Products / Caddy
Emerging personal assistants · United States

Caddy

Caddy Technologies Inc.

As of 9 Oct 2026, PAEval has compiled 15 capability records for Caddy from 13 source URLs; 1 are independent observations and 12 come from the vendor's own documentation. Assistant Benchmark (updated 8 Oct 2026) gives it 7.3 on its 1–10 scale, the mean of the 9 of 15 dimensions it scored, ranking #12 of 12 scored products. Scores from different evaluators use different scales and are not combined. PAEval does not publish its own score or rank for it.

Message-Based Universal Personal/Home Execution Agentcaddy.app ↗ caddy.app/use-cases ↗ caddy.app/privacy ↗
Compare with others

Has cross-app writing, website tasks, and proactive follow-up; not just a chat interface

Independent scores · native scales
1–10 mean of scored dimensions · source rank #12 · coverage 9/15
Capability records by evidence tier
  • Independent1
  • Vendor12
  • Third-party report1
  • Not established1

15 records · 13 source URLs · 1 external result(s)

Capability summary

Strongest status per domain; every underlying record is listed below. Availability does not establish task success.

Positioning & scope

Life and work
DocumentedVendor

Handles family schedules, travel, shopping, budgeting, and small business responses.

Raw labels: documented · official_claim · as of 2026-10-09

Regions, eligibility & access

Openness and price
Limited or conditionalThird-party report

Public beta, free to start; list site records Free public beta, no standard payment price list.

Raw labels: public_beta · mixed_official_and_third_party · as of 2026-10-09
Country and language table
Not disclosedNot established

The listed sources were reviewed, but sufficient public documentation was not found.

Limitations: Having a NYC landing page does not mean it is only open in NYC; the official website does not have a complete country/language list.

Raw labels: not_disclosed · unknown_after_review · as of 2026-10-09

Autonomy & background work

Routines and events
DocumentedVendor

Temporary/cyclic reminder; new users default to the local 8 o'clock morning briefing, which will be sent only if it is useful. Important changes in Gmail/Calendar/Slack/Linear can trigger check-in.

Raw labels: documented · official_claim · as of 2026-10-09
Controllable initiative
DocumentedVendor

Active messages can be stopped while retaining individually created reminders and routines; only selected connection sources are checked.

Raw labels: documented · official_claim · as of 2026-10-09

Execution environments

Browser execution
Partly disclosed / partly testedVendor

Officials explicitly handle store, website, and airline check-ins in their own browser; no word on the OS/persistence of that environment or whether it supports user-native control.

Raw labels: partial_disclosure · official_claim · as of 2026-10-09

Calls, messages & identity

Send and write
DocumentedVendor

You can read, draft and send from Gmail, read and write with Google Calendar; your own clear schedule can be updated directly, external invitations/emails/orders need to be reviewed.

Raw labels: documented · official_claim · as of 2026-10-09

Connectors & tools

Services and scope
DocumentedVendor

Gmail, Google Calendar, Slack, Linear, Todoist; and Drive/Sheets reimbursement workflow. Plaid only queries transactions but does not transfer money.

Raw labels: documented · official_claim · as of 2026-10-09

Memory & personalization

Preference
Partly disclosed / partly testedVendor

The official website says that you can learn communication, working methods, and preferences with use; the complete memory editing interface is not explained.

Raw labels: partial_disclosure · official_claim · as of 2026-10-09

Channels & interfaces

Equipment channel
DocumentedVendor

iPhone iMessage, Android RCS, voice messages and group chats; you can ask Siri to send text messages to Caddy.

Raw labels: documented · official_claim · as of 2026-10-09

Research & deliverables

File/Screenshot
Partly disclosed / partly testedVendor

Official use-cases include receipt screenshots to Drive/Sheets, file search, meeting action items, and travel research; full PPT/video/code generation specifications are unknown.

Raw labels: partial_disclosure · official_claim · as of 2026-10-09

Collaboration & parallelism

Group chat and message permissions
DocumentedVendor

Can join group coordination; other iMessage conversations without Caddy participation will not be read.

Raw labels: documented · official_claim · as of 2026-10-09

Reliability & recovery

Confirm completion and unknown mechanism
Partly disclosed / partly testedVendor

The travel page uses final confirmation from the booking platform as the booking criteria; browser login/store availability will limit execution. Idempotence and breakpoint recovery are not disclosed.

Raw labels: partial_disclosure · official_claim · as of 2026-10-09

Permissions, security & data

Training and evaluation controls
DocumentedVendor

The policy states that Customer Data is not used to train AI; some providers can configure zero retention, but not all. You can turn off sending LLM interactions to the evaluation service provider, and the turn off will take effect in the future.

Raw labels: documented · official_policy · as of 2026-09-18

External evaluations & observations

Official new documentation and old tests
Partly disclosed / partly testedIndependent

The test inbox/Notion/Calendar/Slack in September was unavailable; there was no outbound call channel; seats were remembered on 9/16 but dietary preferences were omitted. Cannot test unconnected when the connector is not present.

Raw labels: partial_test_coverage · independent_test · as of 2026-09-16

External measurements & hands-on results

Different methods, samples and dates. Not combined into one success rate.

Assistant Benchmark ↗

Tested
2026-09-16
Version
v0.2
Source score
7.3
Scored dimensions
9
Evidence labels
test: 9; observed: 0; unlabelled: 0

Similar agents

All Caddy alternatives →

Head-to-head comparisons