✦ Sovelo · the science
Research informs Sovelo’s design. It does not prove the app works. This page distinguishes published findings, product choices, and the independent review still needed.
The claim we make — and the one we don't.
Sovelo is evidence-informed: built from findings in the peer-reviewed literature. Sovelo itself has not been tested in a clinical trial, so we do not call it evidence-based, a treatment, or therapy. When that changes through independent research, we will say so here — with the data, not a press release.
ASSSIST-2 was a randomized trial in UK schools. Individualized goals were reached more frequently, but general social-skills outcomes did not significantly improve. The NIHR report says goals were agreed with teachers and parents; they were not necessarily child-chosen. This trial did not test Sovelo or establish the effectiveness of its games. Our product goal is to support preparation for a specific moment chosen by the learner.
In-app practice does not establish a skill in everyday life. Stories offer an optional, context-specific try with support; choosing it is not evidence it happened. Check-ins distinguish practice in Sovelo from a reported try outside the app and label learner versus supporter reports. They change no scores or unlocks. Supporters record what the learner communicated, not guessed feelings. These records stay on the device unless the user exports a backup.
Sovelo never teaches that a social cue has one meaning ("looking away means bored"). Ambiguous moments always present several plausible readings — including "we don't have enough information to know" — and asking beats guessing. This reflects the double-empathy problem (Milton, 2012): misunderstanding between autistic and non-autistic people runs in both directions, so one-directional decoding training is both scientifically shaky and unfair. Sovelo also ships self-advocacy scenes where the other person misreads you, and the skill is saying what's true.
What Sovelo will never measure: eye contact, smiling, sitting still, stimming, "normality," or how much another person ends up liking you. Masking targets are associated in autistic adults' own reports with exhaustion and worse mental health. Different communication styles are differences, not deficits — AAC, typing, gestures, and speech all earn identical credit in every exercise.
Sovelo's skill graphs (32 adult skills, 32 child skills) are organized around the components of social communication described by ASHA — initiation, turn-taking, reciprocity, topic maintenance, clarification, communication repair — extended with what deficit-focused frameworks omit: self-advocacy, boundary expression, the kind no, and energy regulation. Skill evidence in the app is opportunity-gated: if a conversation offered no opening for a skill, silence is never scored against you.
AI plays practice partners and helps parents draft personalized stories. Following the SS-GEN finding that raw LLM story generation needs strict constraints (Feng et al., 2024), every generated children's story must pass deterministic safety checks before a child sees it: banned-content rules (no eye-contact training, no masking, no coerced touch, no mind-reading claims), required elements (a way to ask for help, honored no's, honest uncertainty), plus parent preview. AI never diagnoses, never infers a condition, and practice data never trains models without separate opt-in consent.
If anything on this page ever gets ahead of the evidence, email ezracbrown1@gmail.com and we will correct it.
Wright, B., Blackwell, J. E., Bell, K., Teige, C., … Hewitt, C. (2025). Autism Spectrum Social Stories in Schools Trial 2 (ASSSIST-2): a pragmatic randomised controlled trial of the Social Stories™ intervention to address the social and emotional health of autistic children in UK primary schools. Child and Adolescent Mental Health, 30(1), 4–12 — doi.org/10.1111/camh.12740 · Milton, D. E. M. (2012). On the ontological status of autism: the 'double empathy problem'. Disability & Society, 27(6), 883–887 — kar.kent.ac.uk/62639/ · Crompton, C. J., Ropar, D., Evans-Williams, C. V. M., … Fletcher-Watson, S. (2020). Autistic peer-to-peer information transfer is highly effective. Autism, 24(7), 1704–1712 — doi.org/10.1177/1362361320919286 · Klein, J., Krahn, R., Howe, S., Lewis, J., McMorris, C., & Macoun, S. (2025). A systematic review of social camouflaging in autistic adults and youth: Implications and theory. Development and Psychopathology, 37(3), 1320–1334 — doi.org/10.1017/S0954579424001159 · Monahan, J. L., Freedman, B., Pini, K., & Lloyd, R. (2023). Autistic Input in Social Skills Interventions for Young Adults: A Systematic Review of the Literature. Review Journal of Autism and Developmental Disorders, 10(1), 1–21 — doi.org/10.1007/s40489-021-00280-9 · Gunning, C., Holloway, J., Fee, B., Breathnach, Ó., Bergin, C. M., Greene, I., & Ní Bheolain, R. (2019). A Systematic Review of Generalization and Maintenance Outcomes of Social Skills Intervention for Preschool Children with Autism Spectrum Disorder. Review Journal of Autism and Developmental Disorders, 6, 172–199 — doi.org/10.1007/s40489-019-00162-1 · Feng, Y., Song, M., Wang, J., … Yu, J. (2024). SS-GEN: A Social Story Generation Framework with Large Language Models. arXiv:2406.15695 (preprint, not peer reviewed) — arxiv.org/abs/2406.15695 (preprint, not peer reviewed) · Parsons, L., Cordier, R., Munro, N., Joosten, A., & Speyer, R. (2017). A systematic review of pragmatic language interventions for children with autism spectrum disorder. PLoS ONE, 12(4), e0172242 — doi.org/10.1371/journal.pone.0172242 · Timler, G. R. (2018). Let's Talk: Review of Conversation Intervention Approaches for School-Aged Children and Adolescents with Autism Spectrum Disorder. Seminars in Speech and Language, 39(2), 158–165 — doi.org/10.1055/s-0038-1628367 · Chang, Y.-C., & Locke, J. (2016). A systematic review of peer-mediated interventions for children with autism spectrum disorder. Research in Autism Spectrum Disorders, 27, 1–10 — doi.org/10.1016/j.rasd.2016.03.010 · Fuller, E. A., & Kaiser, A. P. (2020). The Effects of Early Intervention on Social Communication Outcomes for Children with Autism Spectrum Disorder: A Meta-analysis. Journal of Autism and Developmental Disorders, 50, 1683–1700 — doi.org/10.1007/s10803-019-03927-z · Lee, J., Lee, K., Hwang, I., Park, S., & Kim, Y.-H. (2025). AutiHero: Engaging Parents in Creating Personalized, Multi-path Social Narratives for Autistic Children. arXiv:2509.17608 (preprint, not peer reviewed) — arxiv.org/abs/2509.17608 (preprint, not peer reviewed) · American Speech-Language-Hearing Association (2026). Components of Social Communication (Practice Portal). ASHA Practice Portal — Social Communication Disorder — www.asha.org/practice-portal/clinical-topics/social-communication-disorder/components-of-social-communication/ · Office of Head Start, Administration for Children and Families (publication year unconfirmed; accessed 2026). Social Stories. HeadStart.gov — National Center on Early Childhood Development, Teaching, and Learning — headstart.gov/children-disabilities/article/social-stories · National Autistic Society (publication year unconfirmed; accessed 2026). Autism and communication. National Autistic Society advice and guidance — www.autism.org.uk/advice-and-guidance/about-autism/autism-and-communication · W3C Cognitive and Learning Disabilities Accessibility Task Force (2021). Cognitive Accessibility Design Pattern: Use Clear Words. W3C WAI — supplemental guidance to WCAG 2 — www.w3.org/WAI/WCAG2/supplemental/patterns/o3p01-clear-words/ · National Joint Committee for the Communication Needs of Persons With Severe Disabilities (publication year unconfirmed; accessed 2026). Communication Bill of Rights, 3rd Edition. NJC, hosted by ASHA — www.asha.org/NJC/Communication-Bill-of-Rights/ · National Joint Committee for the Communication Needs of Persons With Severe Disabilities (publication year unconfirmed; accessed 2026). Augmentative and Alternative Communication (AAC). NJC, hosted by ASHA — www.asha.org/NJC/AAC/ · Waddington, H., Jordan, P., Scott, E., … Tupou, J. (2023). Community perspectives on support goals for young autistic children: A qualitative investigation. Neurodiversity — doi.org/10.1177/27546330231218587 · Hull, L., Rane, S., Lee, S. H.-L., & Sedgewick, F. (2025). “Just Ask What Support We Need”: Autistic Adults’ Feedback on Social Skills Training. Autism in Adulthood, 7(3), 283–292; first online 2024 — doi.org/10.1089/aut.2023.0136 · Autistic Self Advocacy Network of Greater Boston (publication year unconfirmed; accessed 2026). First-Hand Perspectives on Behavioral Interventions for Autistic People and People with Other Developmental Disabilities. Community report hosted by UCSF Office of Developmental Primary Care — odpc.ucsf.edu/content/first-hand-perspectives-on-behavioral-interventions-for-autistic-people-and-people-with · Huang, K., Yeomans, M., Brooks, A. W., Minson, J., & Gino, F. (2017). It doesn’t hurt to ask: Question-asking increases liking. Journal of Personality and Social Psychology, 113(3), 430–452 — doi.org/10.1037/pspi0000097 · Boothby, E. J., Cooney, G., Sandstrom, G. M., & Clark, M. S. (2018). The liking gap in conversations: Do people like us more than we think?. Psychological Science, 29(11), 1742–1756 — doi.org/10.1177/0956797618783714 · Epley, N., & Schroeder, J. (2014). Mistakenly seeking solitude. Journal of Experimental Psychology: General, 143(5), 1980–1999 — doi.org/10.1037/a0037323 · Sandstrom, G. M., & Boothby, E. J. (2021). Why do people avoid talking to strangers? A mini meta-analysis of predicted fears and actual experiences talking to a stranger. Self and Identity, 20(1), 47–71 — doi.org/10.1080/15298868.2020.1816568 · Kardas, M., Kumar, A., & Epley, N. (2022). Overly shallow?: Miscalibrated expectations create a barrier to deeper conversation. Journal of Personality and Social Psychology, 122(3), 367–398 — doi.org/10.1037/pspa0000281 · Sprecher, S., Treger, S., Wondra, J. D., Hilaire, N., & Herbert, W. (2013). Taking turns: Reciprocal self-disclosure promotes liking in initial interactions. Journal of Experimental Social Psychology, 49(5), 860–866 — doi.org/10.1016/j.jesp.2013.03.017 · Zhao, X., & Epley, N. (2021). Insufficiently complimentary?: Underestimating the positive impact of compliments creates a barrier to expressing them. Journal of Personality and Social Psychology, 121(2), 239–256 — doi.org/10.1037/pspa0000277 · Antonakis, J., Fenley, M., & Liechti, S. (2011). Can charisma be taught? Tests of two interventions. Academy of Management Learning & Education, 10(3), 374–396 — doi.org/10.5465/amle.2010.0012 · Bandura, A. (1977). Self-efficacy: Toward a unifying theory of behavioral change. Psychological Review, 84(2), 191–215 — doi.org/10.1037/0033-295X.84.2.191 · Roediger, H. L., & Karpicke, J. D. (2006). Test-enhanced learning: Taking memory tests improves long-term retention. Psychological Science, 17(3), 249–255 — doi.org/10.1111/j.1467-9280.2006.01693.x · Metcalfe, J. (2017). Learning from errors. Annual Review of Psychology, 68, 465–489 — doi.org/10.1146/annurev-psych-010416-044022 · Laugeson, E. A., Frankel, F., Gantman, A., Dillon, A. R., & Mogil, C. (2012). Evidence-based social skills training for adolescents with autism spectrum disorders: The UCLA PEERS program. Journal of Autism and Developmental Disorders, 42(6), 1025–1036 — doi.org/10.1007/s10803-011-1339-1 · Gates, J. A., Kang, E., & Lerner, M. D. (2017). Efficacy of group social skills interventions for youth with autism spectrum disorder: A systematic review and meta-analysis. Clinical Psychology Review, 52, 164–181 — doi.org/10.1016/j.cpr.2017.01.006 · Mayo-Wilson, E., Dias, S., Mavranezouli, I., Kew, K., Clark, D. M., Ades, A. E., & Pilling, S. (2014). Psychological and pharmacological interventions for social anxiety disorder in adults: a systematic review and network meta-analysis. The Lancet Psychiatry, 1(5), 368–376 — doi.org/10.1016/S2215-0366(14)70329-3 · Hull, L., Petrides, K. V., Allison, C., Smith, P., Baron-Cohen, S., Lai, M.-C., & Mandy, W. (2017). “Putting on my best normal”: Social camouflaging in adults with autism spectrum conditions. Journal of Autism and Developmental Disorders, 47(8), 2519–2534 — doi.org/10.1007/s10803-017-3166-5 Considered and not used: Goldstein, H., Kaczmarek, L., Pennington, R., & Shafer, K. (1992). Peer-mediated intervention: attending to, commenting on, and acknowledging the behavior of preschoolers with autism. Journal of Applied Behavior Analysis, 25, 289–305. — Held, not admitted. The peer-side finding — teaching partners to attend and acknowledge rather than interrogate — is genuinely relevant and would qualify under §3 partial admission. But the outcome measures of an early-1990s behaviour-analytic preschool study could not be confirmed without the full text, and policy E1 turns on exactly those measures. Requires full-text screening before it may be cited. Considered and not used: Chen, T., Yang, W., Wang, Q., Zhang, Y., & Ma, Z. (2020). Effects of social stories intervention for children and adolescents with autism spectrum disorders: A protocol for a systematic review. Medicine, 99, e22018. — Excluded. This is a review protocol — a statement of intent to review — and reports no findings. It was cited on the public methodology page as though it were evidence about Social Stories. A protocol cannot support a claim.
✦ Try Sovelo — one better conversation a day