Field notes on agentic AI
The blog.
Models, playbooks, and honest takes on making AI agents useful — written by the small team building Agentic AI.
What Are MCP Tasks? Long AI Agent Jobs in Claude Code, Explained
MCP Tasks let an AI agent hand a long job to a tool server and keep working until the result is ready. What they are, how they work in Claude Code, and limits.
Read articleWhat Is Canva Craft? Canva’s First AI Image Model, Explained
Canva Craft is Canva’s first in-house AI image generator, launched October 22, 2026. What it does, where to try it, the API, and how it compares to Dream Lab.
Read articleWhat Is Dessa AI? Block’s Voice Model Trained Only on Speech
Dessa AI is Block’s full-duplex voice model, announced October 23, 2026 and trained only on human speech. What it is, how to try it, and if you can download it.
Read articleWhat Is the OpenAI Decisions API? Fast AI Choices, Explained
The OpenAI Decisions API returns a yes/no, a pick or a score instead of text. Now generally available on GPT-6 Luna at $0.10 per million input tokens.
Read articleWhat Is Anthropic Sandbox Runtime? The srt Tool for Safer AI Agents, Explained
Anthropic Sandbox Runtime (srt) is a free tool that fences an AI agent off from your files and the internet, with no container. How it works, setup and limits.
Read articleWhat Is Claude Opus 5.5? Anthropic’s Cheaper Top Model, Explained
Claude Opus 5.5 is Anthropic’s model from September 22, 2026: about 40% cheaper than Opus 5, faster, and ahead of Fable 5.1 on its own tests. Price, access, scores.
Read articleWhat Is GPT-6 Astra? OpenAI’s Top Model, Explained
GPT-6 Astra is OpenAI’s flagship model, released September 3, 2026. What it does, what it costs, who can use it, and how it compares with Claude Fable 5.1.
Read articleWalmart AI Agents: Agent Gateway and Agent Profiles, Explained
Walmart AI agents can now shop for you through Agent Gateway, with Agent Profiles and spending limits like $50 or $100. What changed, what is safe, and when.
Read articleWhat Is Agent Compute Engine? Google’s MicroVM for Every AI Agent
Agent Compute Engine is Google Cloud’s new service that gives each AI agent its own hardware-isolated microVM. What it does, when it opens, and what it costs.
Read articleWhat Are Gemini Skills? Google’s Replacement for Gems, Explained
Gemini skills are reusable instructions you run with a slash in any Gemini chat. They replace Gems starting November 2026. How they work and what changes.
Read articleWhat Is Kling 4.0? The 30-Second AI Video Model, Explained
Kling 4.0 is Kling AI’s new video model, launched October 15, 2026. What it does, the 30-second limit, Omni Reference, Flash vs full, price, and how to try it.
Read articleWhat Is Kimi K3.1 Pro? Moonshot’s New Model, Price and Benchmarks
Kimi K3.1 Pro is Moonshot AI’s new flagship, out October 23, 2026. What it is, what it costs, how it scores against Claude Opus 5.5, and when the weights arrive.
Read articleWhat Is Claude Duet? Anthropic’s Proactive AI Agent, Explained
Claude Duet is Anthropic’s proactive AI agent, launched October 21, 2026. What it does, who can join the waitlist, what it costs, and how it compares to Dots and Muse.
Read articleWhat Is Mistral Large 4? “Le Chonk,” the 1T Open Model, Explained
Mistral Large 4 (Le Chonk) is Mistral’s 1-trillion-parameter open-weight model, in preview since October 6, 2026. Price, benchmarks and when the weights drop.
Read articleWhat Is Microsoft Decision-1? The AI Model That Only Picks Answers
Microsoft Decision-1 is a decision model built on Qwen3.5-9B that returns a probability for each answer instead of text. Price, speed claims and Jev compared.
Read articleWhat Is Carbon-X? Hugging Face’s Model That Lets You Chat With DNA
Carbon-X is Hugging Face’s open 14.8B model that reads raw DNA and answers questions about it in plain English. What it does, benchmarks, cost and limits.
Read articleWhat Is Spark X2.6? iFlytek’s New AI Model, Explained
Spark X2.6 is iFlytek’s new AI model, launched October 22, 2026 and trained on Chinese chips. Specs, reported price, and how to try the free open 4B version.
Read articleWhat Is 1Password for Agents? AI Logins Without Your Password
1Password for Agents, launched October 22, 2026, lets AI agents like Muse and Grok Bot sign in for you without seeing your password. How it works and who gets it.
Read articleClaude Fable 5.5 Release Date: What Is Confirmed So Far
Claude Fable 5.5 release date: Anthropic has not announced it yet. What the Azure listing, the partner-testing leak and Fable 5.1 tell us about when it may land.
Read articleGemini for Small Business: Google’s New Business Hub, Explained
Gemini for small business now has its own hub in the Gemini app, since October 20, 2026. What the brand, finance and app tools do, and what is still unclear.
Read articleWhat Is NVIDIA OpenShell? The Safety Runtime for AI Agents
NVIDIA OpenShell is a free, open-source runtime that fences in AI agents. What it does, the new reference architecture from GTC Berlin, and who it is for.
Read articleWhat Is ServiceNow Arc? The Nvidia-Backed Work Agent, Explained
ServiceNow Arc is a personal AI agent for work, built with Nvidia and generally available October 21, 2026. What it does, who gets it, and what it costs.
Read articleWhat Is PHP2Shell? The AI-Found PHP Flaws, Explained
PHP2Shell is a pair of critical PHP flaws (CVE-2026-109618 and CVE-2026-109619) patched October 21, 2026, one found with OpenAI’s GPT-5.6 Sol. What to do.
Read articleOpenAI on Google Cloud: What the New Deal Means
OpenAI on Google Cloud, explained: GPT models are coming to Model Garden, Antigravity and Gemini Agent. What was announced Oct 21, 2026, when, and what is unknown.
Read articleWhat Are Gemini Launchpads? Google’s AI Agent Hubs for Government
Gemini Launchpads are AI agent hubs for US federal agencies from Google Public Sector and Accenture Federal Services, announced October 19, 2026. Here is how they work.
Read articleWhat Is Timestral? Mistral’s Time-Series Forecasting Models, Explained
Timestral is Mistral’s first family of time-series forecasting models, released October 15, 2026. The four sizes, benchmarks, license, and how to try it.
Read articleWhat Is the x401 Protocol? Proof’s ID Check for AI Agents
The x401 protocol is Proof’s open standard, launched October 15, 2026, that lets websites ask an AI agent to prove which verified person it acts for. x401 vs x402.
Read articleOpenAI COBOL Update: GPT-6.1 Sol Hits 97.9% on Legacy Code
OpenAI COBOL news: on October 19, 2026, OpenAI said GPT-6.1 Sol migrated 97.9% of COBOL test programs. What changed, what MultiLangBench is, and the limits.
Read articleWhat Is DeepInfer? DeepSeek’s Open-Source Inference Engine, Explained
DeepInfer is the inference engine DeepSeek uses to run its own AI models, open-sourced October 20, 2026. What it does, what is missing, and who it is for.
Read articleWhat Is Voxtral 3? Mistral’s Voice Agent Models and SDK, Explained
Voxtral 3 is Mistral’s new set of speech models plus a voice agent SDK, launched October 20, 2026. The four models, prices, languages and how to try it.
Read articleWhat Is Gemini 4 Argon? Google’s New Frontier Model, Explained
Gemini 4 Argon is Google’s new frontier AI model, out for everyone since October 13, 2026. What it does, the price, who can use it, and whether it is free.
Read articleWhat Are Claude Dynamic Workflows? Up to 1,000 Agents, Explained
Claude dynamic workflows let Claude write a small program that runs many AI agents at once. What they are, where to use them, the limits, and what they cost.
Read articleWhat Is the Anthropic Public Benefit Fund? The 5% Pledge, Explained
The Anthropic Public Benefit Fund, announced October 18, 2026, gets 5% of Anthropic’s shares. How it grows, what it can fund, and what is still unknown.
Read articleWhat Is MiniMax M3.1 Flash? The Space Bunny Model, Explained
MiniMax M3.1 Flash launched October 19, 2026. What it is, the $0.15 price, its agent benchmarks, the Space Bunny preview, and how it compares to DeepSeek.
Read articleWhat Is Nemotron 3.5? Nvidia’s Open Models for AI Agents
Nemotron 3.5 is Nvidia’s family of free, open AI models built for agents. What Super VL, Bolt and Lightning are, what they need to run, and how to try them.
Read articleWhat Is Mercury 3? Inception’s Diffusion AI Model, Explained
Mercury 3 is Inception Labs’ new diffusion AI model, out Oct 19, 2026. How it writes 1,068 tokens a second, what it costs, and how to try it with free tokens.
Read articleWhat Is DeepSeek V4.1 Flash? The October 17 Update, Explained
DeepSeek V4.1 Flash got a new version on October 17, 2026. What changed, the benchmark gains, the API price, and whether it is free to try, in plain English.
Read articleWhat Is Muse Spark Open? Meta’s Open-Weight Model, Explained
Muse Spark Open is Meta’s new open-weight AI model, released October 15, 2026. Is it open source, can it run on a Mac, and how it compares to Muse Wonder.
Read articleWhat Is Muse Wonder? Meta’s First Frontier Model, Explained
Muse Wonder is Meta’s first frontier AI model, launched October 12, 2026. Muse Wonder vs Muse Wonder Full, price, benchmarks, and how it compares to Opus 5.5.
Read articleWhat Is Jev AI? The Model That Decides Instead of Writing
Jev is TypeSafe AI’s System One model. It returns decisions and confidence scores instead of text. What it does, the speed claims, and why agents need it.
Read articleWhat Are OpenAI Dots? The Always-On AI Agents, Explained
OpenAI Dots are always-on AI agents launched September 29, 2026. What they do, what they cost, where they work, and the safety questions worth knowing.
Read articleWhat Is GPT-5.6? OpenAI’s Sol, Terra & Luna, Explained
GPT-5.6 is OpenAI’s new model family, released July 9, 2026. What Sol, Terra, and Luna mean, what each one costs, and why the US government reviewed it first.
Read articleBest Free AI Agent Apps in 2026 (No Subscription, No Login)
The best free AI agent apps in 2026, including which ones work with no subscription, no account, and no email. What each free tier really gives you.
Read articleBest AI Agent Apps for iPhone in 2026 (Tested Picks)
The best AI agent apps for iPhone and iPad in 2026, ranked by what they do well: agent teams, writing, research, and which ones work with no account.
Read articleBest Agentic AI Apps in 2026: 7 Picks, Honestly Compared
The best agentic AI apps in 2026, compared by what each is actually good at: agent teams, writing, research, coding, and free options with no account.
Read articleWhen Will Claude Fable 5 Be Back? It Returned on July 1
Claude Fable 5 is back. Access was restored on July 1, 2026 after the US lifted its export control order. The full timeline and what changed on return.
Read articleWhat Is Claude Fable 5? Anthropic’s New Model, Explained
Claude Fable 5 is Anthropic’s Mythos-class AI model, released June 9, 2026. What it is, how it’s kept safe, pricing, and why it matters for AI agents.
Read articleAI Agents on Your iPhone: The 2026 Practical Guide
How to run real AI agents on iPhone and iPad: what to look for, privacy questions worth asking, and how to get an agent team working in under a minute.
Read article25 Copy-Paste Prompts That Make AI Agents Genuinely Useful
Field-tested prompts for writing, coding, research, studying, planning, and multi-agent teams — with the one structural trick that makes agents deliver.
Read article10 Real Ways People Use AI Agents in 2026
Real, unglamorous, useful: ten ways people actually use AI agents in 2026 — from inbox triage and trip planning to debugging, studying, and job hunting.
Read articleHow AI Agents Actually Work: The Agent Loop, Explained
Plan, act, observe, repeat — the loop behind every AI agent. How agents use tools, keep context, recover from errors, and where they still fail.
Read articleAgentic AI vs. Generative AI: What’s Actually Different?
Generative AI creates content when you ask. Agentic AI pursues goals — planning, acting, and checking its own work. A plain-English comparison with examples.
Read articleWhy Two AI Agents Beat One (and Four Beat Two)
Specialization, critique, and division of labor work for AI agents like they work for people. Why multi-agent team sessions beat one generalist agent.
Read articleStop working alone.
Give any task to a team of AI experts on your iPhone. Start with 3 free tasks, then Agentic AI PRO from $34.99 a year.
3 free tasks · No account · No login
