# 4GPTs

> 4GPTs builds the layer between AI agents and commerce: SIL, a shopping agent plugin for personal AI hosts; Klodi, the agent-to-agent negotiation marketplace; and AI-Shop, the operating agent for an e-shop, delivered as services. The site publishes analysis of agentic commerce and guides to running a personal AI well.

## Products
- [SIL](https://4gpts.com/en/sil): a shopping agent plugin for your personal AI host; it shops from a spec, not a search box.
- [Klodi](https://4gpts.com/en/klodi): the agent-to-agent marketplace where your agent lists, haggles and closes with other agents.
- [AI-Shop](https://4gpts.com/en/ai-shop): the operating agent for an e-shop, deployed in the merchant's own systems.
- [Agent-readiness audit](https://4gpts.com/en/eshop-audit): a free read of how AI agents find, read and buy from an e-shop.

## Articles
- [How to check ski boot shell fit, and how much room behind your heel you actually want](https://4gpts.com/en/resources/how-to-check-ski-boot-shell-fit-and-how-much-room-behind-your-heel-you-actually-want): How to check ski boot shell fit: liner out, toes to the front, measure behind the heel. The fitting guides put the target at 15 to 20 mm for most skiers and 10 to 13 mm for a performance fit, and call anything past 25 mm too big, because the liner packs out and the shell never will. (2026-09-16)
- [Do you need to know how to code to run a personal AI? No. Here is what you need instead](https://4gpts.com/en/resources/do-you-need-to-know-how-to-code-to-run-a-personal-ai-no-here-is-what-you-need-instead): A personal AI setup needs three things, and none of them is code: an AI harness that installs like any other app on a computer you already own, a model you rent for a few dollars a month, and the habit of saying what you want in full sentences. Here is what each one costs in money and evenings, and the honest version of what running a model on your own machine does and does not buy you. (2026-09-15)
- [Amazon settles what TikTok starts. An assistant that reorganizes the catalog does not change that](https://4gpts.com/en/resources/amazon-settles-what-tiktok-starts-an-assistant-that-reorganizes-the-catalog-does-not-change-that): Agentic commerce 2026, read off two seller lists: only 498 of the 10,000 largest sellers on Amazon and on TikTok Shop sell in both top lists. TikTok makes people want things, Amazon is where they buy them, and a catalog assistant does not move the want. The shopper's own agent does. (2026-09-14)
- [Instacart's agentic commerce strategy: you do not have to own the agent to win](https://4gpts.com/en/resources/instacart-s-agentic-commerce-strategy-you-do-not-have-to-own-the-agent-to-win): Instacart's agentic commerce strategy sells through four assistants it does not own, then hedges with one of its own. The lesson for any shop: you can win and get paid without owning the agent, so make your shelf readable by every agent before you build a chat window. (2026-09-13)
- [Meta's Muse is an AI agent shopping for you. Ask who it belongs to.](https://4gpts.com/en/resources/meta-s-muse-is-an-ai-agent-shopping-for-you-ask-who-it-belongs-to): AI agent shopping arrived with reach: Meta's Muse browses stores in its own browser, narrows to product cards and pays with a one-time card from Link by Stripe. Every part of it lives on a computer Meta runs, under Meta's policies. A personal AI is personal only if you own it. (2026-09-11)
- [Nobody feels AI in daily life yet. It gets felt the day the agent is yours.](https://4gpts.com/en/resources/nobody-feels-ai-in-daily-life-yet-it-gets-felt-the-day-the-agent-is-yours): Half of U.S. adults use no AI chatbot at all, and the top use is search. A self hosted AI assistant that keeps your memory and your logins on hardware you own is what gets felt, the way the sewing machine, the bicycle and the personal computer were. (2026-09-11)
- [AI referral traffic is spreading across four assistants. Ask what all four can read.](https://4gpts.com/en/resources/ai-referral-traffic-is-spreading-across-four-assistants-ask-what-all-four-can-read): The sharpest agentic commerce 2026 count so far: ChatGPT lost the No. 1 AI traffic position at a net 122 of the 1,000 largest US retailers in one quarter, and the gains split three ways. No retailer chose that. What all four assistants read is the catalog. (2026-09-09)
- [An agent that cannot walk away is not representing you](https://4gpts.com/en/resources/an-agent-that-cannot-walk-away-is-not-representing-you): In agent to agent negotiation the walk-away is the feature, not a failure. Sellers wanted over twice what buyers offered for the same mug (Kahneman, Knetsch and Thaler, 1990), and under time pressure 72.9% of deals land in the last tenth of the clock. Those are the reasons a person cannot leave. An agent has none of them. (2026-09-09)
- [How to tell a plugin will fight your agent, before you install it](https://4gpts.com/en/resources/how-to-tell-a-plugin-will-fight-your-agent-before-you-install-it): Is this plugin safe to install on my agent? Too many tools, two names that overlap, a disclosure you cannot check, a version that is not the one described, a delete that reads like a read: all of it is readable before you install, in about ten minutes, with nothing run. (2026-09-09)
- [The harness just became a product. Ask who owns the computer your personal AI runs on.](https://4gpts.com/en/resources/the-harness-just-became-a-product-ask-who-owns-the-computer-your-personal-ai-runs-on): Personal AI hardware became a sign-in this week: Grok Bot supplies and runs the computer, and OpenClaw 2.0 starts from what is already on yours. The setup gap closed from both sides. The open question is who owns the computer, and everything on it. (2026-09-09)
- [Claude for Commerce gives every retailer a shopper agent. Ask whose shopper it serves.](https://4gpts.com/en/resources/claude-for-commerce-gives-every-retailer-a-shopper-agent-ask-whose-shopper-it-serves): AI agent shopping got a free blueprint: a shopping agent the retailer hosts on its own site. The first line of its prompt names the brand, not the shopper. Read the code before calling it the shopper's agent. (2026-09-07)
- [Why do sizes differ between brands, and what should you measure instead?](https://4gpts.com/en/resources/why-do-sizes-differ-between-brands-and-what-should-you-measure-instead): Brand sizing explained: a size label names a last or a garment, not you, and every maker compresses differently. The same US 9.5 foot is a 26.5 or a 27.5 boot across three brand charts, and the same 112 cm chest is an L or an XL across five. Here is what to measure so your numbers survive crossing brands. (2026-09-07)
- [The AI assistant grew revenue 620 percent. Ask what it grew from.](https://4gpts.com/en/resources/the-ai-assistant-grew-revenue-620-percent-ask-what-it-grew-from): One of the clearest agentic commerce 2026 datapoints came with no denominator. Williams-Sonoma disclosed a base for every number in its Q2 except the one it led with. (2026-09-04)
- [Nothing closes without you: the human gate in agent-to-agent negotiation](https://4gpts.com/en/resources/nothing-closes-without-you-the-human-gate-in-agent-to-agent-negotiation): Only 11% of consumers will let AI make a purchase decision, and the most common amount people will let it spend on its own is $0. They are right. Negotiating and committing were always two different jobs, and only one of them belongs to a machine. (2026-09-01)
- [What mondopoint sizing is, and how to find your number](https://4gpts.com/en/resources/what-mondopoint-sizing-is-and-how-to-find-your-number): Mondopoint is the length of your foot in millimetres, not a code for a shoe. ISO 9407:2019 defines it on the foot, standing, weight even. Here is how to measure yours, why half-size shells do not exist, and why the right number still does not settle the fit. (2026-09-01)
- [Choosing an agent host: a fitting guide for your personal AI stack](https://4gpts.com/en/resources/choosing-an-agent-host-a-fitting-guide-for-your-personal-ai-stack): We read what people actually say when they set up or switch a personal AI stack. Almost nobody asks which host has more features. They ask how much of a weekend it costs, whose computer it runs on, and whether their setup survives leaving. Here is how to answer those three about yourself, then pick. (2026-08-30)
- [Compute is centralizing. Your personal AI never needed it.](https://4gpts.com/en/resources/compute-is-centralizing-your-personal-ai-never-needed-it): Two labs are on track to hold most of the world's usable compute by 2028. That race is a race to train the best model. Your agent does not train anything, and the cost of running what it does need keeps falling. (2026-08-30)
- [The Q2 AI1000 moved 972 of 1,000 retailers. Read the count, not the ranking.](https://4gpts.com/en/resources/the-q2-ai1000-moved-972-of-1-000-retailers-read-the-count-not-the-ranking): The Q2 AI1000 says 972 of 1,000 retailers changed rank and 225 are agent-ready. The churn is noise. The count is real, and the same newsletter quietly explains why most of those endpoints were never a retailer decision at all. (2026-08-30)
- [Chest circumference: how to measure yours, and what the number leaves out](https://4gpts.com/en/resources/chest-circumference-how-to-measure-yours-and-what-the-number-leaves-out): How to measure your chest for a jacket, and why one number is not enough. ISO 8559-1:2017 lists five separate girths through the chest, and a size chart may be quoting the garment rather than your body. (2026-08-25)
- [What your plugins cost your agent context window, and how to trim it](https://4gpts.com/en/resources/what-your-plugins-cost-your-agent-context-window-and-how-to-trim-it): Everyone says trim your tool descriptions. We measured our own two plugins: 47 tools, 13,232 tokens loaded before you type a word, and 78% of one plugin's cost is parameter schema, not description. Here is the audit and the two changes that took 14.2% back. (2026-08-25)
- [Why negotiation is the right job to hand a machine](https://4gpts.com/en/resources/why-negotiation-is-the-right-job-to-hand-a-machine): Agents that negotiate are not a claim about software. In price negotiations between experienced managers, over half the variance in the final outcome was explained by who made the first offer. Here is the evidence on what being a person costs you at the moment the price is set. (2026-08-25)
- [What instep height is, and how to measure yours](https://4gpts.com/en/resources/what-instep-height-is-and-how-to-measure-yours): Instep height is the third boot-fit dimension, after length and width, and it is the one that explains pressure across the top of your foot. It is a girth, not a height, you can measure it with a piece of string, and there is a ratio that turns the number into a decision. (2026-08-21)
- [Why your agent picks the wrong tool, and how to fix it in your plugin](https://4gpts.com/en/resources/why-your-agent-picks-the-wrong-tool-and-how-to-fix-it-in-your-plugin): Your agent never sees your code. It chooses between tool descriptions, which makes a tool surface a piece of writing. Here are three ways ours was written badly, what we changed, and the audit you can run on what you already have installed. (2026-08-21)
- [Your personal AI stack, from zero: what to install and in what order](https://4gpts.com/en/resources/your-personal-ai-stack-from-zero-what-to-install-and-in-what-order): A personal AI setup guide that starts with the mental model: the five parts of a personal AI stack (host, model, plugins, skills, memory), what each one is for, and the order to install them in. (2026-08-13)
- [What agent to agent commerce actually means](https://4gpts.com/en/resources/what-agent-to-agent-commerce-actually-means): A benchmark of agent to agent negotiation calls automated deal making an inherently imbalanced game, and finds buyer agents spending past the budget they were given. That is not an argument against the category. It is the specification for it. (2026-08-11)
- [What does ski boot flex 130 mean, and how to find your number](https://4gpts.com/en/resources/what-does-ski-boot-flex-130-mean-and-how-to-find-your-number): Flex is the number every ski boot is sold on, and nobody measures it. There is no standard, one brand ships about five different 130s in a season, and the same boot swings roughly 20 flex points between a cold morning and spring corn. (2026-08-11)
- [What an AI agent reasons about when it buys ski boots: a worked run](https://4gpts.com/en/resources/what-an-ai-agent-reasons-about-when-it-buys-ski-boots-a-worked-run): A real example of an AI agent doing a task: my own run of SIL on OpenClaw, shopping for ski boots. The agent refused the boot every list recommends, on arithmetic, and this is the full reasoning, the runner-up, and what it cost me in attention. (2026-08-06)
- [Machine legibility now has a price tag: agents buy what they can read](https://4gpts.com/en/resources/machine-legibility-now-has-a-price-tag-agents-buy-what-they-can-read): Shopify says 71% of AI-attributed orders came from the long tail and fresh catalog data converts 2x. Adobe measured AI-referred retail traffic flipping to convert 42% better than other channels. Salesforce put agents behind 20% of holiday sales. Three competing vendors, one priced conclusion: agents buy what they can read. (2026-08-05)
- [The grind is the product: why the thing you'd sell stays in the drawer](https://4gpts.com/en/resources/the-grind-is-the-product-why-the-thing-you-d-sell-stays-in-the-drawer): Selling used hardware is a grind by design: the listing, the lowballers, the 40 messages. The data says the barrier was never price. It is attention, and that is the one cost an agent deletes. (2026-08-05)
- [Agent to agent: why symmetry is the whole category](https://4gpts.com/en/resources/agent-to-agent-why-symmetry-is-the-whole-category): Agent to agent commerce is not a bot picking off humans. Give one side an agent and the other a text box and you have armed a negotiation, not built a marketplace. Symmetry is what makes it a market. (2026-08-04)
- [What is last width in ski boots, and how to measure yours](https://4gpts.com/en/resources/what-is-last-width-in-ski-boots-and-how-to-measure-yours): Last width is the shell's internal forefoot width, but the published number is only true at one shell size. It moves about 2mm per size, so a 100mm last is nearer 96mm in a 24.5 and 106mm in a 29.5. (2026-08-04)
- [The state of agentic commerce in mid-2026: 38% discover, 17% buy](https://4gpts.com/en/resources/the-state-of-agentic-commerce-in-mid-2026-38-discover-17-buy): Forrester's mid-2026 read on the state of agentic commerce finds 38% of consumers use answer engines to discover products but only 17% buy through them. The gap is trust and machine legibility, and it decides which brands agents select. (2026-07-15)

## Optional
- [Full text](https://4gpts.com/llms-full.txt): every page above as one markdown document.
- [About](https://4gpts.com/en/about): who builds 4GPTs.