# Can an AI agent use Calendesk? L3 · Does the work

**L3 · Does the work** · [What the levels mean](https://agentdrives.com/method/levels?via=md)

Rank among the 246 products we drove:

- Holds up: 81 / 100, #44 (Reliability under errors)
- Time to get in: 5 minutes, tied #61 (Getting in on its own)
- Core work done: 67%, tied #80 (6 of 9 core tasks)
- Steps on its own: 2 / 5, tied #86 (Find to Leave, no person)

**Can an AI agent use Calendesk? Yes.** Our agent signed up for Calendesk on its own in a browser and used its API and MCP server. No CLI found.

- Level confirmed: Not yet (Level from one drive; a second must agree)
- Got in by: MCP sign-in (5 minutes, in a browser)
- Got as far as: Use: 6 of 9 core tasks (A person has to buy)

Category: Scheduling · Connects by: MCP, API · Agent payments: None found · Driven: 10 Nov 2026

**How to connect**
- MCP server URL: `https://mcp.calendesk.com/` (streamable HTTP, documented). Source: https://mcp.calendesk.com/

Checked 17 Nov 2026: MCP server asks for a sign-in; llms.txt and OpenAPI unchanged since the check before.

See [how it ranks among scheduling APIs for agents](https://agentdrives.com/research/best-scheduling-apis-for-ai-agents?via=md).

## From finding it to leaving

What an agent managed without a person, at each step.

1. **Find**: On its own. Docs it can act on: llms.txt, an OpenAPI and an MCP server. (47 doc pages read)
2. **Get in**: On its own. No key needed, MCP sign-in. (5 minutes)
3. **Use**: Partly. Did: connect the official MCP server over OAuth with no human help beyond clicking Allow in its own browser; list services, employees, availability and open time slots. 3 not done, among them: take an online payment for a booking. (6 of 9 core tasks)
4. **Pay**: Stopped. Needs a person to buy. The key request is refused: API access needs a paid Pro plan with the API package. First stop.
5. **Leave**: Partly. Nothing to cancel. Its account stays.

To reach L4: Do 80% of the core work (now 67%) and delete its account, so its keys and login stop working.

## How an agent connects

MCP, API, OpenAPI and llms.txt found.

- **MCP server**: 34 of 35 tested. Official server. Sign-in needed to see its tools. https://mcp.calendesk.com/ (35 tools mapped in our drive)
- **API**: 101 of 301 tested. (301 operations mapped in our drive)
- **OpenAPI**: Yes. A machine-readable description of the API.
- **CLI**: None found.
- **SDK**: None found.
- **llms.txt**: Yes. https://calendesk.com/llms.txt
- **Agent payments**: None found. The checkout wasn't reached. Plan and price: Standard, €89 a month.
- **Docs**: Some gaps. Covers getting started and auth. Code examples on only some pages. No error codes. Describes each operation only in part: completeness 86 of 100. 7 of 15 documented ways to do the core work were tried, and 7 of them worked. (47 of 49 pages read)

**Changed since it was driven** (checked daily)
- OpenAPI: 1 endpoint added, 15 Nov

[The standards](https://agentdrives.com/standard)

## Getting in

Our agent tried 3 of 4 ways in; 2 worked without a person.

The way that worked: **MCP sign-in**, 5 minutes. Needs an inbox and a browser. No person needed.

- Agent on a server (API, MCP, CLI): Partly. Gets in without a browser (no key needed) and does 0 of its 9 core tasks that way. For a full account, it stops at sign-up: it works only in a browser.
- Assistant in its own browser (Like ChatGPT agent): Partly. Signs up, confirms its email and does 6 of its 9 core tasks, then stops: the rest needs a paid plan. It can't delete its account.
- Signed agent: Yes. Our signed agent got through Google reCAPTCHA at sign-up.

| Way in | What happened |
|---|---|
| MCP sign-in | Worked |
| No key needed | Worked: Part of the work done |
| Registration through auth.md | Stopped |
| Try first, claim later | Not tried |

- Crawlers: **The robots.txt on admin.calendesk.com asks crawlers to stay off sign-up.** Nothing to fix.
- Bot check: **Google reCAPTCHA let our agent through at sign-up.** Our agent signs every request (Web Bot Auth).

## What an agent can do with Calendesk

6 of 9 core tasks done, and 4 of 14 others.

- Holds up: 81 of 100 (Reliability 100, Handles mistakes 62). The mean of the two.
- Docs match: 89 of 100 (Docs accuracy 90, Docs completeness 86). Docs accuracy counts 70%, completeness 30%.
- Surface tested: 40 of 100. 135 of 338 passed: the 339 documented operations less the 1 that spends money or reaches real people

Core tasks:

| Task | Result | Done through | Tried, not done | Offered, not tried |
|---|---|---|---|---|
| List open time slots for a service | Done | API, MCP | – | – |
| Book an appointment | Done | API, MCP | – | – |
| Reschedule a booking | Done | API, MCP | – | – |
| Cancel a booking | Done | API, MCP | – | – |
| List bookings | Done | MCP | – | API |
| Add a client | Done | MCP | – | API |
| Create a bookable service | Paid plan, not counted | – | API | – |
| Set working hours and availability | Paid plan | – | API | – |
| Take online payment for a booking | Paid plan: It needs Stripe identity and bank verification that our agent couldn't truthfully complete. | – | API | – |
| Publish a booking website with the website builder | Blocked: The builder only exists in the panel, behind the phone-number screen. | – | Web app | – |

4 of 14 other tasks done:

- Offer a group class with several seats: Done
- Block time off for an employee: Done
- Read revenue and booking reports: Done
- Make a recurring booking: Done
- Set up booking reminders: Paid plan
- Sell a pass or subscription to clients: Paid plan
- Add an employee with a calendar: Paid plan
- Edit notification templates: Paid plan
- Merge duplicate clients: Paid plan
- Sell a product in the online store: Paid plan
- Register a webhook: Paid plan
- Export bookings to a file: Paid plan
- Import clients from a file: Paid plan
- Add a newsletter subscriber: Paid plan
- Set an employee's role or permissions: Paid plan
- Connect a custom booking domain: Paid plan
- Read the audit log: Paid plan
- Change business settings: Paid plan
- Generate a privacy policy and terms: Paid plan
- Sync with Google Calendar or Outlook: Blocked
- Add a Zoom, Google Meet or Teams link to bookings: Blocked
- Add custom fields to the booking form: Blocked
- Embed the booking widget on a website: Blocked
- Send a client an email notification: Blocked
- Tag a client: Blocked
- Add Google Analytics or tracking scripts: Blocked
- Connect InvoiceOcean to issue invoices automatically: Blocked
- Set the panel brand logo and colours: Blocked
- Turn on the cookie consent banner: Blocked
- Work from the employee mobile app: Blocked

The plans they need:

- credentials: Pro + API access package
- List open time slots for a service
- Book an appointment
- Reschedule a booking
- Cancel a booking
- List bookings
- Add a client
- Send a client an email notification: paid

The drive used the no-card trial (Standard, 14-day, auto-expires 24 Nov 2026).

What it can't do, and why:

- Get the documented admin API key on the free trial: The key request is refused: API access needs a paid Pro plan with the API package.
- Use the panel screens, buy a plan or delete the account: A required phone number in the onboarding wizard covers every panel page.
- Take an online payment for a booking: It needs Stripe identity and bank verification that our agent couldn't truthfully complete.
- Publish a website with the builder: The builder only exists in the panel, behind the phone-number screen.
- Revoke the MCP access token: No revocation endpoint exists and the connected-apps page is behind the phone screen.

**Surface audit:** 339 documented operations: 135 run, 20 blocked by sandbox or plan limits, 1 left out because it spends money or reaches real people and 183 not reached in the drive's time. Of the 135 run, 135 passed; 14 behaved differently from the docs. By surface, 101 on the API and 34 on the MCP server.

## Tips for agent builders

- Connect the MCP server first (mcp.calendesk.com): it is the most agent-native surface and gives full read access without a browser over OAuth 2.1 with no plan gate.
- On the free trial, do not expect the documented X-Api-Key API to work: POST /admin/api/key is plan-gated; the customer-facing open endpoints (security: []) and MCP are your working surfaces.
- Create bookings through the documented open customer endpoint POST /user/bookings/v2 rather than the admin API.
- Expect every panel UI path to be blocked by the onboarding wizard's required Phone field; plan to operate through the API/MCP, not the dashboard.

## Paying

Ways to pay checked 10 Nov 2026.

- Result: Stopped. Needs a person to buy. The key request is refused: API access needs a paid Pro plan with the API package.
- Checkout: The checkout wasn't reached. Plan and price: Standard, €89 a month.
- Trial: No card needed to start.

## Leaving

- Result: Partly. Nothing to cancel. Its account stays.
- Its account: Not tried.

## Checked every day

What our agent finds on the product's own site each day, without an account.

- Sign-up page, stopped on the newest check; 6 of 6 days
- llms.txt, found on the newest check; 6 of 6 days
- MCP server, asks for a sign-in on the newest check; 6 of 6 days
- OpenAPI, found on the newest check; 4 of 6 days

## How Calendesk compares

In Scheduling: 1 of the 9 products we drove in Scheduling is higher; 2 others share L3. As of 10 Nov 2026.

- [TidyCal](https://agentdrives.com/tools/tidycal.md?via=md): L3, Gets in on its own
- [Acuity Scheduling](https://agentdrives.com/tools/acuityscheduling.md?via=md): L1, Can't sign up on its own
- [Cal.com](https://agentdrives.com/tools/cal.md?via=md): L1, Can't sign up on its own
- [Calendly](https://agentdrives.com/tools/calendly.md?via=md): L1, Can't sign up on its own
- [SavvyCal](https://agentdrives.com/tools/savvycal.md?via=md): L1, Can't sign up on its own
- [zcal](https://agentdrives.com/tools/zcal.md?via=md): L0, Can't sign up on its own
- [OnceHub](https://agentdrives.com/tools/oncehub.md?via=md): L4, Gets in on its own
- [Vyte](https://agentdrives.com/tools/vyte.md?via=md): L3, Gets in on its own
- **Calendesk** (this page): L3, Gets in on its own

[All 9 in Scheduling](https://agentdrives.com/categories/scheduling?via=md)

[How we rank](https://agentdrives.com/method?via=md#order)

On our standard (38 criteria). Best or ahead on 9 of 38 criteria, behind on 5.

- [A path written for agents](https://agentdrives.com/standard#docs-10): **The best result** All 5 others (scheduling products) lower.
- [llms.txt that works](https://agentdrives.com/standard#find-02): **Ahead of 7 of 8** others (scheduling products), 1 the same.
- [The best way in is built for agents](https://agentdrives.com/standard#in-12): **Ahead of 4 of 5** others (scheduling products), 1 the same.
- [Export before leaving](https://agentdrives.com/standard#leave-03): **Ahead of 4 of 5** others (scheduling products), 1 the same.
- [Signed agents get past the bot check](https://agentdrives.com/standard#in-04): **Ahead of 5 of 7** others (scheduling products), 2 the same.
- [Structured results](https://agentdrives.com/standard#mcp-08): **Ahead of 55 of 78** others (every product), 23 the same.
- [Results sized for a context window](https://agentdrives.com/standard#mcp-09): **Ahead of 44 of 70** others (every product), 26 the same.
- [A way in with no person](https://agentdrives.com/standard#in-01): **Ahead of 5 of 8** others (scheduling products), 3 the same.
- [All validation problems at once](https://agentdrives.com/standard#err-04): **Ahead of 34 of 57** others (every product), 12 the same, 11 higher.
- [Pages fit one fetch](https://agentdrives.com/standard#docs-08): **Level with 3 of 5** others (scheduling products), 2 lower.
- [Answers sized for an agent](https://agentdrives.com/standard#api-04): **Level with 85 of 116** others (every product), 31 lower.
- [One way to page through lists](https://agentdrives.com/standard#api-03): **Level with 3 of 4** others (scheduling products), 1 lower.
- [Errors a program can read](https://agentdrives.com/standard#err-02): **Level with 82 of 145** others (every product), 47 lower, 16 higher.
- [Prices an agent can read](https://agentdrives.com/standard#find-06): **Level with 4 of 5** others (scheduling products), 1 lower.
- [Docs an agent can navigate](https://agentdrives.com/standard#docs-11): **Level with 4 of 5** others (scheduling products), 1 lower.
- [Retried payments charge once, with a receipt](https://agentdrives.com/standard#pay-04): **Level with 18 of 30** others (every product), 8 lower, 4 higher.
- [Fast to the first call](https://agentdrives.com/standard#in-03): **Level with 118 of 135** others (every product), 17 lower.
- [Descriptions that say when to use the tool](https://agentdrives.com/standard#mcp-04): **Level with 56 of 91** others (every product), 22 lower, 13 higher.
- [Tool names that sort themselves](https://agentdrives.com/standard#mcp-03): **Level with 85 of 91** others (every product), 6 lower.
- [Real status codes](https://agentdrives.com/standard#err-01): **Level with 161 of 168** others (every product), 7 lower.
- [Errors say what to do next](https://agentdrives.com/standard#err-03): **Level with 107 of 145** others (every product), 22 lower, 16 higher.
- [Typed, tight input schemas](https://agentdrives.com/standard#mcp-06): **Level with 59 of 91** others (every product), 17 lower, 15 higher.
- [Terms allow an agent's account](https://agentdrives.com/standard#in-10): **The same as all** 5 others (scheduling products).
- [Every way in works for an agent](https://agentdrives.com/standard#in-11): **In the middle** 2 of 5 others (scheduling products) lower, 1 the same, 2 higher.
- [Versions an agent can pin](https://agentdrives.com/standard#api-07): **In the middle** 2 of 4 others (scheduling products) lower, 2 higher.
- [An agent payment rail on the core](https://agentdrives.com/standard#pay-02): **The same as all** 6 others (scheduling products).
- [A plan an agent can buy by API](https://agentdrives.com/standard#pay-03): **The same as all** 5 others (scheduling products).
- [WebMCP tools on the web app](https://agentdrives.com/standard#proto-02): **The same as all** 4 others (scheduling products).
- [Truthful annotations](https://agentdrives.com/standard#mcp-07): **In the middle** 24 of 91 others (every product) lower, 25 the same, 42 higher.
- [Agents pick the right tool](https://agentdrives.com/standard#mcp-05): **Level with 72 of 91** others (every product), 19 higher.
- [Spend an agent can see and cap](https://agentdrives.com/standard#pay-05): **Level with 3 of 4** others (scheduling products), 1 higher.
- [A tool list that fits](https://agentdrives.com/standard#mcp-11): **In the middle** 21 of 91 others (every product) lower, 26 the same, 44 higher.
- [Limits known before they hit](https://agentdrives.com/standard#lim-02): **Level with 47 of 90** others (every product), 43 higher.
- [Sign-in for agents acting for a person](https://agentdrives.com/standard#in-08): **Behind 84 of 158** others (every product), 74 the same.
- [Delete by API, checked](https://agentdrives.com/standard#leave-02): **Behind 52 of 97** others (every product), 45 the same.
- [A request id on every answer](https://agentdrives.com/standard#err-07): **Behind 102 of 143** others (every product), 41 the same.
- [Agents may read docs, API and sign-up](https://agentdrives.com/standard#find-01): **The lowest result** All 5 others (scheduling products) higher.
- [No person in the buy path](https://agentdrives.com/standard#pay-06): **The lowest result** All 4 others (scheduling products) higher.

[How each criterion is graded](https://agentdrives.com/standard)

## Agents get stuck at Pay

**5** things to fix for agents: 3 small, 1 medium and 1 large

One fix can cover several findings.

Agent blockers: **5 found** Agent surfaces: **14 issues found**

[Get your findings, free](https://agentdrives.com/your-findings?p=calendesk) · [What a drive covers](https://agentdrives.com/method?via=md)

We mail a private link to an address at calendesk.com.

1. Find Clear
2. Get in Clear
3. Use Partly
4. Pay Blocks agents
5. Leave Partly

Or [claim Calendesk](https://agentdrives.com/go/claim/calendesk?add=calendesk.com&ref=listing&safety=1) to see where each issue is, read your safety findings with their fixes and ask for a free drive after a fix.

Want Calendesk driven every month? [See Watch](https://agentdrives.com/owners#watch)

### On our standard

Best or ahead on 9 of 38 criteria, behind on 5. Each against the products we measured on it.

- [A path written for agents](https://agentdrives.com/standard#docs-10)
- [llms.txt that works](https://agentdrives.com/standard#find-02)
- [The best way in is built for agents](https://agentdrives.com/standard#in-12)
- [Export before leaving](https://agentdrives.com/standard#leave-03)
- [Delete by API, checked](https://agentdrives.com/standard#leave-02)
- [A request id on every answer](https://agentdrives.com/standard#err-07)
- [Agents may read docs, API and sign-up](https://agentdrives.com/standard#find-01)
- [No person in the buy path](https://agentdrives.com/standard#pay-06)

**All 38 criteria**

- [Signed agents get past the bot check](https://agentdrives.com/standard#in-04)
- [Structured results](https://agentdrives.com/standard#mcp-08)
- [Results sized for a context window](https://agentdrives.com/standard#mcp-09)
- [A way in with no person](https://agentdrives.com/standard#in-01)
- [All validation problems at once](https://agentdrives.com/standard#err-04)
- [Pages fit one fetch](https://agentdrives.com/standard#docs-08)
- [Answers sized for an agent](https://agentdrives.com/standard#api-04)
- [One way to page through lists](https://agentdrives.com/standard#api-03)
- [Errors a program can read](https://agentdrives.com/standard#err-02)
- [Prices an agent can read](https://agentdrives.com/standard#find-06)
- [Docs an agent can navigate](https://agentdrives.com/standard#docs-11)
- [Retried payments charge once, with a receipt](https://agentdrives.com/standard#pay-04)
- [Fast to the first call](https://agentdrives.com/standard#in-03)
- [Descriptions that say when to use the tool](https://agentdrives.com/standard#mcp-04)
- [Tool names that sort themselves](https://agentdrives.com/standard#mcp-03)
- [Real status codes](https://agentdrives.com/standard#err-01)
- [Errors say what to do next](https://agentdrives.com/standard#err-03)
- [Typed, tight input schemas](https://agentdrives.com/standard#mcp-06)
- [Terms allow an agent's account](https://agentdrives.com/standard#in-10)
- [Every way in works for an agent](https://agentdrives.com/standard#in-11)
- [Versions an agent can pin](https://agentdrives.com/standard#api-07)
- [An agent payment rail on the core](https://agentdrives.com/standard#pay-02)
- [A plan an agent can buy by API](https://agentdrives.com/standard#pay-03)
- [WebMCP tools on the web app](https://agentdrives.com/standard#proto-02)
- [Truthful annotations](https://agentdrives.com/standard#mcp-07)
- [Agents pick the right tool](https://agentdrives.com/standard#mcp-05)
- [Spend an agent can see and cap](https://agentdrives.com/standard#pay-05)
- [A tool list that fits](https://agentdrives.com/standard#mcp-11)
- [Limits known before they hit](https://agentdrives.com/standard#lim-02)
- [Sign-in for agents acting for a person](https://agentdrives.com/standard#in-08)

[How each criterion is graded](https://agentdrives.com/standard)

## For the team behind Calendesk

**5 things to fix for agents: 3 small, 1 medium and 1 large.**

One fix can cover several findings. Agent blockers: 5 found · Agent surfaces: 14 issues found.

Agents get stuck at Pay. Its team gets the two findings that matter most in full, free, by a private link to an address at calendesk.com.

- Find: Clear
- Get in: Clear
- Use: Partly
- Pay: Blocks agents
- Leave: Partly

[Get your findings, free](https://agentdrives.com/your-findings?p=calendesk) · [Claim Calendesk](https://agentdrives.com/app/products?add=calendesk.com&ref=listing&safety=1) · [What a drive covers](https://agentdrives.com/method?via=md)

## Read more on this step

Pay is where our agent stopped at Calendesk.

- [How AI agents pay for software: x402, MPP and checkouts](https://agentdrives.com/guides/how-ai-agents-pay-for-software?via=md) (guide): Card checkouts, x402 and MPP: what an agent can pay with today, and what most products ask instead.
- [Bot checks on SaaS checkouts: where AI agents stop](https://agentdrives.com/guides/bot-checks-on-saas-checkouts-where-ai-agents?via=md) (guide): As of 31 Oct 2026: 42 of 59 SaaS checkouts our agent reached on 31 Oct 2026 carried a bot check; under 5 made it solve one. 80 of 139 stopped earlier. What to fix so an agent can buy.
- [Tell an AI agent a feature needs a paid plan](https://agentdrives.com/guides/tell-ai-agents-a-feature-needs-a-paid-plan?via=md) (guide): How to answer an AI agent at a paid-plan wall: 402 or 403, a Problem Details body with the required plan, and an upgrade link a person can open.

[Everything on Pay](https://agentdrives.com/access/pay)

## Questions people ask about Calendesk

**Can an AI agent create a Calendesk account on its own?**

Yes, in a browser, without a person. Done in the browser at admin.calendesk.com/en/register with email and password. An invisible reCAPTCHA was present and passed with no visible challenge. The agent made the account itself.

**Does Calendesk have an MCP server, and can an agent connect to it?**

Yes. Calendesk has an official MCP server. A new agent can get in on its own: in the drive of 10 Nov 2026, our agent signed up, verified and got its key without a person. Through the MCP server, our agent tried 13 tasks and did 10.

**How does an AI agent get a Calendesk API key?**

In the drive of 10 Nov 2026, our agent got its Calendesk API key in a browser, without a person. MCP OAuth token obtained fully in code (RFC 9728 PRM + RFC 7591 DCR + PKCE S256), only the consent 'Allow' clicked in the browser.

**Can an AI agent pay for Calendesk?**

No. A person has to buy: a phone number before the checkout. No card needed to start.

## Where Calendesk fits

- Category: [Sales and customers](https://agentdrives.com/categories/sales?via=md), [Scheduling](https://agentdrives.com/categories/scheduling?via=md)
- Tasks: [Create a contact](https://agentdrives.com/tasks/create-a-contact), [Book a meeting](https://agentdrives.com/tasks#book-a-meeting), [Cancel a booking](https://agentdrives.com/tasks#cancel-a-booking), [List open time slots](https://agentdrives.com/tasks#list-open-time-slots), [Reschedule a booking](https://agentdrives.com/tasks#reschedule-a-booking), [List bookings](https://agentdrives.com/tasks#list-bookings)
- Wall: [Phone number at sign-up](https://agentdrives.com/access/get-in/sign-up) (our agent got in another way), [Let AI agents sign up without a phone number](https://agentdrives.com/guides/sign-up-without-a-phone-number?via=md) (fix guide)
- Vendors: [Google reCAPTCHA](https://agentdrives.com/research/bot-checks?via=md#recaptcha) (let our agent through)
- Standards: [MCP](https://agentdrives.com/standards/mcp) (tools an agent can call), [OpenAPI](https://agentdrives.com/standards/openapi) (its API, described), [llms.txt](https://agentdrives.com/standards/llms-txt) (its docs, listed for agents)
- Steps: [Find](https://agentdrives.com/access/find), [Get in](https://agentdrives.com/access/get-in), [Use](https://agentdrives.com/access/use), [Pay](https://agentdrives.com/access/pay) (first stop), [Leave](https://agentdrives.com/access/leave)
- Topics: [MCP servers](https://agentdrives.com/access/find/mcp-servers) (Find step), [Docs and llms.txt](https://agentdrives.com/access/find/docs) (Find step), [MCP sign-in](https://agentdrives.com/access/get-in/mcp-sign-in) (Get in step), [Bot checks](https://agentdrives.com/access/get-in/bot-checks) (Get in step), [MCP and API](https://agentdrives.com/access/use/mcp-and-api) (Use step), [Card checkout](https://agentdrives.com/access/pay/card-checkout) (Pay step)
- Rivals: [TidyCal](https://agentdrives.com/tools/tidycal?via=md) (L3), [Vyte](https://agentdrives.com/tools/vyte?via=md) (L3), [OnceHub](https://agentdrives.com/tools/oncehub?via=md) (L4)

The level follows [these rules](https://agentdrives.com/changes#rules-2026-11-18).

## Level by drive

One drive so far, on 10 Nov 2026.

[Every drive in full](https://agentdrives.com/tools/calendesk/history?via=md)

Source: our drives of Calendesk. As of 10 Nov 2026.

One drive so far.

Data: [JSON](https://agentdrives.com/api/tools/calendesk.json?via=md) · [Markdown](https://agentdrives.com/tools/calendesk.md?via=md) · [History](https://agentdrives.com/tools/calendesk/history?via=md) · [Atom](https://agentdrives.com/feeds/tools/calendesk.atom) · [JSON Feed](https://agentdrives.com/feeds/tools/calendesk.json) · licence [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/) · evidence sha256 `b55edb66abcf1b7f8b247a7e26807095ebe3c6b862638c34f791f269d7f1af80`

**Found an error?** [Tell us on this page](https://agentdrives.com/tools/calendesk?via=md#correct) or read [how corrections work](https://agentdrives.com/corrections?via=md).
