Mastra introduces Knowledge, a shared store of markdown pages organized into org, resource, and thread scopes that agents can search, read, and write through five built-in tools, working alongside signals to keep context current. Agents receive a Knowledge instance via the knowledge option, and storage adds mastra_knowledge_* tables, with KNOWLEDGE_ROUTES enabling a Studio page view. Knowledge is in alpha and requires @mastra/[email protected] or later.
ElevenAgents now integrates natively with NiCE CXone, Genesys Cloud, Amazon Connect, and Five9, and connects over SIP to any other contact center or PBX that supports SIP trunking. The voice stack, built from ElevenLabs' own audio research, offers more than 17,000 voices in over 90 languages, passes call context from the contact center to the agent, and hands calls back to human agents through existing routing with full context. The company says this lets enterprises automate routine calls without replacing their telephony, routing, compliance recording, or CRM systems.
vLLM announces day-0 support for Kimi K3.1 Pro, Moonshot AI's 2.8T-parameter (104B active) multimodal MoE with a 1M-token context that adds a DSA sparse-attention indexer to all 24 full-attention layers of its KDA + MLA hybrid. The post details a packed KV cache for three kinds of state, token-sharded prefill attention (up to 1.69× faster TTFT at 340K tokens on 8× GB300), decode context parallelism with an exact top-k merge, a fused low-latency decode path, a DSpark speculator preview, AgentX benchmark results on GB300 and Rubin, zero-mismatch RL, and support on NVIDIA, AMD, TPU and Alibaba T-HEAD Zhenwu PPUs.
Why it matters: It is a detailed engineering account of how sparse attention, hybrid KV cache layout and parallelism choices interact, with measured numbers for anyone serving long-context MoE models.
U Mobile's Information Systems Division, working with AWS and AWS Partner Axrail, built AiDaH, an AI-Driven Agentic Helpdesk on Amazon Bedrock AgentCore, which now handles over 150 documented operational scenarios across six business divisions. According to U Mobile's internal measurements, monthly trouble ticket volumes fell by up to 84.5 percent in provisioning and network tickets, 81.6 percent in general inquiries, and 48.7 percent in billing and charging between January and September 2026. The post details AiDaH's six-layer architecture, its security foundation including a Well-Architected Security Review of the Landing Zone, and the spec-driven development approach using Kiro.
NVIDIA describes using NeMo to convert production evidence into prioritized issues and custom evaluations for improving agent prompts, tools, models, memory, skills, and harness code. The post notes that generic benchmark scores may not explain domain agent failures, such as choosing the wrong tool, following the wrong workflow branch, missing relevant context, or using an unnecessarily expensive model.
Daybreak Red brings GPT-5.6 Cyber to approved customers in AWS GovCloud (US-East) through Amazon Bedrock for authorized cybersecurity work.
Cloudflare launched new Security Analytics features that surface personal agent traffic, including a Personal Assistants category in the Bot Analysis chart, a Top statistics widget listing visiting agents, and per-user agent visibility for sites using Account Abuse Protection. It also expanded the Agents policy to allow per-agent settings of Allow, Block on pages with ads, or Block, renaming the setting to AI Crawler and Agent access policies. Cloudflare says its next goal is helping sites preserve user context when agents act as intermediaries.
Together AI introduces Together Compiler (TKCC), a continual optimization loop that uses high-throughput agents to generate inference-engine optimizations, built on "persistent engines" that hot-reload candidate forward passes without restarts and a two-tier engine design balancing measurement throughput against fidelity. TKCC reports up to 2.6x higher TPS across frontier open-source models in under 24 hours, state-of-the-art low-latency results on SemiAnalysis' InferenceX benchmark (1111 TPS on MiniMax M3.1-Flash, 1205 TPS on DeepSeek v4.1-Flash), and 1.7x over open-source megakernels on Llama 1B at batch size 1, enabled by 252x higher experiment throughput than baseline agentic systems. The post also says TKCC generalizes to weather modeling, PDE, time-series, and biology workloads, and is serving trillions of tokens today.
Why it matters: It offers a detailed look at how agent-driven, continual compilation addresses drifting inference traffic, with concrete throughput and benchmark numbers.
Together AI introduces "Polymorphic Inference," an approach for adapting inference to fast-changing model architectures, traffic shapes, and hardware, contrasted with the older "Static Inference" paradigm. The company announces Together Compiler, an AI-agent-driven "Continuous Compilation" optimization loop already running in production on some serverless endpoints, and previews upcoming work including self-serve compilation, shape-shifting speculative decoding, the ThunderAgent Router, post-training, and TogetherLink workload-aware model routing.
Together AI introduces Together Compiler (TKCC), a continual agent-driven system that recompiles inference engines as traffic drifts, using persistent engines, a two-tier fast/slow engine setup for throughput-fidelity balance, and a custom cost model for parallelism selection. TKCC reports 1.3-3x higher TPS across frontier open-source models in under 24 hours, state-of-the-art low-latency results of 1111 TPS on MiniMax M3.1-Flash and 1205 TPS on DeepSeek v4.1-Flash on SemiAnalysis' InferenceX benchmark, and 1.7x over open-source megakernels on Llama 1B batch size 1, enabled by 252x higher experiment throughput than baseline agentic systems. It also generalizes to weather modeling, PDE, time-series, and biology workloads.
Featured coverage of this story: 《Together Compiler: Continual Compilation for AI inference》
Lovable's founder recounts how the platform evolved from the 2023 GPT Engineer project into a product where users have created more than 70 million projects, repeatedly reinventing its agent design—from complex async subagents back to a predictable tool chain, then to "knowledge files" with retrieval instead of fine-tuning. He describes stateful sandboxes that keep development servers running for faster edit-check cycles and a framework called Camille for forking and merging entire running computers. He closes with three open problems: automating the full software lifecycle, making all types of software seamless to build, and building a better software stack.
This comparison contrasts Browser Use and Kernel cloud browser providers across pricing, stealth, performance, authentication, and developer experience. Browser Use offers headless browser time at $0.02/hour with no subscription, while Kernel bills per second at roughly $0.06/hour headless and $0.48/hour headful, with plans from $0 to $200 per month. The article notes Browser Use reached 90.5% of protected sites versus Kernel's 80.5% in a Browser Use-published study, and that lifecycle benchmark totals were 371.5 ms for Browser Use and 398 ms for Kernel on October 27.
Claude Code v2.1.318 adds an answer record when Claude Code asks to enable mods, assume_role on mantle upstreams of the Claude apps gateway, an effort option for a mod's $.model.fork, and sign-in expiry dates in claude auth status (loginExpiresAt) and claude -p JSON results (credential_expires_at). It fixes numerous issues, including --continue losing earlier conversation after malformed tool call retries, macOS stalls with many running Bash commands, permission prompts answered by stray keystrokes, and config save failures on shared network home directories. It also improves auto-update retries, MCP tool errors, remote session reconnects, and adds a No repository option for cloud sessions.
At its first annual Forge conference, Fireworks launched products aimed at helping companies build AI around their own data and tasks, including Ultra-fast inference on NVIDIA Blackwell GPUs reaching up to 1,500 tokens per second, a half-price Background Mode, and multi-day prompt caching. It also introduced Fireworks Nexus for bringing open models into existing coding and coworking tools, No Eval and Specialized Model Inference for training and serving custom models, and Fireworks Sovereign, now in private preview, which runs its inference engine inside customers' own cloud or data centers. Fireworks says it already manages over 25,000 GPUs in customer environments.
Databricks introduces UNIQUE constraints in Public Preview for Unity Catalog Delta tables in Databricks SQL and Runtime 18.2+, allowing tables to record multiple uniqueness guarantees beyond a single non-nullable primary key, with nullable columns and foreign key references supported. Constraints are informational and unenforced by default; after validation, marking them RELY lets the query optimizer eliminate eligible joins and DISTINCT aggregations, with benchmarks showing 7.9x and 12.0x speedups on TPC-DS SF10000.
Databricks MLflow is now a supported destination for native OpenTelemetry export from the Claude Platform, letting developers using the Anthropic SDKs, the Messages API and Managed Agents send traces to Databricks for debugging and evaluation. Spans are received through Zerobus Ingest and stored in Unity Catalog tables linked to an MLflow experiment, where they can be inspected alongside traces from other instrumented services and queried with SQL. Setup involves creating an experiment, configuring the Databricks destination with workspace ID, region and spans table, then running a task and inspecting the trace.
Call transcription converts phone or video calls into written text, typically via AI speech-to-text models, either after recording or in real time. Businesses use transcripts for searchable records, quality assurance and coaching, compliance documentation, and CRM logging. Legality depends on jurisdiction, with some regions requiring one-party consent and others all-party consent.
Baseten announced three launches extending its inference platform: Grid, a gateway, router and guardrail platform launching as a public preview tomorrow; Sandboxes, stateful, VM-isolated sandboxes moving from private to public preview on Thursday; and Loops, its serverless SFT and RL training infrastructure, becoming generally available Friday. The company says all pieces share the same optimized infrastructure and run on Multi-cloud Capacity Management across dozens of clouds, delivering 99.99% uptime.
The article argues that cost per successful task, not price per token, governs production economics for coding agents, and reports a 50-question auto-graded benchmark routing tasks with TypeSafe's Jev classifier across Gemini configurations. A frozen regex and prompt-length heuristic scored 93.8% on 16 development questions but fell 23.2 points to 70.6% on 34 held-out tasks, while Jev agreed with hand labels on all 34 and 48 of 50 overall; capping maxOutputTokens at 300 saved nothing on easy tasks and broke 7 of 25 hard ones. A router sending tasks to Flash-Lite first and escalating Jev-flagged complex ones to Flash on low thinking solved all 50, as did Flash on low thinking alone, and the article notes caching favors keeping long context-heavy turns on one model.
Meta introduces F3 Lightning, an infrastructure layer on top of its Facebook Feature Framework (F3) that decouples feature releases from shared execution so each of the 20,000+ features in an ads ranking request can be compiled, validated, deployed, and rolled back independently. To preserve F3's efficiency, it uses stable computation identifiers, a single shared execution plan, one shared memory buffer per request, and dense index mapping for direct array access. Meta reports comparable extraction features reach production about 3.6x faster than prior F3 with no increase in infrastructure compute cost.
Amazon Bedrock now supports in-country inference in India for Moonshot AI's multi-modal, open-weight Kimi K3 model via the in.moonshotai.kimi-k3 geographic inference profile, processing requests in the Mumbai and Hyderabad Regions for workloads with strict data residency requirements. The post explains global versus India inference profiles and walks through an example of OCR and document understanding for Indic-language documents, including structured extraction and follow-up questions in code-mixed Hinglish. It also covers prompt caching, service tiers, and CloudWatch monitoring, citing Ultrahuman's report of 80 percent lower LLM costs and 85 percent faster multi-turn chats with prompt caching.
This AWS post explains how Cartesia, an AWS Partner, uses State Space Models (SSMs) and AWS infrastructure to deliver sub-100ms text-to-speech (Sonic) and speech-to-text (Ink) at global scale. It details two deployment patterns for Sonic: an Amazon SageMaker AI model package via AWS Marketplace running in-VPC, and self-managed containers on EC2 GPU instances, and describes Cartesia's voice models operating inside Amazon Connect.
This post shows how to build a semantic layer for agentic AI using EDB Postgres AI's AIDB extension, where business meaning lives in Postgres COMMENT statements, join paths come from foreign keys, and governance uses GRANT and row-level security through the built-in MCP endpoint. A Strands Agents agent on Amazon Bedrock AgentCore queries the layer via AgentCore Gateway and an ALB to answer customer 360 questions, with two Postgres roles receiving different results for the same prompt based on column-level grants. AIDB also captures OpenTelemetry traces for each SQL execution as rows in the aidb_otel schema, queryable with ordinary SQL.
Gen Digital describes how its Norton Revamp professional reputation platform, launched in March 2026, uses Web Search on Amazon Bedrock AgentCore as a managed, MCP-compliant connector to ground personalized news feeds, content suggestions and goal recommendations in cited, real-time web results. The post details an event-driven architecture using Amazon Nova Lite, Bedrock and an AI Learning System for ranking, plus reported results including 99.9 percent uptime and 3x faster feature implementation.
This post explains how to configure Amazon Bedrock AgentCore Gateway for an on-behalf-of (OBO) token exchange with Microsoft Entra ID so an AI agent can call the ServiceNow REST API while preserving the calling user's identity. It covers creating Entra application registrations for the agent and a ServiceNow API connector, configuring a ServiceNow inbound OAuth integration with an OIDC provider, and setting up the gateway with MCP version 2025-11-25, an outbound OAuth client using the JWT authorization grant, and a target with the token exchange grant (scope plus requested_token_use: on_behalf_of). The post states that native OBO support removes the need for custom AWS Lambda interceptors to perform token exchanges.
This AWS post walks through connecting an Amazon S3 bucket as a knowledge base, enriching a Product_Sales.csv dataset with semantic descriptions, and combining both in a Space that a custom chat agent queries through a single conversational interface. The agent uses text-to-SQL for structured questions, cites sources across both data types, and can generate PowerPoint, Excel, and Word artifacts from chat prompts. It also covers prerequisites, sharing, best practices, security considerations, and cleanup.
NVIDIA describes an "AI-defined fab" in which accelerated computing, physics-based AI, AI agents and digital twins help semiconductor engineers shorten simulation cycles, predict process behavior and test changes virtually before physical trials. The article cites up to 10x acceleration for COMSOL multiphysics simulations with cuDSS, up to 17x for Siemens Calibre lithography workloads with cuLitho, and Lam Research predicting plasma behavior in milliseconds versus days for full simulation. It also covers Advantest using NeMo Switchyard agents to cut model-selection response times from hours to minutes and Applied Materials building fab digital twins on Omniverse libraries.
Amp introduced Service Accounts: workspace-owned accounts created by workspace admins that are not tied to a single user, with their own API keys and third-party credentials, whose threads are visible to and usable by other workspace members. They suit team-owned work such as codebase review and maintenance, recurring documentation checks, and programmatic invocations like a CI job that starts a thread via amp -ox using the service account's API key. Because anyone in the workspace can drive a service account's threads, credentials assigned to it should be ones you would be comfortable giving all workspace members.
Wiz describes how its Green Agent addresses three remediation bottlenecks—identifying the right owner via repository, project, catalog, CMDB and cloud log signals; tracing root cause across the Wiz Security Graph; and generating environment-specific fixes with 1-click pull requests or API/MCP access for agentic IDEs. The post cites Rogo on automatic assignee surfacing, Fireblocks on cutting daily triage time by more than 70%, and project44 on accelerating remediation velocity by 10x.
Cloudflare introduced Zero Wire, a public vulnerability intelligence feed on Cloudflare Radar that provides plain-language briefings on critical CVEs in Internet-facing software, covering impact, who should investigate, recommended actions, and links to vendor advisories and evidence. Each briefing includes a pre-compiled prompt for use with an AI agent to assess exposure, and Cloudflare notes that WAF mitigations are compensating controls rather than replacements for patching.
Angle Health, an AI-native health benefits technology company, piloted ElevenAgents voice agents for provider-service workflows, answering calls in eight languages and working directly with its core administration system. During the pilot, the agents handled about 80% of total provider call volume, with more than 90% resolved end to end without transferring to a person, and the provider team gained back nearly 9,000 minutes a day. Angle Health plans to expand the pilot to its commercial, brokerage and account management segments.
Heimstaden is using OpenAI's ChatGPT Enterprise and Codex to transform property management, cut costs, and empower employees across Europe.
PyTorchKR and XCENA co-hosted KVCache Meetup Korea on Sep 30, 2026, with Tensormesh sponsoring, featuring talks from XCENA, SK hynix, FuriosaAI, and LMCache on LLM inference and KV Cache optimization. Sessions covered CXL memory expansion and the Maru KV Cache storage engine, GPU and HBM utilization analysis with H100 GPUs and vLLM, request scheduling and KV Cache management in Furiosa-LLM on RNGD, and LMCache's MP Mode for unified KV Cache management. A survey of 72 responses cited the program (66.7%) and venue and facilities (41.7%) as positive points, with requests for better audio, screen visibility, interpretation, and real production examples.
Transformers introduces Model Integration Contracts (MICs), which pair a shrunk fixture model built from a real checkpoint's configuration with a runnable usage path and human-reviewed baselines, run on cheap CPU runners in PRs. Replaying frozen MICs over five months of commits showed a small UMT5 fixture flagged a decoder-attends-to-future-tokens regression from July 30 to September 28, 2026, which a forward pass alone would have missed. The tmic CLI and agents help draft contracts, and the MIC CI job currently reports failures without blocking PRs.
Agents in Amp can now collaborate with users and teammates in Artifacts, documents that belong to a single thread and that the agent, the user, and teammates can all edit. The agent writes an artifact instead of a long reply when it has something to read, such as a plan, report, or call notes, and when it returns to the artifact it reads the user's edits first and works them in rather than overwriting them. Users can open Views → Artifacts in any thread or ask Amp to write one.
Claude Code v2.1.317 adds a warning to /schedule when a new cloud scheduled task receives connectors you did not request, a confirmation before a web or shell tool call sends your account email address to the network, and onFailure: "block" for Agent SDK hook callbacks. It also adds anthropic.plan, anthropic.seat_type, anthropic.provider and anthropic.custom_base_url to OTel metrics, events and spans, plus a cost report endpoint at GET /v1/organizations/analytics/cost on the Claude apps gateway admin API. The release includes numerous fixes across MCP servers, auto mode, self-hosted runners, OpenTelemetry exports, VSCode, cloud sessions and Remote Control.
OpenAI describes how it built Pando, a Git-compatible backend designed for the scale of development that Codex makes possible.
In distributed AI workloads, a single GPU or fabric event can cascade into NCCL errors on other ranks, scheduler state changes, and thousands of downstream messages, so the reported exception shows where the workload stopped rather than where the failure began. The post explains how to run NVIDIA Attribution on sample workload evidence.
As distributed AI training scales, failures across hardware and software dependencies increasingly disrupt training progress, making fast, reliable recovery essential. The material notes that a stalled training rank can trigger an NCCL timeout, a GPU node can stop responding to the scheduler, or a straggler can slow the entire job, and that each disruption is manageable on its own.
Sierra has redesigned Agent Studio around Ghostwriter, its always-on agent for building agents, so users can investigate issues, edit journeys, run simulations, and test fixes within a single conversation. Ghostwriter now follows users through Agent Studio and sees what they are viewing, combining capabilities previously spread across Explorer, Sierra Assistant, and other specialized agents, with each piece of work kept in its own shareable or forkable session. The redesign also brings related agents into a single project, adds line-by-line change comparisons, Preview Chat and Simulations, and release governance with required approvals and controlled rollouts.