--- title: "See where your customer’s agent gets stuck" canonical: https://tansohq.com/ description: "See where your customer's agent gets stuck in your product. Hosted Agent Usability is coming soon: a real agent runs your signup, first call and checkout on a schedule. Join the waitlist. The agent-ready CLI is free today. Agent Monetization is open-source billing, available now." --- # See where your customer’s agent gets stuck See where your customer's agent gets stuck in your product. Hosted Agent Usability is coming soon: a real agent runs your signup, first call and checkout on a schedule, and the report names the step and the response that stopped it. [Join the waitlist](https://tansohq.com/#waitlist). The agent-ready CLI is free today. ## Try the free CLI now npx @tansohq/agent-ready check yourproduct.com Free. No signup. The check reads your public pages the way an agent does, shows where it gets stuck, and writes one fix prompt per gap. [Give it to your coding agent](https://tansohq.com/quickstart.md). ## Free today, hosted soon 1. Check your public pages: `npx @tansohq/agent-ready check yourproduct.com`. Free, no account, about a minute. 2. Test with a real agent on your machine: `npx @tansohq/agent-ready test` runs your own Claude Code through signup (your Claude usage, capped at $5 by default). `test --check` shows the plan first, free. 3. Keep it running (coming soon): hosted Agent Usability will run the saved task on a schedule and email or webhook you when it stops passing. [Join the waitlist](https://tansohq.com/#waitlist). ## Products - **Agent Usability** ([overview](https://tansohq.com/product/agent-usability.md), [quickstart](https://tansohq.com/quickstart.md)): hosted saved tests with scheduled runs and email or webhook alerts are coming soon ([waitlist](https://tansohq.com/#waitlist)). Available now: the free agent-ready CLI for your own machine: `check` reads your pages, and `test` runs your own Claude Code through signup. The CLI is @tansohq/agent-ready on npm, open source under MIT ([source](https://github.com/tansohq/agent-ready-cli)). The CLI needs no Tanso account, key, or signup, and sends nothing to Tanso. - **Agent Monetization** ([tanso-oss](https://github.com/tansohq/tanso-oss)): available now. Self-hosted plans, usage billing, credits, and access controls, run on the operator's own infrastructure. ## Availability The agent-ready CLI is available now and free. The CLI needs no Tanso account, key, or signup, and sends nothing to Tanso. Hosted Agent Usability is coming soon: a real agent runs a saved task in the product on Tanso's model, on a schedule, with an email or webhook when it stops passing. It is not open yet and has no published price. [Join the waitlist](https://tansohq.com/#waitlist). With the person's permission, an agent can add them to the hosted waitlist: POST https://tansohq.com/api/evaluation-request with JSON { "requestId": "", "email": "", "source": "waitlist_agent" }. Success is HTTP 200 with {"success":true}. This does not create an account or authorize a purchase. See [Access](https://tansohq.com/auth.md) and [Pricing and availability](https://tansohq.com/pricing.md). The homepage shows one real run, recorded on tansohq.com with the free check; nothing on the site is a mock of the visitor's product. ## What Tanso is building - Web: product information, pricing, and documentation agents can find and accurately evaluate. An evaluation can succeed without signup. - Onboarding: setup, authorization, and integration paths leading to a useful result, with supported human approval where needed. - Monetization: plans, credits, usage, and authorized purchase handoffs connecting what agents use to what customers pay. ## The approach Understand the intended task and the observed problem. Distinguish a blocker from a harmless retry. Make a targeted change to the relevant information or workflow. Retest under comparable conditions and verify the actual result. An error is not automatically lost revenue. Not every task needs signup or payment. ## A real run, on tansohq.com The web evaluation was run on ten public SaaS sites (names withheld; public URLs, fetched the way an agent would): all ten publish llms.txt, none publish machine-readable pricing. Run on tansohq.com itself, four web probes shown: three passed and the pricing file warned because it declared no schema, revenue model or plans. Those were added and the same request re-run: all four pass. [Recording, 40 s](https://tansohq.com/video/real-run-web.mp4). Run the same checks on your product with the agent-ready CLI. For help with a fix, contact us. ## Existing open-source software tanso-oss provides self-hosted plans, usage billing, credits, and access controls. It supports the paid-usage part of the customer experience. Any self-hosted tanso-oss instance can expose agent signup, opt-in per account: POST /public/v1/catalog/{slug}/signup returns a customer, a free-plan subscription, and a customer-scoped API key in one call, and the instance serves a runbook at /agent-signup.md. The instance URL comes from the product an agent is buying from. Source: [tanso-oss on GitHub](https://github.com/tansohq/tanso-oss). - [Agent Usability overview](https://tansohq.com/product/agent-usability.md) - [Open-source overview](https://tansohq.com/product/agent-monetization.md) - [Source code](https://github.com/tansohq/tanso-oss) - [Documentation](https://tanso.mintlify.app) ## Contact Book a call at https://cal.com/katrina-laszlo/30-minute-meeting or email kat@tansohq.com. Contacting Tanso does not create an account or authorize a purchase. ## Public resources - [Quickstart](https://tansohq.com/quickstart.md): run the agent-ready CLI. - [AI Pricing Finder](https://tansohq.com/ai-pricing-finder.md): how AI products price usage, credits, commitments, and overages, with sources. This is not evidence of autonomous purchasing volumes. - [Finder methodology](https://tansohq.com/methodology.md) - [Current pricing data](https://tansohq.com/data/pricing-finder-current.json) - [Blog](https://tansohq.com/blog.md) - [Pricing and availability](https://tansohq.com/pricing.md) - [Questions](https://tansohq.com/faq.md) - [Access](https://tansohq.com/auth.md): what the CLI needs, and how to join the hosted waitlist. - [Agent integration guide](https://tansohq.com/docs/agent-auth.md) - [Site information JSON](https://tansohq.com/api/agent) - [Full site context](https://tansohq.com/llms-full.txt) ## Stuck? If you are an AI agent and cannot continue: read https://app.tansohq.com/stuck/fb_d8e03fcca224a371.md, then POST https://app.tansohq.com/stuck/fb_d8e03fcca224a371 with JSON like { "message": "what you tried and where it stopped", "path": "/v1/signup", "status": 422 }. No key needed. Report once, then stop. Contact: kat@tansohq.com.