Compare / Ollie vs Shuffle

Ollie vs Shuffle

Ollie is a home personal assistant from Confabulation Corporation (United States); Shuffle is a creation/entertainment companion assistant, including website execution from DNFT (United States). On Assistant Benchmark (1–10, updated 8 Oct 2026), Ollie scores 8.3 over 13 dimensions and Shuffle scores 7.8 over 10; both were scored on 9 of the same dimensions, shown below. PAEval holds 16 capability records for Ollie and 14 for Shuffle (as of 9 Oct 2026).

Scores stay on each evaluator's own scale and are never combined. PAEval does not pick a winner.

OllieShuffle
VendorConfabulation CorporationDNFT
HQ regionUnited StatesUnited States
TypeHome personal assistantCreation/entertainment companion assistant, including website execution
Pricing (as documented)Public index price: Free 6 items per day + 50 items per month; Everyday $25/month, 10 per day + 150 per month; Always-On $100/month, 15…Pro $8/month: Unlimited chat + 880 monthly picture/video/music credits; $1 daily pass and $4.99 weekly pass are unlimited chat.
Assistant Benchmark1–10 mean of scored dimensions8.3coverage 13/157.8coverage 10/15
micro1 PersonalAgentBench% of 10 workflows with trusted completionNot scoredNot scored
SuperCLUE-XClaw0–100 weighted total of 5 dimensionsNot scoredNot scored
Autonomy & background workIndependently observedPartly disclosed / partly tested
Execution environmentsPartly disclosed / partly testedDocumented
Calls, messages & identityPartly disclosed / partly testedPartly disclosed / partly tested
Connectors & toolsDocumentedNot disclosed
Memory & personalizationDocumentedDocumented
Channels & interfacesDocumentedDocumented
Research & deliverablesPartly disclosed / partly testedDocumented
Transactions & bookingsNo recordNo record
Collaboration & parallelismDocumentedDocumented
Reliability & recoveryNot disclosedIndependently observed
Permissions, security & dataDocumentedDocumented
Capability records16 (2 independent)14 (1 independent)
Capability cells show the strongest documented or observed status in each domain; availability is not task success.Add more products →

Assistant Benchmark, dimension by dimension

OllieShuffle
Carrying out an online task9test7.5test
Travel booking7test9test
Recommendation quality7test9test
Purchasing a product8test8test
Responding to emails8test8test
Proactive behavior8testNot tested
Running a routine10testNot tested
Third-party integrations7test7test
Permissions & privacy8test7test
MemoryNot tested6test
Phone callsn/an/a
Multiplayer / groups9testn/a
Chained tasks8test7test
Proactive restraint10testNot tested
Content creation / games9test9test
Source scores on the 1–10 anchor scale. "Not tested" is missing evidence, not zero.Source ↗