Reflection vs Switchyard: Features, Pricing & Which Is Better (2026)
A side-by-side comparison of Reflection and Switchyard — features, pricing, and ideal use cases — to help you decide which AI tool fits your workflow.
Reflection
Reflection
AI-powered journaling app and coach that provides guided prompts and insights to support mental health and yearly self-reflection.
Key features
- Guided Prompts: Structured, context-aware prompts that guide users through daily, weekly, monthly, and annual reflection exercises to surface insights and support consistent journaling habits.
- AI Insights and Summaries: Automated analysis of journal entries that highlights themes, mood trends, and actionable observations to help users understand patterns over time.
- Cross-Platform Access: Accessible on web, iOS, macOS, and Android so users can write, review, and continue their reflective practice across devices with synchronized entries.
- Real-Time Coaching Feedback: Immediate coaching-style responses and suggestions based on user entries to help reframe thoughts, set goals, and suggest next steps for wellbeing.
- Privacy-Focused Design: Emphasis on private and secure journaling with controls to keep personal reflections confidential and protected across platforms.
- Habit Building Tools: Features that encourage routine reflection, including reminders, streak tracking, and templated review workflows (e.g., annual reviews) to reinforce consistency.
- Export and Archive: Ability to maintain a personal archive of reflections for long-term review, enabling yearly retrospectives and longitudinal insight gathering.
- Custom Prompts and Templates: Support for adapting or creating templates (such as annual review prompts) so users can tailor reflection practices to personal goals.
- Yearly review Markdown template (2025.md) and folder structure linking Daily, Weekly, Monthly notes
- Organized directories for Daily/Weekly/Monthly/Quarterly/Yearly notes (e.g., 2025-08-27.md, 2025-W35.md)
- Local-first Obsidian compatibility (plain Markdown files stored in vault)
- Optional integration with AI journaling apps (Reflection) for real-time coaching and insights
- Support for Reflection Mode / RAG-style retrieval to enhance responses using historical notes
- PDF parsing capability (upload PDFs and extract text) when used with compatible tools
- Custom rules management for prompt augmentation (save/delete rules locally and toggle insertion)
- API configuration support in companion tools: set model, API key, and API URL for LLM calls
- Privacy-oriented — templates are file-based and suitable for local storage/backups
Best for
- 2025 Annual Review: Conduct a structured year-end reflection using guided prompts to summarize accomplishments, lessons learned, and goals for the coming year.
- Weekly Mental Health Check-Ins: Use brief guided prompts and AI summaries to monitor mood, stressors, and coping strategies across weeks to detect trends early.
- Therapy Supplement: Prepare notes and reflections before or after therapy sessions to clarify topics to discuss and track progress between sessions.
- Career and Goal Retrospectives: Run monthly or quarterly reviews to assess career progress, extract actionable next steps, and realign priorities.
- Habit Formation and Tracking: Use reminders and templated prompts to build a consistent journaling habit that reinforces positive routines and accountability.
- Personal Insight Discovery: Aggregate and analyze past entries to surface recurring themes, behavioral patterns, and emotional triggers for deeper self-understanding.
- Meeting or Project Retrospectives: Adapt templates for professional retrospectives, summarizing outcomes, lessons, and action items at project or year-end boundaries.
- Conducting an annual personal or professional review and archiving reflections
- Integrating daily/weekly/monthly journal entries into a consolidated yearly summary
- Using AI-assisted reflection to surface themes, insights, and next-year goals from existing notes
- Running private mental-health journaling with optional cloud-based AI coaching
- Feeding historical notes to a RAG pipeline for better context-aware prompts and annual analysis
Switchyard
NVIDIA
An open-source Rust proxy and library that routes LLM traffic across models and providers while preserving native OpenAI and Anthropic API compatibility.
Key features
- Protocol Translation: Converts between OpenAI Chat Completions, OpenAI Responses and Anthropic Messages formats so clients keep their native API while any backend serves the request.
- Multi-Backend Routing: Spreads traffic across vLLM, NVIDIA NIM, Ollama and any OpenAI-compatible endpoint, letting you point an existing coding agent at an open-source model without changing the agent.
- LLM Classifier Router: Uses request content to decide whether a given turn needs the weak or the strong model tier, cutting spend on turns that do not need frontier capability.
- Stage Router: Routes most turns from signals already in the conversation — tool results, errors, conversation stage — so no extra model call is needed to make the decision.
- Escalation Router: Runs every turn on the weak tier first, then has a judge read that answer and decide whether the same request should be re-sent to the strong tier.
- Random Routing for A/B Tests: Applies a fixed traffic split across targets for benchmarking, baselines and cost experiments.
- Operational Metrics: Exposes Prometheus metrics for requests, errors, latency, token counts and the overhead added by routing itself.
- Server or Library Deployment: Run it as a standalone Rust proxy configured by routes.toml, or embed switchyard-libsy in your own application so it decides the target and hands the model call back to you.
Best for
- Pointing Coding Agents at Open Models: Serve Claude Code or Codex from vLLM, NIM or Ollama without the agent knowing the API changed.
- Cost/Performance Optimization: Send routine turns to a cheap weak-tier model and reserve the strong tier for turns a classifier or judge says need it.
- Model A/B Benchmarking: Split traffic on a fixed ratio across two models to compare quality, latency and cost on real production requests.
- Provider Migration and Failover: Keep application code on one API shape while swapping or mixing the providers behind it.
- Embedding Routing in an Agent Runtime: Drop the routing algorithms into an existing gateway or agent framework via the library path without adopting a new HTTP stack.
- Operational Visibility: Track per-route latency, error rates and token spend through Prometheus to find which routes are actually costing money.