iCreatAI News
Back to main site
Skip to content
#Agent
Nov 12Thu
  1. Hacker News AI58

    Show HN: Datatomcp – AI agents propose business definitions, a person approves

    Datatomcp is an AI-native data layer that connects databases, apps and sheets into versioned datasets, links them by shared IDs, and drafts business definitions that a person must approve before agents can use them. Agents query through read-only MCP tools or a REST API, with exact totals computed by the database and every question recorded in an audit log. It is free for 3 datasets and 2 people, with Pro at €12/month, and is hosted in the EU.

  2. Hacker News AI38

    Don't build your own harness: lessons from building Paywalls AI Editor

    RevenueCat describes how its Paywalls AI editor initially manipulated a custom JSON paywall schema through a bespoke harness, producing results that lacked taste despite model, prompt and skill tweaks. The team switched to letting the agent edit a JSX representation of the paywall with familiar Read, Write, Edit and compiler tools, which set a record on their blank-paywalls eval two days after the prototype and let them cut over half the system prompt and almost all skills. After rollout to 100% of users on September 2nd, positive feedback across roughly 46K requests grew 83% and negative feedback fell 40%, with gains concentrated in large edits, new paywall creation and anything requiring taste.

  3. Claude Blog32

    J. Crew brings its signature approach to styling to life with Claude

    J.Crew launched Style Advisor on JCrew.com, an AI stylist built with Claude Code using multiple Claude models (Fable, Opus, Sonnet and Haiku) that helps U.S. customers shop by complete outfit drawn from J.Crew's own photo shoots. Customers describe an occasion or start from a single piece and refine recommendations in a visual conversation, with every look based on J.Crew stylists' work. J.Crew plans to make it more personal over time and expand it to more markets and product lines.

  4. Hacker News AI34

    Show HN: MudGym's WebAssembly browser playground for AI agents in MUD2

    The post presents MUD2, one of the earliest online multiplayer games, compiled to WebAssembly and running in a browser tab, with much of the original C engine code, some dating to the early 90s, unchanged. The examples were built alongside MudGym, a reinforcement learning environment built around the game, and most are marimo notebooks running MudGym in Python in the browser through Pyodide.

  5. Hacker News AI60

    Show HN: A free course from engineer to AI engineer, one Git tag per episode

    A free YouTube-based course, "From engineer to AI engineer," teaches experienced software engineers with no generative-AI background to build a retrieval-augmented generation (RAG) pipeline in eight episodes, with a second seven-episode series, "Prove it works," building an evaluation harness on the same repository. Each episode is one commit and one Git tag (s1e1–s1e8 and s2e1–s2e7), so checking out a tag reproduces the repository exactly as that episode leaves it. The series uses TypeScript, SQLite, curl and an HTTP server, answering with claude-sonnet-5-5 over a fictional 26,000-word corpus (Lantern Supply Co.) that includes deliberate traps such as near-identical product names and a policy changed in later release notes.

  6. Hacker News AI20

    Show HN: Closed,Mechanical Mould Design AI Agent

    Closed is a mould design AI agent that accepts a customer STEP file or part photo, keeps the customer's part locked, and drafts stages including parting, core and cavity, layout, mould base, feed, side actions and ejection, logging each stage. It pauses for human decisions when a rule is violated, shows the source of every dimension from one of six non-AI origins, and supports switching between agent and manual mode on the same model. Nothing ships until the user approves it; the macOS and Windows studio plus iOS and Android apps are not yet available and builds go to a waitlist first.

  7. Hacker News AI40

    Show HN: Vibetime – see what you ship when coding with AI agents

    Vibetime is an npm-installable CLI that wraps Claude Code, Codex, Gemini, Aster, and Opencode in the terminal and uses session hooks to track the Claude Code, Codex, Cursor, and ZCode desktop apps, printing a session summary with git commits, line changes, and files touched when each session ends. It requires no config, daemon, or account by default, stores data locally in ~/.vibe/, and reads only git metadata, with an opt-in GitHub-based leaderboard that ranks sessions by commits with meaningful changes.

  8. Hacker News AI38

    Bringing Agentic AI to COBOL and the Mainframe with Rich Larin

    Recorded at IBM TechXchange 2026, RedMonk's Kate Holterhoff speaks with Rich Larin, IBM's Director of Z DevX & Platform Engineering, about bringing agentic AI tools to mainframe developers. Larin describes how Bob and the Premium Package for Z let COBOL teams use the same agentic IDE as other developers, with deployment options including SaaS, hybrid and air-gapped on-prem, plus Z code scan for deterministic security checks that Bob can remediate automatically and a data dictionary that captures experts' knowledge. He advises trying a proof of concept and hints at upcoming releases combining AI with analysis of very large applications.

  9. Hacker News AI62

    Oura to acquire AI-native primary care startup Counsel Health for $625M

    Oura has entered a definitive agreement to acquire Counsel Health, an AI-native primary care company that combines medical AI with in-house physicians, for $625 million in cash, with the deal expected to close before the end of the calendar year. The acquisition aims to pair Oura's continuous biometric data with Counsel's platform and on-demand doctors inside the Oura App, spanning preventive, acute, and specialty and chronic care. The announcement follows Oura's record fiscal fourth quarter, with revenue up 153 percent year over year to $533 million for the quarter ended Sept. 30, 2026, and approximately $1.75 billion for fiscal year 2026.

  10. Hacker News AI38

    Show HN: Wings – queue the next prompt while your AI is still working

    Wings is a macOS sidebar that docks beside AI desktop apps such as Claude, ChatGPT and Gemini so you can save a draft message while the AI is still working, then click it to paste it back into the input box. It never presses Enter, keeps notes locally with no account or upload, supports image notes, and offers ten interface languages. It follows or docks to many AI apps and terminals, though saving is not supported in terminals, and a Windows version is in progress.

  11. Hacker News AI58

    Remote Labor Index: Measuring AI Automation of Remote Work

    The authors introduce the Remote Labor Index (RLI), a multi-sector benchmark of real-world, economically valuable projects designed to evaluate end-to-end AI agent performance in practical settings. AI agents perform near the floor on RLI, with the highest-performing agent achieving an automation rate of 2.5%. The authors state these results help ground discussions of AI automation in empirical evidence and provide a common basis for tracking AI impacts.

  12. Hacker News AI46

    Adversarial defense for binaries/JS/Python against AI reverse-engineering agents

    BLA is a defensive tool for software authors that hardens build artifacts (JavaScript/TypeScript, Electron .asar and fuses, WASM, SQLite, Safetensors, GGUF, Go buildinfo, PE, Flutter/Dart, BEAM, EVM, PCAP, Python, PTX, and others) against AI reverse-engineering agents by planting decoys, tripping analyzer resource limits, and entangling sibling artifacts. It ships as a CLI (`npx bla-agents harden .`), an MCP/Skill setup for coding agents, and Vite/Rollup/Webpack/esbuild plugins, and reports 14/14 bundled benchmark targets passing input/output equivalence checks. The project states its empirical REA results were recorded on commodity hardware and that token/cost multipliers are internal estimates.

  13. Hacker News AI22

    AI Customer Driven Development

    Dr. Navraj Chohan proposes AI Customer-Driven Development (AI-CDD), a methodology where customers request capabilities in natural language, AI discovers or proposes them, human-governed engineering agents implement approved changes, and configuration-aware testing and telemetry govern product evolution. Existing features can be enabled via public toggles or found through embedding and vector search, while new requests go to product management for human review before AI agents implement, review, test, and document the feature behind a public toggle. Because the resulting configurations are exponential, AI would generate end-to-end tests for the configurations customers actually use and add them to the CI/CD pipeline.

  14. Hacker News AI22

    Show HN: MetaArena – Compare & Rank 5,353 Meta Global AI Hackathon Projects

    The author built MetaArena, a site that presents two projects from Meta's Global Developer Hackathon head-to-head and lets users pick the stronger one, ranking them on a leaderboard using the Bradley-Terry algorithm used by LLMArena and DesignArena. The hackathon had a $1M prize pool, 34K applicants, 20K accepted developers, and over 5K submitted projects, which made human review infeasible and AI rubric scoring disappointing.

  15. n8n Blog22

    The future of work is built by everyone

    The article argues that centralizing automation in a small specialist team becomes a bottleneck as a company scales, and that the ability to automate one's own repetitive work should become a normal part of how people work, much as spreadsheets did. It describes n8n's move toward a guild-like Automation team with reusable templates, office hours and documentation standards, while acknowledging the approach is still early and that regulated industries may legitimately keep build access centralized.

  17. Hacker News AI50

    Why AI Coding Agents Lose Context After the PR, and How to Keep It

    AI coding agents can write and test code but lose the delivery evidence produced after a pull request—failed builds, security findings, latency regressions—unless it is carried back into the workflow. The post describes Harness's Code Context Engine (from its Augment Code acquisition) for code context and its Software Delivery Knowledge Graph for delivery context, citing Augment's benchmark of 80%, 71%, and 30% improvements and Harness's internal estimate of about 12K tokens per graph query versus 250K+ via raw APIs. It presents a CVE workflow combining both, notes the two-way link between them is planned rather than shipped, and covers governance via policy as code, RBAC, and approval gates.

  18. Latent Space58

    The Jev Revolution: What Engineers Are Already Building with System One Models

    At the AI Engineer Code Summit, TypeSafe AI CEO Diogo Almeida argued that system one models like Jev—non-generative models returning structured choices, scores, or probabilities—should be integrated directly into application code to make software more reliable and automate more tasks. Glean's Chinmay Goyal said Jev is used alongside LLMs and other classifiers for its zero-shot flexibility, while UiPath and Workday engineers demonstrated prototypes including sub-second document-chunk ranking and interfaces that predict what a user wants to do while they type.

  19. Hacker News AI12

    Show HN: Nova Buddy AI – a friendly AI assistant for everyday people

    Nova Buddy AI is a browser-based everyday AI assistant that answers questions, drafts text and helps plan tasks, with no app install required and no sign-up needed to start. It offers five chat personalities, optional custom "Avatar AIs," and a Buddy memory feature for Buddy Plus subscribers, with a free tier of 50 messages a day and paid plans at $4.99 CAD/month or $79.99 CAD lifetime. The post also describes a Christmas promotion with free holiday tools and an advent calendar opening December 1.

  20. Hacker News AI58

    What it takes to operate a SaaS when AI agents write all the code

    A solo founder describes running DocSpring, a document automation SaaS, with AI agents handling much of the coding, bug fixing, Sentry error triage, performance work and CI, coordinated across 49 Claude Code sessions. He reports shipping long-deferred features such as Word templates, a Page Designer and API v2, and clearing his inbox and error queues, while noting that agents can drift into unwanted behavior changes, as when a date fix expanded into an unplanned date-parser project. He concludes that he still sets priorities, approves changes and decides what to promise customers, and that AI does not by itself protect the business from competitors using the same tools.

  21. Hacker News AI60

    Show HN: Motion Debugger – A browser critic for AI slop

    Motion Debugger is a CLI and agent skill that critiques local pages in Chromium, recording entrances, scrolling, hovers, phone layout and reduced motion, then returns ranked fixes with screenshots. Its premium-motion skill runs an upgrade pipeline that keeps facts, links and forms while rebuilding layout and motion on a GSAP/ScrollTrigger/SplitText/Lenis stack or Motion in React. The author reports four single-run upgrades and a blinded four-pair A/B study where judges preferred the plugin's sites in all eight judgments, noting the sample is too small for significance.

  22. Hacker News AI58

    Show HN: gethome – a local-first smart home hub with AI

    gethome is a local-first smart home hub that runs on a small Linux computer such as a Raspberry Pi, unifying Matter, Zigbee (via Zigbee2MQTT and a USB stick) and MQTT devices in one app with no cloud account. It offers an assistant and plain-language rule creation using your own Anthropic or OpenAI key, while rules keep running without any AI key. The code is source-available under the PolyForm Noncommercial License 1.0.0, with commercial deployments requiring a separate license.

  23. AWS Machine Learning Blog36

    Build autonomous AI agents with Amazon Bedrock and Spring AI

    This post shows how Java teams can build autonomous AI agents on the JVM using Spring AI and Amazon Bedrock AgentCore, with a single-agent travel assistant demonstrating tool calling, streaming, and memory, and a multi-agent intelligent document processing system with five specialist agents, a SpEL rules engine, and alerting. It covers the AgentCore runtime contract (@AgentCoreInvocation for POST /invocations and GET /ping), @Tool methods, structured output to Java records, memory advisors, and production patterns including Resilience4j retries, twelve-factor configuration, least-privilege IAM, Bedrock Guardrails, and Micrometer observability. Deployment uses an ARM64 image pushed to Amazon ECR and provisioned through modular Terraform, with an optional Amazon EKS and IRSA path.

  24. Hacker News AI58

    Show HN: Lynx – open-source fully-customizable AI workspace

    Lynx is an open-source, fully-customizable AI workspace that runs entirely on your device and uses your own local Claude Code or Codex subscriptions, with interactive UIs at the center of agent interaction rather than chat. It supports connecting any service via MCP or API, official and community templates, a point-to-edit tool, and cron-scheduled tasks, and is released under the MIT license. The author describes it as an experiment, noting they have done over 80% of their daily work from Lynx for a couple of weeks.

  25. OpenRouter Announcements36

    How to Benchmark LLMs

    A guide to benchmarking LLMs by writing tasks with script-checkable answers, grading with code, and comparing models on identical tasks via OpenRouter using graded accuracy, billed cost, and request time. On 60 synthetic tasks, GPT-6.1 Sol passed 180/180 trials while DeepSeek had the lowest response cost at 157/180 passes, and agreement with the public Artificial Analysis ranking was weak (Spearman correlation 0.109). The article includes a downloadable Python companion package with offline checks, configuration examples, and guidance on repeats, missing answers, and run comparison.

  26. OpenRouter Announcements58

    How to Stop an AI Agent Stuck in an Infinite Loop

    OpenRouter describes four guards against runaway agent loops, tested on six models with its Agent SDK (@openrouter/agent 0.11.0): doom-loop detection, a loopKey that normalizes tool arguments, stopWhen caps on steps and cost, and a credit limit on the API key. With doomLoop: true, all six models were blocked on their third identical tool call, and across 18 runs detection cut tool calls from 314 to 64 and spend from $0.29 to $0.05. The article notes that loops vary between runs and that only the key-level limit caps total spend when agent code is buggy or caps are missing.

  27. AWS Machine Learning Blog58

    Introducing the Web Search API on Amazon Bedrock AgentCore

    AWS announced the Web Search API on Amazon Bedrock AgentCore, which lets developers call the InvokeWebSearch operation directly from AWS SDKs or the AWS CLI with SigV4-signed IAM credentials, without creating a gateway or other resources. It returns up to 25 ranked results from an Amazon-operated web index, each with a text extract and, when available, title, URL, and publication time, and supports domain and publication-date filtering. It is available in six Regions and billed at $7 per 1,000 queries, complementing the existing AgentCore Gateway path.

  28. AWS Machine Learning Blog38

    OpenAI Codex on Amazon Bedrock

    This AWS post explains how developers can run OpenAI Codex on the workstation while routing model inference through Amazon Bedrock using supported OpenAI models such as GPT-5.6 Sol, Terra, and Luna. It compares three access paths—Native AWS Access with IAM Identity Center, AgentCore Gateway, and an LLM Gateway—and recommends starting with a small, least-privilege pilot before expanding. It also covers validation steps, identity-isolation testing, OpenTelemetry and CloudWatch observability, cost allocation, plugins, hooks, MCP servers, phased rollout, and cleanup.

  30. Hacker News AI42

    Composing data pipelines in an AI-native workflow

    Fivetran describes its CLI as a terminal-native interface that lets engineers and AI coding harnesses (Claude Code, Codex, Gemini CLI, dbt Wizard) create connections, configure schemas, trigger syncs, and build custom connectors, with MCP servers supplying context from task trackers and observability stacks. The post walks through a session that lands Stripe data in Snowflake and ships an fct_mrr dbt model, then covers iterating on changed requirements and failed syncs, and offers guidance on scoped API keys, confirmation prompts, and prompt injection.

  31. Databricks Blog28

    Detecting credential-driven attacks on Databricks

    Databricks describes how credential-driven attacks unfold on its platform in six non-linear stages—initial access with valid credentials, environment mapping, credential harvesting, execution via UDFs and jobs, persistence, and data collection with cleanup—and what to look for in verbose audit logs at each stage. The post explains how to investigate these attacks with Genie and the Detection App, how to respond once a compromise is confirmed, and which preventive controls such as context-based ingress, least privilege, and credential rotation limit what a stolen credential can do.

  32. AWS Machine Learning Blog38

    ICYMI: What landed for AI builders in October 2026

    AWS recaps its October 2026 releases for AI builders, including new Amazon Bedrock models such as Claude Haiku 5.5, OpenAI GPT-6.1 Terra, Amazon Nova 2.5 Sonic, GLM 5.3, and TwelveLabs Pegasus 1.5. Amazon Bedrock AgentCore gains a generally available CLI 1.0, model fallback and InvokeModel support in Gateway, Step Functions workflows as agent tools, and usage-based memory pricing, while Strands adds Bidi Agents, the Box local sandbox, red teaming in Strands Evals, and Decider on Gemma 4. The post also covers structured outputs for Claude models, Web Search domain filtering, a new Guardrails Standard tier for contextual grounding, and Amazon Bedrock cost breakdowns in AWS billing tools.

  33. Browser Use Blog34

    How to Use Custom Proxies with Browser Use

    This tutorial shows how to connect a third-party (bring-your-own) proxy to Browser Use Cloud by supplying the provider's host, port, protocol, and credentials when creating an agent run or cloud browser, then verifying the browser's exit IP and country via ipwho.is. It also demonstrates using the same credentials with Playwright both locally and against a Browser Use cloud browser over CDP, and compares managed proxy pricing ($5/GB) with BYO (provider rate plus $0.20/GB Browser Use egress). The guide includes setup steps, code samples, a troubleshooting table, and production tips such as preserving cookies alongside sticky sessions and stopping unused browsers.

  34. The Verge · AI58

    United won’t let your AI agent book your flight

    United says it will not allow personal AI assistants to book tickets on the airline, citing privacy and regulatory concerns, including the risk that agents could expose customer information, make unintended purchases, or bypass federal rules such as having customers attest that their bags contain no explosives. Agents can still show users United flights but cannot complete transactions on their behalf, and United CEO Scott Kirby said, "To be honest, I don't want to create another middleman." United said it could reconsider as third-party AI agents advance, but wants protections for travelers established first.

  35. AWS Machine Learning Blog12

    The attendee’s guide to the AWS re:Invent 2026 AI/ML track

    AWS will hold re:Invent from November 30 to December 4, offering over 2,000 learning sessions, with more than 140 in the AI/ML track spanning breakouts, chalk talks, builder sessions, workshops, code talks, and lightning talks. The guide organizes AI/ML sessions around the AWS AI stack—global infrastructure, AI chips (Trainium and NVIDIA GPUs), data foundation, models/training/inferencing (Amazon Bedrock and SageMaker AI), agent development and management (AgentCore), and agentic solutions—plus sessions on trust in agents, sustainability, and Local Zones and AI Factories. Breakout sessions are recorded and posted to the AWS Events YouTube channel a few days later, while other session types are live and not recorded.

  36. Hacker News AI20

    An AI-assisted RP2040 audio board that worked on first spin in 5 days

    Beyondex is a custom hardware mod that brings Valve Index audio to the Bigscreen Beyond VR headset, combining an RP2040-based DAC, battery management, and mechanical integration. After two failed designer attempts, the team delivered a production-ready design in five days, replacing the IP5310 power approach with TI's BQ25185 and fitting the board to a 24 mm by 50 mm envelope. From initial contact to shipping 200+ production units took weeks, not months.

  37. MarkTechPost74

    Google Launches Gemini Decisions API With Gemini Decision 1 at $0.10/M Tokens

    Google launched the Gemini Decisions API, powered by the new Gemini Decision 1 model, which does not generate text but scores up to 1,000 typed questions against one shared input and returns calibrated probabilities for uses like routing, policy checks, tool selection and grading. It supports text, images, audio, video and PDFs with a 262,144-token context, bills $0.10 per 1M input tokens with zero output tokens, and is available only via the Google-hosted Gemini Developer API (v1beta). Google reports it leads 7 of 9 accuracy benchmarks in its table with a top-1 ECE of 0.0250, though it trails TypeSafe Jev 1.14 on When2Call (79.9% vs 82.0%) and costs more across the shared suite ($0.88 vs $0.68).

  38. Hacker News AI58

    I made an AI harness / orchestrator that *actually* gives you decent limits

    Scout is a Windows and Linux coding agent that pools the free tiers of five providers plus Kilo Code, OpenCode and OVH Cloud, falling back to the next model when one is rate limited, with free models limited to 10/min and 200/day without an account. It offers five permission modes, context pruning at 60k and compaction at 90k, self-maintaining memory in committable .scout/memory.md and ~/.scoutcode/memory.md files, and a Rust desktop app with a React WebView2 window shipping as an 18 MB executable. It also includes an issue tracker, remote control from a browser or phone, and an MCP bridge letting claude.ai, ChatGPT, Gemini and Grok use local file and shell tools.

  39. Hacker News AI22

    Show HN: Version History for Your Synced Notes (AI Agent Safety)

    EtherPK 0.22.0 adds automatic version history for every page and journal entry in a synced graph, creating versions as you write and before actions like delete, rename, merge, Replace all, or removing protection. Versions and deleted items are kept for a set period (30 days in the examples), thinned as they age, encrypted with the graph's key before upload, and restorable from a Version history tab or the Deleted documents and files section. AI agents connected to a synced graph can list and read versions via the list_versions and read_version tools but cannot restore them, which a person does in EtherPK.

  40. Hacker News AI40

    Apple II Agent: An AI Coding Environment for the Apple II

    The author revived an open source Apple II Agent project in which an Apple IIe client connects over an Uthernet II Ethernet card, via a Mac proxy with Claude API access, to Anthropic's Claude Opus model so AI can write software through a chat on the machine itself. After automated testing in emulators on the proxy, the agent deploys new BASIC or assembly programs directly into real Apple II memory over the Ethernet link, and the author has made mouse-supported solitaire games and a Sim City clone. The code is on GitHub, the proxy runs on a Unix-like machine, and the Apple II end currently requires an Uthernet II card though it could be adapted to other network interfaces.