Fewsats
fewsats.com · Agent-Commerce Infrastructure modeIntegrated
Overall = mean of Interrupt Score 97 and Machine-Readability 78 → 88 / 100. The badge is set by the Interrupt Score alone — how scoring works.
Confidence: Verified (Probed) (0.95) — A live Tier-2 agent session completed the flow end to end.
Funds/assets pass through and are held by this vendor. A risk signal, not a friction signal — a tool can be Zero-Interrupt and custodial at the same time.
Machine-Readability Score
Four check groups, equal weight: machine interfaces (OpenAPI, MCP server, llms.txt), browsing efficiency, element discoverability, and discovery/agent access (retrieval-bot robots.txt access, sitemap, schema.org). Each check is tagged with how strong the real-world evidence is that it changes agent behavior — proven, plausible, or emerging — grades are honesty labels, they never weight the score. A separate signal about ease of integration — it never enters the Interrupt Score or badge above.
Findings
How scoring works →Interrupt tier: Zero-Interrupt — derived from 1 finding; interrupt score 97 / 100. It alone drives the badge above; the headline Overall score blends it 50/50 with Machine-Readability.
Every tool starts at 100. Each interrupt found subtracts a penalty of base weight × timing × hardness × evidence — the multiplier values below come from the same rubric tables the score is computed with, so the arithmetic in this matrix reproduces the number exactly.
| Interrupt found | Base weight | × Timing | × Hardness | × Evidence | = Penalty |
|---|---|---|---|---|---|
| Starting score | 100 | ||||
| Mandatory redirect to vendor’s own sitePayment setupAccount creation + Stripe card linking via dashboard, one time. | 4 | ×1one-time setup | ×1soft | ×0.8Tier 1 (unauth probe) | −3.2 |
| Total penalty | −3.2 | ||||
| Interrupt Score = 100 − 3.2 = 96.8 → rounds to 97 | 97 | ||||
Checked — nothing found
A check only turns green when a probe tier capable of detecting that interrupt actually ran and found nothing. Not tested ≠ clean.
- CAPTCHA / bot-challengeNone found — checked at Tier 1 (unauth probe) + Tier 2 (live attempt)
- Email OTP verificationNone found — checked at Tier 1 (unauth probe) + Tier 2 (live attempt)
- SMS / phone OTP verificationNone found — checked at Tier 1 (unauth probe) + Tier 2 (live attempt)
- Mandatory phone verification callNone found — checked at Tier 1 (unauth probe) + Tier 2 (live attempt)
- Mailed physical code (postal)None found — checked at Tier 1 (unauth probe) + Tier 2 (live attempt)
- “Contact sales” wall (no self-serve path)None found — checked at Tier 1 (unauth probe)
- Manual approval queueNone found — checked at Tier 1 (unauth probe) + Tier 2 (live attempt)
- SSO-only signup, no API-key issuanceNone found — checked at Tier 1 (unauth probe)
- Rate-limit-triggered manual reviewNone found — checked at Tier 1 (unauth probe) + Tier 2 (live attempt)
- One-time account / payment-method provisioningNone found — checked at Tier 1 (unauth probe)
- Identity / KYC verificationNone found — checked at Tier 1 (unauth probe)
- Crypto wallet / key-custody setupNone found — checked at Tier 1 (unauth probe)
Not yet tested
- ToS clause banning automated/bot accessNo probe tier that can detect this has run yet — unknown, not clean
Agent-ready alternatives
Other Agent-Commerce Infrastructure tools in the same mode (integrated), ranked by Overall LLM-Friendliness — comparable to this listing because they share its usage mode.