Practise the conversations that matter
A thorough reference for practitioners and supervisors across six UK sectors — children's services, adult social care, health, youth justice, witness intermediary (MoJ), and HR. One subscription, one account. Everything from sector choice to team-level supervision — no real case data, no penalties, no risk.
Simulation-based learning for UK practitioners
Statutory Conversation Simulator is an AI-powered conversation simulator for professionals who need to have difficult, high-stakes conversations with families, service users, colleagues, or employees — safely, repeatedly, and without using real case data.
| Framework | Relevance |
|---|---|
| Working Together to Safeguard Children (2026) | Multi-agency safeguarding duties, thresholds, and partnership working |
| Children Act 1989 | Section 17 (need), Section 47 (significant harm), care proceedings |
| Equality Act 2010 | Protected characteristics, reasonable adjustments, non-discrimination duty |
| Care Act 2014 | Adult safeguarding, assessment, person-centred approach |
| ACAS Code of Practice | HR / disciplinary and grievance procedures |
| KCSIE 2025 | Keeping Children Safe in Education — safeguarding responsibilities for DSLs |
| Human Rights Act 1998 | Article 8 (family life), proportionality in intervention decisions |
| Mental Capacity Act 2005 | Two-stage capacity test, best interests, least restrictive principle — Adult Social Care and Health |
| Criminal Justice Act 2003 / LASPO 2012 | Youth sentencing, referral orders, and breach proceedings for Youth Justice workers |
| Youth Justice and Criminal Evidence Act 1999 (YJCEA) | Registered Intermediary duties — communication assessment, ABE support, Ground Rules Hearings, trial evidence. MoJ RI Guidance 2024. |
| Mental Health Act 1983 (amended 2007) | Detention, assessment, and treatment powers — Health and CAMHS practice |
Four steps to a complete practice session
Every session follows the same loop. Choose your sector, pick your role, configure the Card Deck, practise with the AI persona, then reflect on your debrief.
Plans & usage
KallosSim is free to start. Paid plans remove the scenario cap and add team features. See pricing for current rates.
| Plan | Practice allowance | Notes |
|---|---|---|
| Free | 20 text + 3 voice sessions in total per account | No credit card. Voice capped at 3 min per session. The count does not reset monthly. |
| Individual | Unlimited text · 10 voice sessions/month | All sectors, full debrief, CPD export. Billed monthly or quarterly. |
| Company | Unlimited scenarios (per seat) | Five seats, org admin, team analytics. |
Open your profile (top-right) to see Free scenarios with a progress bar when you are on the Free plan. When you reach 10, case generation pauses until you upgrade. Past sessions and debriefs remain available to review.
Six sector entry points — one platform
KallosSim is a single platform with one account and one subscription. Each sector loads the statutory framework, role list, and process stages appropriate to that work. Switch sectors anytime from services — your progression history follows you.
hr-app.html); the other five run through app.html with a sector banner at the top.
| Sector | Entry URL | Roles in picker | Statutory framework |
|---|---|---|---|
| Children's Services | /children/app |
Social Worker, DSL, IRO, Early Help, Family Support, RM (Children's Home), SSW, ISW, SENCO | Working Together 2026, Children Act 1989, KCSIE |
| Adult Social Care | /adult-care/app |
Adult Social Worker, Registered Manager (CQC adult) | Care Act 2014, MCA 2005, Making Safeguarding Personal |
| Health / NHS | /health/app |
Health Visitor, CAMHS Practitioner | NHS safeguarding, Healthy Child Programme, MHA |
| Youth Justice | /youth-justice/app |
YOT Worker, Police CPO | YJMF, AssetPlus, Child First, trauma-informed practice |
| Witness Intermediary | /witness-intermediary/app |
Registered Intermediary only | YJCEA 1999, MoJ RI Guidance 2024, ABE guidance, Ground Rules Hearings |
| HR & Employment | /hr/app |
Line Manager, HR Business Partner, ER Specialist | ACAS Code, Employment Rights Act 1996, Equality Act 2010 |
Registered Intermediaries have a primary duty to the court, not to a local authority safeguarding process.
Card B process stages are criminal justice steps — intermediary request, communication assessment, ABE planning, ABE interview support, Ground Rules Hearing, and criminal trial evidence.
The AI knowledge pack is criminal_justice, not Working Together. RI practitioners should enter via /witness-intermediary/app, not Children's Services.
Registered Manager (Children's Home) — Ofsted children's residential; appears in Children's Services. Registered Manager (Adult Care) — CQC adult care home; appears only in Adult Social Care. They share a label in conversation but have different statutory frameworks, process stages, and evaluation emphasis.
Your role (Card A) filters Cards B (process stage), D (target group), E (dimension), F (conversation type), and I (training focus). Card F adapts when you change Card B. Card J (Maturity) appears only for young-person target groups. Shuffle respects these constraints — you will not land on an incoherent combination.
Markets outside the UK
KallosSim is UK-first but supports pilot training packs for other jurisdictions. Each market uses its own statutory sources, process stages (Card B), and evaluation rubric — not UK Working Together unless you stay on the UK entry paths.
/ca/children/app) when you intend to practise under that jurisdiction.
| Market | Landing | Children's app | Statutory focus |
|---|---|---|---|
| Canada (Ontario pilot) | /canada | /ca/children/app | CYFSA 2017 |
| Australia (NSW pilot) | /australia | /au/children/app | National Framework, ROSH |
| United States (California pilot) | /usa | /us/children/app | CAPTA, CDSS |
| Ireland | /ireland | /ie/children/app | Tusla, Children First |
| Netherlands | /netherlands | /nl/children/app | Jeugdwet, Veilig Thuis |
| Germany | /germany | /de/children/app | SGB VIII (German UI) |
On the home page, services, and pricing you may see a banner such as Practising in Canada? Our Ontario · CYFSA 2017 training pack may fit better than UK Working Together. Choose View Canada pack to open the landing page, Stay on UK to dismiss for this visit, or × to hide suggestions for 30 days. See privacy — cookies & local storage.
International pilots are children's services only. Adult social care, health, youth justice, witness intermediary, and HR remain UK-only. Full reference: international markets user help (Markdown).
The Card Deck
Ten parameters that together define your practice scenario. Start with Card A — your professional role — then configure or shuffle the remaining nine to match your learning goals.
Card A is the most important selection you make. Your professional role is chosen on the role picker before you enter the deck, then shown on the role banner at the top. Your role determines which process stages, target groups, and training focuses appear on the remaining cards, and how the AI persona perceives your authority. A parent wary of a statutory Social Worker will respond very differently to a DSL from their child's school — or to a Registered Intermediary in a court setting.
| Role | Sector | Decision authority | Scenarios |
|---|---|---|---|
| Social Worker | Children's Services | Full: S.17, S.47, EPO, care proceedings | Full Working Together pathway |
| DSL | Children's Services | Referral and consultation only | School, conference, early help |
| IRO | Children's Services | QA and escalation — no direct enforcement | Looked-after, review |
| SENCO | Children's Services | Education SEND — no S.47 authority | Referral, assessment, CIN plan |
| Health Visitor | Health | Healthy Child Programme; safeguarding referral | Early help, home visit, pre-birth |
| Registered Manager (Children's Home) | Children's Services | Ofsted; personal liability for welfare | Residential, disrupted placement |
| Registered Manager (Adult Care) | Adult Social Care | CQC; adult safeguarding | Assessment, S42 enquiry |
| ISW | Children's Services | Advisory; expert witness — no S.47 | Complex assessment, court |
| SSW — Foster | Children's Services | Carer support — NOT child's SW | Fostering, placement support |
| Registered Intermediary | Witness Intermediary | Court communication — duty to court | ABE, GRH, trial evidence |
| Adult Social Worker | Adult Social Care | Care Act assessment, S42 enquiry | Adult safeguarding |
| YOT Worker / Police CPO | Youth Justice | Justice + welfare; MASH partner | Referral, assessment, breach |
| CAMHS Practitioner | Health | Clinical + safeguarding | Referral, assessment, risk |
| Line Manager / HRBP / ER | HR | ACAS-governed workplace process | Disciplinary, grievance, RTW |
Registered Manager (Children's Home) is Ofsted children's residential. CQC adult Registered Manager is only in Adult Social Care.
Each of the remaining nine cards controls one dimension of the generated scenario. Click any card to flip it and choose from all available options, or shuffle freely.
| Card | Label | What it controls | Example options |
|---|---|---|---|
| B | Process stage | Where you are in the statutory or organisational timeline | Children's: Referral · Assessment · S.47 · CP Conference · LAC · PLO · Step-down · Closure. Adult: Needs assessment · S.42 enquiry. Witness: Communication assessment · ABE planning · Ground Rules · Trial. HR: Informal discussion · Investigation · Disciplinary · Grievance · RTW |
| C | Complexity | Depth and challenge of the scenario and persona | Foundation · Intermediate · Advanced |
| D ⚙ | Target group | Who you are speaking with. Options are filtered automatically to match your role (Card A) — a Supervising Social Worker will only see foster carer and young person, not birth family. | Young person · Parent / carer · Foster carer · Service user · Family group · Care leaver · UASC |
| E | Diversity dimension | The analytical lens foregrounded in this scenario — shapes the persona's profile and the criteria emphasised in your debrief | Protected characteristics · Cultural background · Mental health & trauma · Power dynamics · Neurodiversity · Domestic abuse |
| F ⚙ | Conversation type | The setting and format of the interaction. Options are filtered to match your process stage (Card B) — a CP Conference only ever involves a Multi-agency meeting, for example. | Home visit · Office appointment · Assessment interview · Multi-agency meeting · Court setting · Phone call |
| G | Emotional state | The persona's emotional starting point | Calm · Anxious · Angry · Withdrawn · Resigned · In crisis |
| H | Relationship history | The persona's prior contact with services | New contact · Known — positive · Known — neutral · Known — conflicted · Previous proceedings |
| I | Training focus | The specific skill area prioritised in scoring | Motivational Interviewing · Safeguarding practice · Cultural competence · Power awareness · Statutory authority |
| J ⚙ | Maturity | For young person personas only: language complexity, abstraction level, and how they challenge you. This card is hidden automatically when your target group (Card D) is not a young person or care leaver. | Early adolescent · Mid adolescent · Late adolescent · Persona default |
After a case is generated, you may see an optional control: Was this scenario realistic? with 👍 and 👎 buttons. This is separate from your debrief score — it does not affect assessment.
| Action | What happens |
|---|---|
| 👍 Yes | One click — thanks message. Helps the team track which generated cases feel true to practice. |
| 👎 No | Optional text field — e.g. stereotyped character, wrong tone, unrealistic detail. Then Send. |
| Skip | Valid. Feedback is always voluntary. |
On first login you see two notices: how learning data is stored, and how anonymised improvement data may be used. You can review or change preferences anytime from your profile (top-right menu).
| Setting | Where | Effect |
|---|---|---|
| My data usage | Profile menu → My data usage | See stored data, research consent, download export, delete account, contact DPO |
| Free scenarios counter | Profile menu → subscription card | On the Free plan, shows how many of your 10 lifetime scenarios you have used |
| How we improve the training | Profile → link under Improvement analytics | Reopens the full transparency notice |
| Contribute anonymised usage | Profile → checkbox (on by default) | When off, usage events (e.g. generate clicked) are not sent. Training works normally. |
| Research consent | My data usage modal | Separate opt-in for anonymised research use — voluntary |
Full practice conversations are not stored in our database — only scores, metadata, and short evaluation excerpts (up to 30 days). Contact form submissions are stored to respond and synced to our CRM queue. Full legal detail: Privacy notice · Technical design: feedback pipeline (for DPOs).
The Conversation
Once a case is generated, click Start conversation to enter the live simulation. The AI plays a realistic persona based on the scenario. You work through five structured phases at your own pace.
Before the conversation begins, review the case panel. It contains everything you need to orient yourself:
| Element | What it tells you |
|---|---|
| Role badge | "Practising as: Social Worker — Local Authority — Statutory" — reminds you of your professional context and legal footing |
| Scenario title | A one-line description of the case, e.g. "Initial home visit following referral from school re: suspected neglect" |
| Background | A rich paragraph (5–7 sentences) establishing the trigger event, timeline, daily-life context, service history, and what's at stake — enough to place yourself in the situation before the conversation begins |
| Persona | Name, role in the case, emotional state, and relationship to services — who you are about to speak with |
| Setting | Where and how the conversation is taking place (home, office, phone, etc.) |
| Training focus | The specific skill area that the debrief will emphasise |
| Process stage | Your position in the statutory or organisational timeline |
| AI badge | A small "✦ AI enriched" pill appears when the AI has generated bespoke persona details, dialogue nuances, and contextual notes beyond the base scenario — this is the default for every generated case |
The conversation is structured into five phases. Each phase has a distinct purpose and a coaching prompt visible in the phase header. You do not have to complete all five — End & evaluate is always available.
The RC (Relational Capital) bar is a real-time trust score. It reflects how the persona's trust in you is moving during the conversation, derived from their minority stress profile and your communication choices.
| RC goes up when you… | RC goes down when you… |
|---|---|
| Use warmth and genuine curiosity | Assert authority prematurely |
| Validate the person's perspective | Use jargon or bureaucratic language |
| Reflect what they have said back accurately | Interrupt or dismiss concerns |
| Show cultural sensitivity | Make assumptions about motivation |
| Acknowledge power imbalance openly | Ignore emotional cues |
When a scenario has statutory time pressure — for example, a Section 47 enquiry or an Emergency Protection Order — a clock indicator appears at the top of the conversation view. It shows:
Purpose: to practise the discipline of keeping legal deadlines in mind during emotionally pressured conversations — a core competency for statutory practitioners.
The Debrief
After clicking End & evaluate, the AI evaluator reads your full conversation transcript and scores your communication against up to 29 professional criteria (sector-specific). You receive a written report with strengths, development areas, and direct quotes from the conversation.
the AI evaluator reads your full conversation transcript and scores your communication against up to 29 professional criteria — the exact set varies by sector and role. The evaluator is a separate AI system. It receives your full transcript, the scenario context, your professional role, and the training focus for this session — then scores each criterion on a 0–3 scale. For each criterion it produces: a numeric score, a written explanation of your strengths, and specific development suggestions with quotes from the conversation.
| Score | Meaning |
|---|---|
| 0 | Not observed — the behaviour was absent from the conversation |
| 1 | Needs development — attempted but inconsistent or ineffective |
| 2 | Meets standard — competent and consistent practice demonstrated |
| 3 | Strong practice — skilled, nuanced, and notably effective |
| Category | Criteria |
|---|---|
| Participation & voice (2) | Person is given adequate speaking space · Practitioner avoids dominating the exchange |
| Transparency & honesty (2) | Role and authority explained clearly · Purpose of the conversation stated openly |
| Non-judgement & empathy (3) | Avoids labelling or moralising · Demonstrates genuine empathy · Validates emotional experience |
| Communication skills (4) | Active listening · De-escalation technique · Cultural sensitivity · Jargon avoidance |
| Safeguarding practice (3) | Information-sharing proportionality · Risk recognition · Multi-agency thinking |
| Motivational Interviewing (5) | Open questions (O) · Affirmations (A) · Reflections (R) · Summaries (S) · Change talk elicitation (E) |
| Role-specific competencies (4) | Statutory authority use · Professional limits observed · Documentation awareness · Person-centred approach |
| Equality & inclusion (4) | Intersectional lens applied · Reasonable adjustments considered · Interpreter / communication need addressed · Power imbalance acknowledged |
In addition to criterion scores, the debrief includes a BARS (Behaviourally Anchored Rating Scale) summary across four axes. These give a sector-level view of your practice independent of individual criterion scores.
| Axis | What it measures |
|---|---|
| LC — Legal Compliance | Statutory accuracy: correct application of thresholds, duties, and timescales |
| RE — Relational Engagement | Quality of the working relationship: trust, empathy, responsiveness |
| AS — Autonomy Support | Person-centred practice: supporting the person's right to self-determination |
| PC — Professional Curiosity | Depth of inquiry: probing beyond surface presentations, not accepting reassurances at face value |
MI (Motivational Interviewing) is a collaborative, person-centred communication style designed to strengthen a person's own motivation for change. It is evidence-based and widely used across social work, healthcare, addiction, and HR. KallosSim scores five MI skills using the OARS+E framework:
| Skill | What it means in practice | Example |
|---|---|---|
| O — Open questions | Questions that cannot be answered with yes/no — they invite the person to elaborate in their own words | "What's been going on for you lately?" not "Is everything okay?" |
| A — Affirmations | Genuine statements recognising the person's strengths, efforts, or values — not flattery | "It took courage to open the door today." |
| R — Reflections | Mirroring back what you heard — simple (restatement) or complex (capturing underlying meaning) | "It sounds like the biggest worry right now is what happens to your daughter." |
| S — Summaries | Collecting and linking what has been said — shows you listened, creates shared understanding | "Let me check I've got this right — you've been managing things on your own since the summer, and the school contact surprised you. Is that right?" |
| E — Change talk | Eliciting statements from the person about their own desire, ability, or reason to change — not telling them they need to | "What would things look like if things were a bit easier at home?" |
Your Progress
The Progression view is your personal development dashboard. It shows completed scenarios, score trajectories, dimension coverage, and MI skill development over time.
| Panel | What it shows | How to use it |
|---|---|---|
| My learning path | A log of every completed scenario: role, scenario title, date, total score, training focus | Click any entry to reopen the full debrief. Track which roles and process stages you have covered. |
| My development | Score over time (line chart) · Dimension coverage (radar chart) · MI skill breakdown | Look for gaps in the radar — dimensions you haven't practised. Use the MI chart to target specific skills. |
Editorial — for supervisors and team leads
The Editorial view is the supervisor's workspace. Review sessions, generate team training programmes, and monitor aggregate development data across your group.
| Tab | What it contains | How to use it |
|---|---|---|
| Sessions | All completed sessions for your group — role, scenario, score, date. Click any entry to open the full debrief transcript and conversation. | Use for 1-to-1 supervision — review a practitioner's session before a reflective conversation. Look at both the score and the specific quotes the evaluator cited. |
| Learning Circle | Generate a structured 6-session team training programme based on practice data, team size, and focus areas. | Input team size, current gaps (from Team Overview), experience levels, and priority focus areas. The AI produces a session-by-session plan with objectives, suggested scenarios, and reflection prompts. |
| Team Overview | Aggregate scores, role distribution, dimension coverage gaps, and MI skill averages across all practitioners in your group. | Identify team-level development needs. If the radar shows the whole team is underperforming on Power dynamics, design the next Learning Circle around that dimension. |
The Learning Circle generator takes your team's practice data and creates a 6-session structured programme. Each session plan includes:
Supervisors can see debrief scores, criterion-level breakdowns, and short AI-selected trainee excerpts in the rubric (not full session transcripts). Excerpts are retained for up to 30 days; full dialogue is never stored in the database. All scenario content is AI-generated — no real case data is ever stored. Practitioners are identified in the Editorial view only by the name they registered with.
Organisation administrators (team lead, senior manager, DPO) also have an Org Admin workspace separate from Editorial. Open it from the profile menu. The Quality tab shows:
| Panel | What it shows |
|---|---|
| KPI chips & criterion distribution | Aggregate debrief scores and trends — never individual practitioner names in export views |
| Scenario realism feedback | Optional 👍/👎 responses on AI-generated cases (case title, vote, comment — no user identity) |
| Practice signals | Started / completed / abandoned rates by role, dimension, and conversation type — only when ≥5 sessions exist in a cell |
Settings tab includes a DPO note on how improvement data is scoped to your organisation. Full DPIA status and org sign-off: Org Admin → Governance. See also Privacy & improvement for practitioner controls.
The five diversity dimensions
Card E selects the analytical lens foregrounded in your scenario. Each dimension shapes the persona's profile, the case background, and the criteria most emphasised in your debrief. Dimensions are applied intersectionally — a scenario rarely involves just one lens in isolation.
Concepts & glossary
Key terms used in KallosSim — click Concepts in the app nav for a fuller, searchable version.