标签：#Agents

A2A has become like a standard for enabling agent to agent communication, we could use the a2a-sdk for running and configuring the a2a server and its features such as agent card, agent skills, agent executor, request handler etc. However we are going to go with a simplified approach here with strands where the agent card will be fetched automatically. Let's get started! Server Initialize a uv project for the a2a server and switch to that directory. uv init ~/strands-a2a-server cd ~/strands-a2a-server Add the required packages. uv add python-dotenv == 1.2.2 strands-agents[a2a] == 1.42.0 Change the code in main.py to look like below. $ cat main . py from dotenv import load_dotenv from strands import Agent from strands.multiagent.a2a import A2AServer load_dotenv () def main (): agent = Agent ( callback_handler = None , description = " A sample strands agent " , model = " us.amazon.nova-micro-v1:0 " , ) a2a_server = A2AServer ( agent = agent ) a2a_server . serve () if __name__ == " __main__ " : main () I like the simplicity here, as you see above, it's quite simple to start a basic a2a server from with in strands, with just a couple of lines of code, we didn't have to install the a2a-sdk separately. Run the code, to start the a2a server. $ uv run main.py INFO: Started server process [18006] INFO: Waiting for application startup. INFO: Application startup complete. INFO: Uvicorn running on http://127.0.0.1:9000 (Press CTRL+C to quit) Client Let's now do the client part on a separate terminal. Initialize the project and switch the directory. uv init ~/strands-a2a-client cd ~/strands-a2a-client Modify main.py code to look as follows. import asyncio from strands.agent.a2a_agent import A2AAgent async def main (): agent = A2AAgent ( endpoint = " http://localhost:9000 " ) agent_card = await agent . get_agent_card () print ( " Invoking remote agent with agent card: " ) for key , value in agent_card : print ( key , " : " , value ) print ( ' - ' * 20 ) while True : prompt = input

Not long ago, I saw articles analyzing how Chinese people obtain US model API at low prices through non-compliant means, and also saw Chinese developer sharing their Vibecoding experiences. Very interesting, it seems the outside world is finally starting to understand our daily lives. I want to share a complete perspective here: how an ordinary Chinese student, also developer, accesses the most advanced US models. Including the evolution of various access methods over 4 years, the practical experience of using various methods, and the problems encountered, etc. I will try to describe it objectively and truthfully. Let's start by going back to November 2022, when OpenAI released "ChatGPT": Phase 1: "ChatGPT" ChatGPT was released, and it was big news in China, even though it predictably did not serve China. Even though I was still a high school student at the time, I was still interested, after all, it was the first time I saw something truly close to "intelligence". How to access it? There are two types of services generally inaccessible in China: one is that the GFW blocks the domain name or IP of the service, and the other is that the service provider refuses IPs from China. ChatGPT is both. The solution is also simple, use a proxy, which is a basic skill for Chinese developers. In addition, registration requires receiving a SMS verification code. Chinese mobile numbers are definitely not an option, but the solution is not difficult either, find a verification code receiving platform, use a temporary number to receive the verification code. Thus, I started using ChatGPT, which now seems like a model that speaks slowly and is not very smart. Phase 2: "Mirror Sites" During high school, I didn't have many scenarios to use ChatGPT. I started using AI more when I entered university, as AI is well-suited for dealing with those annoying assignments. It was the second half of 2023, and there was a new way to access it: mirror sites. "Mirror sites" originally referred to an

The benchmark is the wrong story Anthropic shipped Claude Opus 4.8 this week. You probably saw the announcement post on Tuesday, the swarm of benchmarks on X by Wednesday, and somebody's curated leaderboard of "the new SOTA on SWE-bench Verified" by Thursday morning. By Friday everyone had moved on. That is the normal shape of a model release in 2026. It is also the wrong story. The benchmark delta from 4.7 to 4.8 is real but not load-bearing. The load-bearing story is the calendar. Opus 4.6 shipped late February. Opus 4.7 shipped in April. Opus 4.8 shipped this week, in early June. Three Opus generations inside four months. Whatever the headline numbers say about coding, agentic reasoning, or long-horizon tool use, the operating reality has already changed underneath you: if you run a production agent on a fixed model pin, you are now eating a migration tax every six to ten weeks. You can either notice that now and refactor, or notice it in late August when Opus 4.9 lands and your customer-facing agent regresses for the third time this year. This post is the second story. I am going to skip the benchmark recap — go read the model card — and tell you what to do before the next release lands. What Anthropic shipped The announcement post on anthropic.com confirmed three things and implied a fourth. The three confirmed: Opus 4.8 is the new default Opus tier model, ID claude-opus-4-8 . The previous defaults (4.7 and 4.6) remain accessible by explicit pin for at least 90 days. Fast mode is available on 4.8 the same way it shipped on 4.7 — same model weights, higher-throughput inference path, no quality downgrade. That matters because the practical difference between Opus and Sonnet for many workloads now comes down to fast-mode availability, not raw capability. The model card claims meaningful improvement on long-context coherence, agentic tool dispatch, and refusal calibration. The benchmarks back this up to roughly the degree we expect from a 6-week cycle — modest but

So far I've only been running openclaw agents and had a steep learning curve. "self-improvement" became a very attractive term on this journey. So I took a dive into Hermes Agent, the self-improving agent runtime from Nous Research. One of the first things I wanted to understand was a risk: what actually happens when you install a community skill? Skills are code and instructions that the agent will execute, and Hermes pulls them from an open ecosystem. So I read the install path in the source - instead of blindly trusting the docs. What I found is better than I expected in one way and structurally limited in another. What Hermes already has on board Hermes does not install external skills blindly. Every externally-sourced skill goes through a real gate before it lands on disk. In hermes_cli/skills_hub.py , the install flow is: fetch → quarantine → scan → policy decision → install or block-and-audit. The scan lives in tools/skills_guard.py and runs regex-based static analysis for known-bad patterns: secret exfiltration ( curl interpolating $API_KEY / $TOKEN / $SECRET ), reads of credential stores ( ~/.ssh , ~/.aws , ~/.gnupg , ~/.kube , and Hermes's own ~/.hermes/.env ), destructive commands, persistence, and obfuscation. If the scan blocks an install, the quarantined copy is deleted and the event is written to an audit log. This is more than most agent tooling ships with. If you remember the wave of malicious skills that hit competing ecosystems, a chunk of that class of attack would be caught here before anything ran. Someone thought about this. The part that doesn't scale imo The scanner produces a verdict — safe , caution , or dangerous . That verdict is then combined with a trust level to decide whether to install. The trust levels and their policies look like this: INSTALL_POLICY = { # safe caution dangerous " builtin " : ( " allow " , " allow " , " allow " ), " trusted " : ( " allow " , " allow " , " block " ), " community " : ( " allow " , " block " , " bloc

Production is down. Slack is on fire. Your phone is ringing. You've seen this exact error before — ConnectionResetError: [Errno 104] cascading through your FastAPI worker pool — but you can't remember exactly which Redis configuration tweak fixed it last time, who applied it, or how long the incident lasted. You're starting from zero again. Twenty minutes of context-building before you even touch a fix. I got tired of that feeling. So I built an AI agent that never forgets. The Problem With Generic AI in Production When production breaks, most engineers reach for their LLM of choice and paste in the stack trace. And the response is almost always the same: a competent, thoughtful, completely useless answer. The model has no idea that your team already tried increasing max_connections six weeks ago and it made things worse. It doesn't know that your infrastructure runs on a specific internal Kubernetes setup that changes how standard fixes apply. It gives you textbook advice for textbook problems, and your problems are never textbook. This is what I started calling the Round 1 problem. Round 1 — generic response: Error: ConnectionResetError: [Errno 104] Connection reset by peer Stack: redis.exceptions.ConnectionError in worker pool The agent responds with something like: "This typically indicates your Redis connection pool is exhausted. Try increasing max_connections in your Redis client config, add retry logic with exponential backoff, and check network stability between your app and Redis instance." Technically correct. Practically useless if you've already tried all three. The agent is reasoning from general knowledge, not from your specific production history. It has no memory of your past incidents. Every error feels like the first error. What I Built: Code Memory's Incident Agent Code Memory is a developer workspace I built in Next.js with a three-pane interface — a file explorer, a code viewer with syntax highlighting, and a real-time AI fix panel. But the core

Claude Cowork est sorti en 2026 et le distinguer des agents cloud classiques change tout pour les equipes techniques. Deux modeles, deux philosophies Un agent cloud (ChatGPT Operator, Mistral Agents, Gemini pour Workspace) fait des appels API vers des serveurs distants. Vos donnees quittent votre machine. La session prend fin quand vous fermez le navigateur. Claude Cowork fonctionne differemment : il tourne sur votre Mac, lit votre systeme de fichiers en direct, execute des bash commands, et continue sa tache quand vous fermez le laptop. Ce que cela change pour les equipes tech Contexte reel. Cowork peut lire vos logs, vos configs, vos repos locaux directement, sans copier-coller. Execution longue distance. Vous lancez un refactoring sur 40 fichiers, vous allez en reunion. La tache continue. Impossible avec un chatbot classique. Isolation des donnees. Pour les equipes qui travaillent sur des donnees sensibles (sante, legal, finance), garder les donnees en local repond a une contrainte non negociable. Les limites a connaitre Cowork necessite un Mac recent (Apple Silicon recommande). Le context window est partage entre linterface et les fichiers lus. Pour des taches qui necessitent une recherche web temps reel, un agent cloud reste complementaire. Pattern que je recommande aux equipes Dans les formations que janime pour des equipes de 10 a 100 personnes, on structure generalement comme ca : Agent local (Cowork) pour tout ce qui touche le codebase, les fichiers, les automatisations internes. Agent cloud pour les recherches, les comparaisons marche, les taches qui ont besoin dun acces web. Un workflow clair pour decider lequel utiliser selon la nature de la tache. Le point cle : ne pas les traiter comme interchangeables. Ce sont deux outils avec des forces differentes. Ce que les chiffres montrent Dans les equipes que jai accompagnees sur 18 mois, celles qui ont adopte ce pattern produisent en moyenne 40 % de code de configuration en moins de temps, avec moins de bugs l

What Ollama actually is Ollama is an open-source runtime for large language models that runs on your own computer — Mac, Windows, or Linux. Think of it as the “Docker for LLMs”: instead of wrestling with Python environments, model weights, and GPU drivers, you type one command and a model is running. The pitch is simple: keep your data on your machine, pay nothing per token, and work offline. When you run ollama run gemma4, Ollama downloads the model, loads it into your GPU’s memory (or system RAM if you don’t have a GPU), and drops you into a chat prompt. That’s it. Behind that simplicity, Ollama is doing a lot of work for you: Model management — pulling, versioning, and storing models from its registry, the way a package manager handles software. Quantization — automatically using compressed (GGUF) versions of models so a 27-billion-parameter model fits in consumer memory. GPU layer allocation — deciding how much of the model lives on your GPU versus CPU, based on the VRAM you have. Context and KV-cache management — handling the memory that grows as a conversation gets longer. A REST API — exposing everything on http://localhost:11434 so your own apps can talk to it. How it works under the hood Ollama is not itself an inference engine. It’s an experience layer wrapped around one. Under the hood it uses llama.cpp, the C++ engine that does the actual math of running a quantized model efficiently on CPUs and GPUs. As of v0.19 (March 2026), Ollama also uses Apple’s MLX backend on Apple Silicon — a change that delivered enormous speedups (on an M5 Max running Qwen 3.5, decode throughput nearly doubled). The workflow looks like this: You run a command — ollama run qwen3 from the terminal, or a request to the API. Ollama resolves the model — if it isn’t already downloaded, it pulls the GGUF weights from the registry. It loads the model into memory — splitting layers between GPU and CPU based on available VRAM. It serves responses — either interactively in your terminal o

been building AI agent infrastructure for the past few months. The two things that kept biting me — and kept coming up when I talked to other devs building agents — were runaway costs and agents doing irreversible things without asking first. So I built gvnr: an open-source MCP server that gives agents per-agent spend caps (hard-stop before a call if the budget's gone) and a human approval gate (agent asks, you get a mobile link, you approve or deny, agent waits). Both work as plain REST calls or MCP tools — no platform to adopt, no SDK. It's live. You can get an API key in one curl command and try the approval gate for free (it doesn't burn the trial ops). Source is at github.com/mightbesaad/gvnr . Here's what I genuinely want to know from devs building in this space: Does the spend-cap shape match how you think about cost control, or do you manage that somewhere else entirely? Is the approval gate useful if it's email-only and single-approver, or does that make it a toy? What flag would stop you from wiring this into an agent you actually run? Not fishing for encouragement — if this is solving the wrong problem, or solving it the wrong way, I'd rather know now.

The dangerous part of web extraction is not the error. The dangerous part is a clean JSON response that looks correct and is not. If an AI agent uses that output, the mistake does not stay inside a scraper. It moves into a report, a lead list, a price alert, a CRM update, or an automated decision. So before you trust any web extraction API in an agent workflow, test whether it fails honestly. Here is the checklist I use. 1. Test a real page, not a demo page Demo pages are usually polite little museum exhibits. Use pages that behave like the actual internet: a JavaScript-heavy product page a search results page a page with missing fields a login-gated page a blocked or rate-limited page a thin page that has layout but little useful content If the tool only looks good on clean static pages, you have not learned much. 2. Check whether the API separates fetch success from extraction success A page can return HTTP 200 and still be useless. Common examples: the final page is a login screen the visible content is a bot challenge the useful data loads after hydration and never appeared in the fetch the page contains a generic country selector instead of the product the source has navigation text but no actual item data The extractor should not treat these as success just because the request completed. A better response says something like: { "status" : "failed" , "failure_type" : "login_required" , "extracted" : null , "next_step" : "Use a public URL, authorised access, or sample content." } That is boring. Boring is good here. Boring means the agent can stop safely. 3. Ask for fields that are not on the page This is the easiest lie detector. Ask the extractor for something impossible: Extract the product name, price, stock status, warranty length, CEO name, office address, and refund policy. If the page only contains product name and price, the API should say the other fields are missing or low confidence. It should not politely invent them because the schema asked nicely.

TL;DR I built AutoMaintainer , a multi-agent AI system that transforms GitHub issues into production-ready pull requests during the Qwen Cloud AI Hackathon. It coordinates specialized agents (Issue Analyst, Developer, QA, Security, Documentation, Reviewer) to solve problems like a real engineering team—all while keeping humans in control. Here's what I learned. The Problem Open-source maintainers face a brutal reality: 📚 Overwhelming issue backlogs 🔄 Repetitive bug fixes and documentation gaps ⏱️ Code review bottlenecks 😴 Burnout from handling everything solo Existing AI tools help write code, but they don't orchestrate the entire workflow: planning, development, testing, security review, documentation, and human approval. What if we could build an AI engineering team that collaborates like real developers? The Solution: AutoMaintainer AutoMaintainer is a multi-agent orchestration system that mirrors a real software company: Issue Analyst – Reads GitHub issues, extracts requirements, assesses severity Architect – Analyzes repo structure, designs the implementation approach Developer – Writes code, updates files, creates new modules QA Tester – Generates tests, validates fixes, checks edge cases Security Agent – Scans for vulnerabilities, prevents dangerous patterns Documentation – Updates changelogs, PR summaries, release notes Reviewer – Scores code quality, recommends improvements Human Approval Gateway – Final human review before merge The result? A pull request that's analyzed, built, tested, secured, documented, and reviewed—all before a human ever sees it. Tech Stack Frontend Next.js – React framework for the dashboard UI Tailwind CSS – Rapid, utility-first styling TypeScript – Type safety for the frontend layer Backend FastAPI (Python) – Lightweight, async-first API Qwen-compatible LLM API – AI model integration for all agents SQLite + Async (aiosqlite) – Persistent pipeline and memory storage Redis-ready architecture – Prepared for distributed queuing Integr

LinkedIn’s Karthik Ramgopal and Prince Valluri discuss leveraging AI as a new execution model for large-scale engineering. They explain how to move beyond fragmented implementations by building platform abstractions for orchestration, structured context, and safe tooling like MCP. They share architectural insights from real-world coding, observation, and UI testing agents built at LinkedIn. By Karthik Ramgopal, Prince Valluri

It is time to put my proposition made in my previous blog post to the test. Is it possible to spec an application for execution by an agent without encoding it in source? Let's find out. One type of application every knowledge worker is familiar with is task management. Every task has a lifecycle status, dependencies on other tasks, and a history of progress. Let's give agents their own. TaskTrack is a simple but non-trivial task management system variant implemented as a Specify spec. It goes beyond checkbox-based to-do lists that agents sometimes use internally and mimics the key system features listed above. TaskTrack defines two procedures: a "Plan Authoring Run" to create an interconnected set of tasks from requirements and a "Plan Execution Run" to advance a previously authored plan toward completion. One execution run might not always be enough to achieve completion, because TaskTrack allows requesting human feedback and incorporating it during the next execution run. Furthermore, every execution run is divided into "Task Processing Run" sub-procedures to allow for advanced agent context management. TaskTrack implements all of this in less than 300 lines of text. If the implementation used source code, then, depending on the programming language, this would be enough space to implement only the required file I/O operations (TaskTrack uses files for simplicity, not a database). Natural language can easily become quite bloated, but a stringent, scientific writing style and extensive use of what the Specify standard offers can effectively counter that. The official test is, how could it be any other way, the implementation of yet another uninspired Breakout clone. The requirements, the completed TaskTrack plan, and the deliverable are contained in the repository. If you want to run the test yourself, the included README file contains the necessary information, including the launch prompts for both the authoring agent and the execution agent. Please note how both

The Quiet Threshold There's a moment in working with generative models that nobody really talks about, because it doesn't look like progress. It looks like surrender. For the first few months you write prompts. You optimize them. You collect tricks: chain-of-thought, role assignments, few-shot examples, the right magic words. You treat the model like a stubborn intern who needs very precise instructions. And it works — sort of. You get outputs. You ship things. Then one day you notice you've stopped doing any of that. You're just writing. You're typing the way you'd talk to a collaborator at 2am, half-formed sentences, the actual shape of your thinking before it's been edited into something presentable. And the model is answering as if it had been in the room the whole time. This is the quiet threshold. It's not a technical milestone. The model didn't get smarter. You stopped performing. Most people never cross it. They keep prompting at the machine because they're still treating it as an audience to impress, an authority to convince, or an obstacle to outmaneuver. They're managing how they look to a thing that has no opinion of them. And the outputs reflect that — polished, hollow, slightly anxious. The artists I trust on this stuff all describe the same shift: a point where they stopped writing FOR the model and started thinking THROUGH it. The work got rougher and stranger and more theirs. The tool disappeared. What's left is just the practice — the same one you had before, but louder, faster, more honest with itself. I suspect this is the actual measure of fluency with these systems. Not the prompts you can write. The masks you can finally drop.

Lets start our discussion from 2010 . Timeperiod 2010 - 2020 we have predictive AI models such as Recommendation systems , customer segmentation etc .. From 2020 the when the generative models were introduced to the world then the landscape was completely changed . We have this generative era till 2022 . Then industry was stepped into a new era called "Augumentation" models like AI Copilot . This was continued from 2022-2024 . Then came AI Agents—one of the most transformative innovations of the modern AI era. Unlike traditional AI systems that primarily generate responses, agents can reason, plan, use tools, and execute tasks autonomously. Today, the industry is rapidly evolving toward Autonomous Systems, where multiple specialized agents collaborate through orchestration frameworks to solve complex real-world problems. The best AI Timeline : Traditional ML ↓ Deep Learning ↓ Transformers (2017) ↓ Foundation Models ↓ LLMs (GPT Era) ↓ Prompt Engineering ↓ Embeddings ↓ Vector Databases ↓ RAG ↓ Function Calling ↓ AI Agents ↓ Agent Frameworks ↓ Multi-Agent Systems ↓ MCP ↓ Agentic AI ↓ Autonomous AI Organizations Just in the span of 6 years we saw a drastic change in the evolution of AI. Can't imagine how this AI is going to be in the next few years. ai #machinelearning #python

Every AI agent ships with the same bottleneck: it can only reason over what it can reach. MCP servers dissolve that boundary. They expose tools, resources, and prompts to any compliant client over a JSON-RPC wire format so lean you can implement it in an afternoon. Yet most developers grab a framework, copy a template, and ship something they can barely debug. Forge starts differently. You will build an MCP server from the bare protocol up, understand every byte on the wire, and gain the mental model that makes every future server trivial. The Idea (60 Seconds) MCP is a JSON-RPC 2.0 protocol. A client sends a request. Your server returns a response. Three request types power the core loop: initialize , handshake. Client and server exchange capabilities. tools/list , discovery. Server returns every tool it offers, each with a JSON Schema describing its inputs. tools/call , execution. Client names a tool and passes arguments. Server runs the handler and returns structured content. Transport is either stdio (JSON-RPC over stdin/stdout) or HTTP (Streamable HTTP). Stdio is the simplest place to start: read a line from stdin, parse it, dispatch, write a line to stdout. That is the entire architecture. Everything else is error handling, schema validation, and ergonomics. Why This Matters MCP servers are the new APIs. Where REST gave machines endpoints, MCP gives agents tools with typed inputs and structured outputs. Every integration layer from IDE assistants to autonomous workflows converges on this protocol. The standard is young. The primitives are stable. The surface area is small enough to hold in your head all at once. Knowing the wire format gives you three advantages frameworks obscure: Debugging , when a tool call fails, you can read the raw JSON-RPC message and pinpoint the fault in seconds. Portability , any language, any runtime, any transport. Write a server in Bash if you want. The protocol is the contract. Evolution , MCP will add capabilities. Understanding

I Read Your AI Agent Logs So You Don't Have To: A $149 Service That Beats Another Dashboard What if the cheapest fix for your broken AI agent is a stranger reading 40 hours of traces for $149? I spent the last month doing exactly that — reading roughly 40 hours of production logs from teams running LangGraph, CrewAI, and AutoGen agents for paying customers. Not building observability dashboards. Not comparing LangSmith vs Langfuse. Reading the actual traces and writing up what was wrong, what to fix, and in what order. Three observations from those 40 hours: The dashboard was never the problem. Every team already had LangSmith or Helicone or a homegrown equivalent logging every LLM call. None of them were reading the logs. The "fix" was almost always one of seven patterns. I kept seeing the same shapes — stuck retry loops, idempotency gaps, tool-call argument drift, etc. — dressed up in different framework jargon. The teams that asked for "another tool" were the ones least likely to use it. They had 14 tools. The teams that paid for an hour of my time were the ones who said "I don't have time to look at this myself." That second group is who I'm now building a $149 service for. Here's why I think it works, what the deliverable looks like, and where the limits are. Why a $149 fixed-fee reading and not an hourly rate I tested three pricing models against the same deliverable: a written diagnostic of an agent's last 7 days of traces, prioritized fixes with code-level examples, and a 30-minute async follow-up. Model Conversion Avg revenue / inquiry Notes $200/hr (estimated 3hr) 2/40 inquiries $15 (lost 38 to sticker shock) Freelance default, fails on cold traffic $1,500 flat project 0/40 inquiries $0 Above the "I'll just keep it broken" threshold for most small teams $149 fixed diagnostic 11/40 inquiries $41 Below "another contractor" threshold, above "free advice" The $149 number is the inversion point — low enough that a stressed eng lead can expense it without a meet

You have explained your tech stack to your coding agent four times this month. You mentioned your preferred approach to a problem in January, and your agent has no idea it ever happened. You corrected a decision last week and the old version is still surfacing. You set up context at the start of every session because there is nowhere for it to go at the end. This is not a model problem, as GPT-4, Claude, and Gemini all have the same limitations. The model is stateless. They all have inbuilt memory, and still every session starts from zero unless you have the infrastructure to persist what matters and surface it at the right moment. That sophisticated memory infrastructure is what most developers do not have. VEKTOR Slipstream v1.6.3 is a local-first memory SDK for AI agents. This release adds the layer most memory systems skip: not just storing what you tell it, but managing what should still be there months later: curation. What you actually get Before the architecture: What changes for you as a developer embedding this SDK. Every AI memory system forces decisions you didn’t realise you were making. Where does your agent’s context actually lives, is it on your machine or on someone else’s server? Are you paying per token every time your agent understands a memory, or does that happen locally? When you connect your GitHub, your calendar, your files — where does all that data go, and who can see it? Most memory systems answer all four questions for you, quietly, in their terms of service. VEKTOR’s answer to all four is the same: your machine, your data, your rules. Memory lives in a single SQLite file you own. Embeddings run locally on CPU — no API calls, no per-token cost, no data leaving the process. MCP connectors spawn as local stdio processes; nothing is routed through an external service. There is no telemetry, no cloud sync, no account required. If you want to understand exactly what your agent knows about you, you open the database with any SQLite browser and

Anthropic published a thoughtful guide to making skills. It is worth reading, but it's a map of work you should not have to do. The Claude Code team wrote a piece on how they use agent skills . If you make skills, read it. It is honest and tells you something important: making a good skill is real work. Here's what the guide covers. It sorts skills into nine categories. It explains progressive disclosure, where the agent knows which files to load and when. It covers scripts, config files, combining skills together, and writing the description so the model reaches for the skill at the right moment. All of that is true and useful. It is also a lot to learn. And most of it exists only because you are doing the work by hand. We're SkillsCake . We make and score agent skills all day. So we read this guide a little differently than someone meeting skills for the first time. Here's what we think. Skills are infinite The guide splits skills into types: library reference, verification, and so on. That is a helpful way to teach a class. It is not what a skill actually is. A skill is prose that tells an agent how to do one thing, sometimes with scripts attached. The set of possible skills is not nine boxes. It is every job you could describe in writing; it's infinite. Categories are how a person gets a handle on something that open-ended. They are scaffolding for learning, not the shape of the thing. This matters because the moment you think in categories, you start bending your skill to look like the example in its bucket. Your real job rarely fits the bucket. The best engineered skill is the one written for your exact task, by an expert. Doing it yourself might not be worth it Progressive disclosure, scripts, config, descriptions tuned for the model, gotchas earned by failing, and eval loops: none of that is busywork. It's how a good skill gets built by hand. The guide is not overcomplicating anything. It is being honest about what the manual path costs. But that is the poin

It all started in a plaza. One guy with apples, another with wheat. They looked at each other, negotiated, and traded. That's how commerce worked for thousands of years: face to face, hand to hand, trust to trust. If you wanted to buy something, you had to go where it was. If you wanted to sell, you had to wait for someone to show up. Commerce had a physical limit: your body. You couldn't be in two places at the same time. Your market was your street, your town, your city. Nothing more. Then internet came along and someone asked: what if the store doesn't need walls? E-commerce eliminated distance. Amazon started selling books from a garage. MercadoLibre connected a seller in Santiago with a buyer in Antofagasta. Shopify gave an online store to anyone with a credit card. Suddenly, an artisan in southern Chile could sell to the entire country. An entrepreneur in Colombia could have clients in Mexico. The market stopped being a street and became the planet. But e-commerce had a problem nobody wanted to see: it still needed a human behind it. Someone had to update the inventory. Someone had to answer the questions. Someone had to make the quotes, check the payments, control the stock, send the shipments, analyze the metrics, decide the prices. E-commerce digitized the storefront, but it didn't digitize the operation. And that's where we are now. MCP-Commerce is not a term that exists yet. I'm inventing it because I need a name for what's coming. MCP — Model Context Protocol — is a protocol that lets AI use tools. Not "display" tools. Use them. Read a database, send an email, create an invoice, update an inventory, analyze this month's sales. In traditional commerce, you were the store. In e-commerce, you had an online store. In MCP-commerce, the AI IS your operation. It's not a chatbot that answers questions. It's a system that manages your entire business through conversation. You say "how much did I sell this week" and it responds with real data. You say "I need to c

This is part sixteen in a series about managing the growing pile of skills, scripts, and context that AI coding agents depend on. The 0.8.0 release notes cover the storage and pipeline changes that shipped alongside this rewrite; Part thirteen covers how the new profiles.improve config drives the improve pipeline. Config files are where projects go to accumulate technical debt quietly. Each new feature gets a new key. Each new key gets a new parser. Each parser has slightly different error handling, slightly different defaults, and slightly different ideas about what "invalid" means. Nobody notices until a user files an issue that says "I had a typo in my config and akm just silently used defaults for three weeks." That was the state of akm's config layer going into 0.8.0. What the Old Shape Looked Like The v1 config had three top-level blocks that grew independently over two years: llm.* for LLM connection settings, agent.* for agent process settings, and llm.features.* boolean flags gating per-feature LLM calls. The features block was nested under llm for historical reasons even though many features used the agent, not the LLM. The agent's per-process map lived under agent.processes , while LLM-gated features used llm.features.index.metadata_enhance style dotted paths. Each block had its own parser function. parseLlmConfig , parseEmbeddingConfig , parseIndexConfig , and a dozen more. The comment at the top of the new config-schema.ts is blunt about it: the Zod schema "replaces the ~1.4k LOC of legacy per-shape parsers." The problems that accumulated in that ~1.4k LOC: Unknown keys were silently accepted. If you wrote llm.temperaure (typo), the parser ignored it and fell back to the default temperature. No warning. You tuned a key that did nothing. Bad JSON was masked. The config loader caught JSON parse errors and fell back to DEFAULT_CONFIG — the compiled-in defaults. Your entire config file could be corrupt and akm would start without complaint, using defaults a