managed Knowledge Base with a coding agent

    AWS added a knowledge base migration guide to the amazon-bedrock skill in the Agent Toolkit for AWS, letting a coding agent plan a move from a customer-managed knowledge base to Amazon Bedrock Managed Knowledge Base. The agent starts with read-only discovery and a line-by-line reviewed plan, then creates the new knowledge base and data sources alongside the original or writes a migrated IaC template. Managed Knowledge Base raises default quotas to 200 data sources per knowledge base and 10,000 knowledge bases per account per Region, and adds agentic retrieval, AgentCore Gateway integration, and resource-based policies.