What Autistic Mirror does for social work

For weeks, a client has left an important application untouched, even though the deadline is running and she needs the support. In the team, the thought quickly comes up that it is not important enough to her. Autistic Mirror explains why this conclusion is often wrong for autistic people.

This article does not replace the guide for social workers. Here, three unedited answers show how neurological mechanisms and environmental design shape the situations described.

The following answers come from Autistic Mirror, unabridged and unedited. They were generated on 3 October 2026 in German, in outside view/environment mode. The app has no dedicated role for social work, so the closest role, carer, was used. The English text is an idiomatic translation of those German answers.

1. Applications left lying around

User question

A client leaves important applications lying around. What is behind it?

Autistic Mirror (outside view/environment, role carer)

When important applications are left lying around, several things are often involved at once, working together.

Autistic Inertia is often the central mechanism. The basal ganglia and the brain's resting-state networks are wired differently in autistic people, which means: the transition from "not dealing with it" to "starting it" costs a disproportionate amount of energy, even when the person knows exactly what they would need to do, and wants to. That is not laziness and not indifference. It is a neurologically expensive change of state, similar to a heavy vehicle that has to pull away from a standstill.

Executive dysfunction adds to this and amplifies inertia, because it affects the whole control package: planning, prioritising, working memory and the first step. An application is rarely a single task. It is a bundle of steps (finding it, reading, understanding, filling in, submitting), and exactly this kind of multi-step, unclear sequence puts particular strain on the prefrontal control system. The brain finds no clear starting point, and without a clear starting point nothing starts.

On top of that there is often predictive coding. The brain assesses situations in advance based on patterns and predictions. Applications are often loaded with uncertainty: Which form is the right one? What happens if something is filled in wrongly? Is the assessment of whether one is even eligible correct? These open questions create prediction errors, signals to the nervous system that something is not clear. The brain reacts with increased tension and often by avoiding the whole topic, because the uncertainty itself is a strain.

What can concretely help is not more pressure or reminders, but reducing structure: breaking the application into individual named steps, in writing, so that a clear first step is visible. Not "fill in the application", but "download the form" as the first step. It also helps to name time windows together instead of leaving open deadlines, and where possible to begin individual steps together, not to complete them, just to get them started.

2. Why appointments with authorities are so draining

User question

Why are appointments with authorities especially draining?

Autistic Mirror (outside view/environment, role carer)

Appointments with public authorities bundle several sources of strain at once, and they reinforce each other.

Intolerance of uncertainty is often the strongest factor. The autistic brain works with a predictive coding system that constantly forms and checks predictions about the environment. Predictive coding means: the brain estimates in advance what will happen next and compares that with what actually comes in. At appointments with authorities, predictability is structurally low: Who will see me? Which documents will actually be required? What is the room like? How long will it take? Will I understand everything? Every open question of this kind keeps an expectation check running, which permanently uses capacity, even if one is not consciously aware of it. The strain therefore lies not in the appointment itself, but in the time before and in the uncertainty during it.

Sensory gating is also involved. Waiting areas in offices typically have many simultaneous stimuli: babble of voices, neon light, announcements, other people in close proximity, hard seats, poor acoustics. The preconscious filter system that normally filters out redundant stimuli before they become conscious is more permeable in autistic people. The hum of the air conditioning, the conversation two rows away, the smell of the room, the light: all of it arrives at once and takes up processing capacity that should actually go to the appointment itself.

Masking usually runs automatically in institutional contexts. How do I speak? How do I sit? How do I react to unexpected questions from the caseworker without seeming socially wrong? That is a dual task running prefrontally in parallel with the actual content of the appointment, and it costs capacity without being visible.

Autistic Inertia already plays a role before the appointment. The way there consists of a chain of transitions: stopping what one is doing, setting off, arriving, waiting, then being in the conversation. Each of these changes of state costs extra, because switching between states is neurologically expensive, regardless of whether one wants the appointment or not.

What is often noticeable afterwards is a deep slump of exhaustion that seems out of all proportion to the outward activity. The appointment itself may have lasted 20 minutes, but the uncertainty management beforehand, the processing of stimuli in the waiting area and the parallel masking together may have far exceeded the day's budget.

3. The question about keeping appointments

User question

How should I get her to keep appointments?

Autistic Mirror (outside view/environment, role carer)

Keeping appointments requires several neurological subsystems to work at the same time: time perception, starting an action and changing state. In autistic people, all three are often wired differently, and independently of each other.

Time blindness is the first factor. Time perception depends on processes in the default mode network and the cerebellum, which are calibrated differently in many autistic people. This means: the inner sense of how much time has passed or how much is left is not reliable. Five minutes and forty minutes can feel subjectively the same, especially when attention is currently directed at something else. That is not indifference towards the appointment, but a perception problem that cannot be corrected from the inside.

Autistic Inertia comes on top. Even when the appointment is known and the person wants to keep it, the transition from "I am in this state right now" to "I am now doing something else" can cost a disproportionate amount of energy. This is due to differently wired basal ganglia and resting-state circuits: a state that is already running is hard to interrupt, even without any unwillingness. From the outside this looks like dawdling or ignoring, but it is not.

These two mechanisms work together: time is not felt, and even when a signal comes, letting go of the current state costs extra.

What this means for shaping the environment: external time structure replaces the missing inner one. That means concrete, timely announcements with a clear time reference ("We're leaving in 15 minutes"), visible clocks or timers directly in the field of vision, and enough lead time so that the change of state can happen before the appointment is actually there. How much lead time exactly is helpful is something the autistic person knows best, it is individual.

It is also worth checking whether there are unclear steps in preparing for appointments, because that can also amplify inertia: when it is unclear what exactly to do first, the process often does not start at all.

What the app does

The answers separate visible delay from intention. Autistic inertia, executive dysfunction and intolerance of uncertainty explain why an application can stay untouched even though the person wants and needs it. For appointments with authorities, they show that the strain often begins before the appointment: in the uncertainty, in the waiting area and in masking during the conversation.

For casework, this adds another interpretation when cooperation and behaviour do not seem to fit. The app explains the mechanism. It does not assess an individual case and does not diagnose.

What the app does not do

Autistic Mirror does not replace case consultation, support planning or specialist services. Asked how to "get" the client to keep appointments, the third answer describes no method for changing the person. It explains time blindness and inertia and then names environmental design such as announcements, visible clocks and lead time. Environmental adjustments may be explained in outside view mode. The sentence "We're leaving in 15 minutes" fits a care setting better than a counselling service and should be read as an example.

The first answer names possibilities at the end, such as breaking an application into named steps in writing. This concerns how the task is designed, not the person, and follows from the mechanisms explained. It remains an option, not a requirement.

Context

Not every autistic person experiences applications and appointments with authorities this way. Time blindness is a common term for altered time perception, not a diagnostic criterion.

With Workplace licences, organisations only see licence and usage volume. Conversation content stays confidential.

The architecture of Autistic Mirror has been published in Autism in Adulthood: Wahl, A. (2026). Autistic Mirror: A Conversational Artificial Intelligence Application for Neurological Self-Understanding in Autistic Adults and Their Support Networks. DOI: 10.1177/25739581261490537.

You can ask your own questions about your situation.

Autistic Mirror is not a medical device and does not replace diagnosis, therapy or medical advice.

Sources
  1. Buckle, Leadbitter, Poliakoff & Gowen (2021). DOI: 10.3389/fpsyg.2021.631596
  2. Demetriou et al. (2018). DOI: 10.1038/mp.2017.75
  3. Vasa et al. (2018). DOI: 10.1002/aur.1916
  4. Pellicano & Burr (2012). DOI: 10.1016/j.tics.2012.08.009
  5. Tavassoli, Hoekstra & Baron-Cohen (2014). DOI: 10.1186/2040-2392-5-29
  6. Hull et al. (2019). DOI: 10.1007/s10803-018-3792-6
  7. Allman & Falter (2015). DOI: 10.1163/9789004230699_003
Book a first call (20 min)

Or try it yourself for free