Attentive vs Postscript for SMS
What ChatGPT and Perplexity actually recommended when asked this, three times each, on 12 October 2026. Results are shown per engine because the two do not agree.
ChatGPT
All figures measured.
| # | Product | Recommended in |
|---|---|---|
| 1 | Attentive | 3 of 3 |
| 2 | Postscript | 3 of 3 |
| 3 | Klaviyo | 1 of 3 |
Scanned 12 October 2026. 3 samples from ChatGPT, round 9. 3 products recommended. Methodology v2026-09-29.1.
Perplexity
All figures measured.
| # | Product | Recommended in |
|---|---|---|
| 1 | Attentive | 3 of 3† |
| 2 | Postscript | 3 of 3† |
† Corrected 12 October 2026: incomplete_round. Some of this round's samples had failed when it was first published. They were collected afterwards with the same questions and settings, and the figures marked † were recomputed. How corrections work
Scanned 12 October 2026. 3 samples from Perplexity, round 9. 2 products recommended. Methodology v2026-09-29.1.
Counts, not percentages: with three samples a percentage would imply a precision the sample size cannot carry. “2 of 3” means the assistant recommended that product in two of its three answers to this question.
Sources the assistants cited
- zigpoll.com 3
- sequenzy.com 2
- attentive.com 2
- resources.rework.com 2
- maestra.io 2
- comparegiants.com 1
- youtube.com 1
- finsi.ai 1
- appstoreresearch.com 1
- selecthub.com 1
- g2.com 1
- ustechautomations.com 1
Scanned 12 October 2026. 6 samples across ChatGPT and Perplexity, round 9. Methodology v2026-09-29.1.