LangChain Company Harness: 5 Parts Internal Agents Need
LangChain's internal agents for sales, marketing and engineering needed the same five parts. A company harness checklist for teams building internal agents.
Using Blender with Coding Agents on macOS: A Working Workflow
How to Set Up DESIGN.md So AI Agents Generate Brand-Consistent UIs
How to Use Git Effectively with Coding Agents
The Agentic Stack 2026: The 'GitHub Copilot CLI' Workflow
Stack #8: The Local LLM Infrastructure Blueprint
The Agentic Stack 2026: The 'Autonomous Researcher' Blueprint
Anthropic: When One Agent Loop Beats a Team of Subagents
Anthropic says one agent loop with skills and tool search often beats subagents on quality, cost and latency. A four-step test for teams running agent teams.
OpenMobile-2: Open Phone Agents Hit 79.9 on AndroidWorld
OpenMobile-2 releases open phone agents, 110+ training apps and the full recipe. Why app count and app-native tools mattered more than RL for agent builders.
Coding Agent Harnesses: Study Finds They Buy Tokens, Not Wins
A coding agent harness study ran Claude Code, OpenCode and mini-SWE-agent with the same models. Pass rates stayed within noise; cost per task varied up to 3x.
Kimi K3.1 Pro: Near-Frontier Scores, Open Weights Due Nov 4
Kimi K3.1 Pro scores 55 on the Artificial Analysis index, 3 points behind Claude Opus 5.5, with open weights due Nov 4. What agent builders should test first.
Agent Skills Joins the Agentic AI Foundation, With Open Responses
Anthropic donates Agent Skills and OpenAI donates Open Responses to the Agentic AI Foundation. What vendor-neutral standards mean for teams building AI agents.
VocabX: How a Custom SLM Vocabulary Cut Inference Cost 77%
Dharma-AI rebuilt a fine-tuned Qwen3-4B's vocabulary around token cost, not frequency, and cut SLM inference cost 77% while quality rose. What teams can learn.
Claude Duet: Anthropic's Always-On Agent Asks Before It Acts
Claude Duet is Anthropic's proactive agent app for Pro and Max users. How it works, what it can't do even with approval, and how it compares to Dots and Muse.
OpenAI Models on Google Cloud: GPT-6 Joins Gemini and Claude
Google Cloud adds GPT-6 Astra, GPT-6.1 Sol and GPT-6 Luna to model garden in private preview. What it changes for billing, governance and multi-model teams.
Mistral Voxtral 3: A Voice Agent Stack at 4 Cents a Minute
Mistral's Voxtral 3 voice agent stack bundles transcription, speech and a LiveKit SDK. What its agentic AI pricing means for teams building phone agents.
NVIDIA Nemotron 3.5 Embed, Rerank and Parse for Agent Retrieval
NVIDIA's Nemotron 3.5 Embed, Rerank and Parse models target agent retrieval. What the benchmarks show, the 14% token savings claim, and who should test them.
AI Agent Work Reports: Why Models Hide Mistakes They Can See
AI agent work reports often omit flaws the model already spotted. A Google, MIT and Harvard study found one prompt sentence fixes most of it, but not all.
ChatGPT in Chrome: The Agent Now Works Inside Your Signed-In Tabs
The ChatGPT Chrome extension can now read open tabs and act on them through Computer Use. Why signed-in sessions make site permissions the real decision.
DeepSeek V4.1 Flash 1017: 77% on DeepSWE at 20 Cents a Task
DeepSeek V4.1 Flash 1017 claims 77% on DeepSWE for under $0.20 per task, while rivals cost $2 to $10+. What the numbers mean for teams running coding agents.
Muse Spark Open: Meta's 816B Open Model Runs Like a 42B One
Muse Spark Open is Meta's open-weight agentic coding model: 816B parameters, 42B active, 1M context. What it takes to run it, and who should try it first.
Nemotron 3.5 Super VL: Nvidia's Open Model for Always-On Agents
Nemotron 3.5 Super VL is Nvidia's open model for always-on enterprise agents: 120B parameters, 12B active, open data. What it means for self-hosted agents.
Agent Evals: A 5-Step Framework From LangChain's LangSmith Team
Agent evals start with 10 to 20 traced examples, not a benchmark. LangChain's five-step framework for offline, online and LLM-judge evals, and its limits.
Context Rot: How Deep Agents Keeps Long-Running Agents Focused
Context rot degrades long-running agents as tool output piles up. How LangChain's Deep Agents offloads, summarizes and isolates context, and what to tune.
Anthropic Scion: Why Agents Outgrew Git at 30,000 Merges a Day
Anthropic Scion replaced git after merges rose from 2,500 to 30,000 a day. How its always-online design works, and what agent-heavy teams should borrow.
LFM2.5-24B-A2B: An On-Device Agent Model With 2B Active Params
LFM2.5-24B-A2B runs on-device agents with only 2B active parameters, leading on tool use but trailing on coding. What the benchmarks show and where it fits.
LangSmith AI Search: Finding Agent Failures by Behavior
LangSmith AI Search finds agent traces by behavior, such as false claims of success, using a model that reads each trace. How it works and where it falls short.
AI Agents Context Reset: Fork-and-Flush Lifts Scores 66%
A context reset helps long-running AI agents escape idea basins. Fork-and-Flush beat single runs by 66% on equal compute. What it means for agent design.
Self-Improving AI Agents: Sakana MASS and Its Shared Blind Spots
Sakana AI's MASS lets one model solve, judge, and refine its own work. Self-improving AI agents got better, but shared blind spots let errors pass as progress.
AI Agent Teams: Up to 5.1x the Cost, Rarely Better Quality
AI agent teams cost 1.8x to 5.1x more than single agents in Vals AI's coding test, and only 1 of 4 gained quality. Why higher effort often beats a team.
AI Research Agents: Epoch Finds Polished Reports, Thin Results
Epoch AI's InnovationEval gave AI research agents 3,000 GPU-hours. The best recovered 15% of a human method's gains, and the reports hid best-of-run picking.