Let Agents In

Agent readiness · sinch.com

2026-08-12 10:33 UTC · formula v9.2 · 10.8s

You publish files for machines to read, but nothing that tells one how to become a customer.

None of the nine known agent entry paths answered, including /agent-signup.md and /.well-known/agent-access.json. Reading is solved on your site; joining is not.

9/ 13
A · Discovery
5/5
B · Agent entry
1/2
C · Registration
0/1
D · Provisioning
1/3
E · Integration
2/2

of the 13 points that apply to you and we could measure · 4 of 17 were not scored

You 9 · category median 11 · best telnyx.com 14 · 15 deterministic HTTP checks, published formula

Pass it onEmail itLinkedIn

Fix this first

+2points, taking 9/13 to 11/13, past plivo.com

This is the whole list: everything we could measure and you do not pass. Another 4 points sit behind checks we could not evaluate on your domain, and each of those lines below says what would make it measurable.

  1. 1
    Free tier or no-card trial stated in textminutes · +1

    Every mention of free on your pricing page sits inside a button. An agent reads text, not chrome, so state the tier in a sentence or a price cell: what is free, what it is limited to, and whether a card is needed.

  2. 2
    Programmatic key provisioningan afternoon · +1

    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

  • MCP surface a project · +1Wrap your top three API calls in an MCP server and declare it at /.well-known/mcp.json.
  • Signup reachable without a browser a project · +1Let https://dashboard.sinch.com/signup render its form in server HTML and stop refusing non-browser requests to it.

Take it with you

5 of the checks an agent depends on, sinch.com 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 sinch.com. 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 fullWhat the same run on sinch.com costs

Against sms, voice and messaging

You are 4 of 6 in a category where a developer is trying to send a message a person actually reads.

  1. 1
    telnyx.com
    14/17
  2. 2
    bird.com
    13/16
  3. 3
    twilio.com
    12/16
  4. 4
    sinch.comyou
    9/13
  5. 5
    plivo.com
    10/15
  6. 6
    vonage.com
    4/8

Where competitors pass and sinch.com does not

  • Free tier or no-card trial stated in texttwilio.com · plivo.com · bird.com
  • Paths robots.txt points at answertwilio.com · telnyx.com
  • MCP surfacetelnyx.com · bird.com
  • Programmatic key provisioningtwilio.com · telnyx.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

A
DiscoveryCan an agent find and read you?
5/5
B
Agent entryIs there a door built for a machine?
1/2
C
RegistrationCan an agent get an account?
0/1
D
ProvisioningCan it get credentials without a human?
1/3
E
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://docs.sinch.com/llms.txt and https://developers.sinch.com/llms.txt, and the 12 links we sampled across the file all answer
  • PASS
    Docs readable without JavaScript2,689 characters of text without JS, on https://developers.sinch.com/docs/errors/registry/invalid-credentials rather than on https://developers.sinch.com
  • 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

  • UNMEASURED
    Agent entry pointUnmeasurable: 8 of the 9 known agent entry paths answered with a refusal rather than a file or a 404, so what you publish there is not something we measuredLet ordinary HTTP reach these paths and this becomes measurable.
  • PASS
    OAuth dynamic client registrationregistration_endpoint published, and client_credentials is among the 13 advertised grants, so an unattended agent has a documented path to a token
  • FAIL
    MCP surfaceNo MCP surface: nothing answered at mcp.sinch.com, mcp.sinch.com/mcp, mcp.sinch.com/v1/mcp, api.sinch.com/mcp, /mcp or /api/mcp, and no file mentions MCPAn MCP server turns your API from something an agent reads about into something it can call.

C · Registration

  • UNMEASURED
    No CAPTCHA in the signup HTMLUnmeasurable: the signup form at https://dashboard.sinch.com/signup is not in the server HTML, so its gates are not eitherServer-render the form, or tell us the endpoint it posts to, and the gates become visible to us and to an agent.
  • FAIL
    Signup reachable without a browserhttps://dashboard.sinch.com/signup is reachable, but its form needs JavaScriptIf a bare HTTP request gets a 403, the agent never sees the form at all.

D · Provisioning

  • PART
    Programmatic key provisioning1 of 7 provisioning phrases across the 6 documents we read: "provisioning api"Documented key creation is the difference between a two-minute integration and a support ticket.
  • FAIL
    Free tier or no-card trial stated in texthttps://sinch.com/pricing/ carries a "start for free" style link and nothing else about a free tier, so what we found is a button rather than a stated priceA free tier is what lets an agent finish the job in the same session it started. Usage-priced products with self-serve signup can fail this honestly, which is why it is one point and not a verdict.

E · Integration

  • PASS
    Typed SDK on the registry@sinch/sdk-core@1.5.0 ships types, matched from the registry by who publishes it rather than by a link on your site
  • PASS
    Machine-readable API descriptionDocs serve markdown to machines, at https://developers.sinch.com/docs/est/api-reference/est/credentials.md

What we discovered on the way

Docs
https://developers.sinch.com · found on a subdomain
Pricing
https://sinch.com/pricing/ · linked from the site
Signup
https://dashboard.sinch.com/signup · linked from the site
npm package
@sinch/sdk-core (registry guess)
GitHub
not found
Package licence
Apache-2.0
Crawl-delay
none
Content-Signal
none
Blocked on-demand agents
none