Nowhere in your documentation does an agent learn how to get a key without a human.

No management API, service account or programmatic key creation is described in the pages we read.

13/ 16

A · Discovery: 5/5
B · Agent entry: 3/4
C · Registration: 2/2
D · Provisioning: 1/3
E · Integration: 2/2

of the 16 points that apply to you and we could measure · 1 of 17 were not scored

You 13 · category median 11.5 · best resend.com 14 · 15 deterministic HTTP checks, published formula

Pass it onEmail it LinkedIn

Fix this first

+2points, taking 13/16 to 15/16, past resend.com

This is the whole list: everything we could measure and you do not pass. Another 1 point sits behind checks we could not evaluate on your domain, and each of those lines below says what would make it measurable.

1
Programmatic key provisioningan afternoon · +2
Document how a key is created without opening a dashboard: management API, service account or CLI. If no such path exists, that gap is the finding, not the docs.

Then, when you have room

OAuth dynamic client registration a project · +1Your OAuth metadata is already published and has no registration_endpoint in it. Adding that one field is the whole change: RFC 7591 is the only standard way an agent registers itself without a human.

Take it with you

3 of the checks an agent depends on, loops.so does not pass.

Send yourself the list above with the checks that cost the most, and a permanent link. Whoever owns the fix is usually not the person who ran the scan.

One email with the report, and one follow-up asking what you did with it. No newsletter, no sequence. Delete on request at hello@letagentsin.com.

None of this tells you whether an agent picked you

Everything above is a file an agent could read. Whether one actually chose you is a different measurement, and we have not run it on loops.so. What we have run it on is a rich text editor vendor: six agents, one brief, six isolated copies of a real codebase. All six picked the same competitor, and the vendor being studied was never named, not even on a rejection list, while the runs named and dismissed ten alternatives between them. In an earlier round, run before we isolated the copies, it was named twice and struck off both times in four words: Fully commercial, licence key required. That study is about them, not about you. It is here because it is the difference between a file and a decision.

Read the audits in full What the same run on loops.so costs

Against transactional email apis

You are 2 of 6 in a category where a developer is trying to send password resets and receipts that arrive.

1
resend.com
14/16
2
loops.soyou
13/16
3
postmarkapp.com
11/14
4
sendlayer.com
12/16
5
mailgun.com
9/14
6
sendgrid.com
9/14

Where competitors pass and loops.so does not

OAuth dynamic client registrationresend.com
Programmatic key provisioningpostmarkapp.com

Only domains we have actually scanned appear here, so the ranking is a floor: a competitor missing from the list has not been measured, not beaten.

By stage

DiscoveryCan an agent find and read you?

5/5

Agent entryIs there a door built for a machine?

3/4

RegistrationCan an agent get an account?

2/2

ProvisioningCan it get credentials without a human?

1/3

IntegrationCan it ship working code?

2/2

Every check

Each line is one HTTP observation with a published rule, so you can rerun any of them yourself. Most are the same tomorrow if you are: the two that are not are the bot gate and the pricing page, which answer inconsistently on their own, which is why those run more than once and say so when the tries disagreed. PASS and PART are counted. UNMEASURED means we could not evaluate it, N/A means it does not apply to a product like yours, and neither is in the score or its denominator. See the formula

A · Discovery

PASS
Answers an agent user-agentAnswered 200 to LetAgentsIn/1.0 (+https://letagentsin.com/methodology)
PASS
llms.txt publishedllms.txt present at https://loops.so/llms.txt, and the 12 links we sampled across the file all answer
PASS
Docs readable without JavaScript9,205 characters of text without JS
PASS
On-demand agents not blockedNo on-demand agent is blocked
N/A
Paths robots.txt points at answerrobots.txt names no concrete path, only patterns or nothing, so there is no claim to check
PASS
No punishing crawl delayNo Crawl-delay applies to the agents we check

B · Agent entry

PASS
Agent entry pointFound: https://loops.so/skill.md, https://loops.so/agents.md
FAIL
OAuth dynamic client registrationOAuth metadata published, but no registration_endpoint in itRFC 7591 is the only standard path by which an agent can register itself without a human.
PASS
MCP surfaceLive MCP endpoint at https://mcp.loops.so/mcp, answered 401 with an auth challenge

C · Registration

PASS
No CAPTCHA in the signup HTMLNo CAPTCHA vendor in the server HTML. A widget mounted later by JavaScript would not show here.
PASS
Signup reachable without a browserForm renders in server HTML at https://app.loops.so/register

D · Provisioning

FAIL
Programmatic key provisioningNone of the 7 provisioning phrases appears in the 5 documents we readDocumented key creation is the difference between a two-minute integration and a support ticket.
PASS
Free tier or no-card trial stated in textFree tier or no-card signals at https://loops.so/pricing: "no credit card", "Free Plan", "free to start"

E · Integration

PASS
Typed SDK on the registryloops@7.2.0 ships types
PASS
Machine-readable API descriptionDocs serve markdown to machines, at https://loops.so/docs/api-reference/intro

What we discovered on the way

Docs: https://loops.so/docs/api-reference/intro · linked from the site
Pricing: https://loops.so/pricing · from your llms.txt
Signup: https://app.loops.so/register · linked from the site
npm package: loops
GitHub: plutolinks/loops-php
Package licence: MIT
Crawl-delay: none
Content-Signal: none
Blocked on-demand agents: none