Haven is an active-hardening crisis simulation trainer for domestic violence hotline operators and advocate training programs. The connected repo implements a browser-based frontend, a backend service with a real-time voice AI proxy, post-call analysis, secure authentication, session history, custom scenarios, audit events, quotas, and a managed cloud hosting environment.
Voice-based crisis hotline simulation with live AI coaching and post-call analysis
Actual Haven app screenshot. Public-safe preview with no sensitive caller or trainee data shown.Public-safe preview
Asset type
Voice-Based Crisis Hotline Simulation Trainer
Active-hardening browser-based simulation platform with live AI voice sessions, post-call analysis, scenario authoring, history, mastery analytics, secure authentication, a managed database, and cloud hosting.
Demo posture
Controlled walkthrough available by
Controlled walkthrough available by request. Buyer-facing claims should be verified with current lint, build, unit tests, emulator-backed end-to-end checks, database rules checks, microphone functional test, and health/readiness endpoint evidence.
Best fit
Crisis hotlines, DV coalitions, advocate onboarding programs, social work training programs, and simulation platforms seeking voice-based practice for hotline skills.
Domestic violence hotline training coordinators, New advocate onboarding programs
Buyer paths
Pilot • License • Acquisition • Training Partnership
Trust signals
Public-safe indicators buyers can use before requesting deeper materials.
Modern browser-based frontendBackend service proxyLive AI voice simulationServer-side AI credential handlingAuthentication and managed database
Product thesis
Why this asset exists
Hotline and advocacy trainees need realistic, repeatable practice before supporting people in crisis. Haven gives trainees a browser-based simulation environment where they can practice de-escalation, active listening, safety planning, and scenario-specific decision-making, then review post-call feedback and progress over time.
01
Buyer need
New hotline advocates often move from classroom concepts to live crisis support with limited realistic practice. Text, voice, safety planning, escalation, silence, uncertainty, and caller emotion are hard to rehearse consistently with human role-play alone. Training programs need a safe, repeatable simulation environment with scenario structure, feedback, and skill progression.
Hotline trainees need realistic practice before handling live crisis interactions
Human role-play is hard to scale consistently across distributed volunteer programs
Voice-based de-escalation requires timing, tone, silence management, and safety planning practice
Training programs need structured feedback and session review, not only one-time practice calls
AI simulation tools require strong privacy, quota, credential, and deployment controls before real training use
02
Product response
Haven provides a browser-based voice simulation workflow. Trainees authenticate, choose built-in or custom scenarios, start a microphone-enabled live AI session through a backend proxy, complete the simulation, receive post-call analysis, and review saved history and mastery analytics. The backend keeps AI credentials server-side, verifies user tokens, enforces quotas and concurrency limits, validates analysis payloads, and writes audit events.
Runs browser-based voice simulations through a backend live AI proxy
Provides built-in scenario personas with objectives, meters, rubrics, and difficulty settings
Supports custom scenario creation for non-anonymous authenticated users
Generates post-call analysis and reflection support after simulations
Saves history and supports mastery analytics through securely managed data paths
Uses backend auth, rate limits, quotas, concurrency controls, and audit events to support safer operation
Capabilities
What buyers evaluate first
These are the product behaviors, workflows, and evidence points a buyer can scan before requesting deeper materials.
Voice simulation entry
Public-safe Haven landing screenshot replacing the previous diagram-only placeholder on public app surfaces.
Scenario library
Built-in training scenarios support structured crisis hotline practice before live caller work.
Backend safety controls
Authentication, AI proxying, rate limits, quotas, concurrency controls, and audit events are documented for diligence.
3
Interface previews
Public-safe product visuals
Previews use demo, redacted, or representative content so buyers can inspect the interface without exposing sensitive data.
Screenshot
Screenshot1 of 1
Screenshot
Actual Haven app screenshot. Public-safe preview with no sensitive caller or trainee data shown.
Use cases
Where this asset fits
New advocate onboarding
Trainees complete realistic voice simulations before moving into supervised hotline or chat work.
Scenario-based skill practice
Training coordinators assign scenarios focused on de-escalation, safety planning, trust-building, or difficult caller dynamics.
Custom training scenario creation
Programs create their own scenario modules or custom scenarios to reflect local hotline patterns and coaching priorities.
Post-call coaching
Trainees review results, history, and mastery data to identify strengths and practice goals.
Controlled training pilot
A DV coalition pilots Haven with a small training cohort while validating privacy, database access rules, microphone flow, accessibility, and release controls.
Review package
What transfers, what stays gated, and what needs verification.
The public brief gives buyers a safe first pass. Deeper implementation and operational materials stay controlled by fit review.
Documentation
Public overview available. Detailed documentation is gated for controlled review.
Review by request
Testing / QA
QA evidence is available in controlled review and should be freshly verified before buyer reliance.
Controlled review
Transfer boundary
Transfer scope is reviewed privately during app-specific diligence.
Controlled review
Included assets
Browser-based frontend — Implemented
Backend service — Implemented
Real-time voice AI proxy — Implemented
Post-call analysis endpoint — Implemented
Authentication and managed database integration — Implemented
Database access rules for users, simulations, custom scenarios, and audit logs — Present; deployed parity must be verified
Built-in scenario library — Implemented
Custom scenario creator — Implemented for non-anonymous authenticated users
Results, history, and mastery dashboard routes — Implemented
Quotas, concurrency controls, rate limiting, and audit events — Implemented
Managed cloud hosting path — Documented
Production runbook and compliance/security docs — Present
Automated test and E2E scripts — Present; current pass status must be verified
License or sale terms — By inquiry
Commercial paths
acquisitionlicensingpartnershippilotcustomization
Controlled Pilot
Limited pilot for a hotline or DV training program after current build, test, end-to-end, database rules, microphone, privacy, and accessibility checks.
Source-Code License
License the frontend, backend service, live AI proxy, authentication and database integration, scenario registry, and runbook materials for buyer-operated infrastructure.
Training Partnership
Customize scenario libraries, rubrics, mastery dashboards, and training workflows for a DV coalition, hotline, or social work training program.
Full Acquisition
Acquire source code, scenario framework, live AI proxy, backend architecture, post-call analysis workflow, runbooks, and transition support under negotiated terms.
Evidence and review posture
Public evidence boundary
This section shows only public-safe evidence language. Deeper technical, security, billing, operational, transfer, and implementation materials stay gated.
Public overview
Available
Public pages provide buyer-centered positioning, fit, use cases, and a controlled next step without implementation details.
Private walkthrough
By request
A private walkthrough can be requested for qualified review. No public demo access is implied.
QA evidence
Controlled review
QA evidence is available in controlled review and should be freshly verified before buyer reliance.
Gated materials
Not public
Technical, security, billing, operational, transfer, and implementation materials are gated and are not included in the public portfolio payload.
What is public versus controlled review
Public pages are designed for discovery: product overview, use case, high-level features, category, and public-safe readiness summary. Deeper technical, security, billing, operational, transfer, and implementation materials are shared selectively after review.
Roadmap labels distinguish completed work from active hardening or planned next steps.
Browser-based crisis simulation frontenddone
Backend servicedone
Real-time voice AI proxydone
Authentication and managed database repositoriesdone
Built-in scenario registrydone
Custom scenario creatordone
Post-call analysis and results UIdone
Session history and comparisonsdone
Mastery dashboarddone
Database access rules and validation constraintsdone
Rate limiting, concurrency, quotas, and audit logsdone
Managed cloud hosting docsdone
Current test, E2E, and microphone smoke runin-progress
Accessibility verification and audit evidenceplanned
Formal privacy/security audit updateplanned
Organization-level cohort managementplanned
Expanded scenario library and trainer calibration toolsplanned
FAQ
Common diligence questions
Controlled next step
Interested in adapting Haven for your organization or portfolio?
Start with a fit conversation. Public summaries stay safe to browse; technical, security, and transfer materials are shared only when the review path is appropriate.
