Synthesis Tutor
https://www.synthesis.com/tutor
Embeds micro-assessments into every lesson to track understanding in real time, adjusting difficulty and teaching approach within session. Combines AI personalization with human-curated content. No publicly disclosed mechanism for a durable cross-session learner profile beyond progress tracking within its math curriculum scope (ages 5–11).
At a glance
- Type
- Real-time micro-assessment adaptation
- Tier
- T3
- Created
- 2020 (founded 2020 by Josh Dahn and Chrisman Frank; Synthesis Tutor AI product added later)
- Latest release
- not applicable — not OSS
- License
- not applicable — not OSS
- GitHub
- not applicable — no GitHub repo
- Pricing
- $20–$45/month; annual from $99/year (up to 7 kids)
- Funding
- $12M Seed · 2024-01
Taxonomy
- storage
- kv
- retrieval
- injection
- persistence
- session
- update
- overwrite
- unit
- profile
- governance
- inspectable
- conflict
- n/a
When to use
Optimised for: learner profile + spaced repetition + assessment-driven adaptation
Anti-fit: not for non-educational use cases
Pros & cons
Pros
Combines AI-driven real-time adaptation with neuroscientist- and educator-designed content; praised for age-appropriate pacing.
Cons
Limited to math, ages 5–11; memory is effectively session-scoped adaptive state, not a long-term learner model.
Claims & capabilities
On pace for $10M+ revenue 2025. Subscribed students up 4.5x YoY.
Technical surface
- API surface
- not applicable — research paper
- Backend storage
- not applicable — research paper
- Deployment
- iOS (iPad) + Web
- Embedding model
- not applicable — research paper
- Multi-tenancy
- not applicable — research paper
- MCP
- not applicable — research paper, no deployed product
- A2A
- not applicable — research paper, no deployed product
- OpenTelemetry
- not applicable — research paper, no deployed product
Similar systems
Other vertical / domain-specific ai memory in the catalog, ranked by inbound references.
- NVIDIA ReMEmbR T3
Builds long-horizon memory by captioning video segments with VILA, storing captions with timestamps + 3D position coordinates in MilvusDB. At query time, LLM iterates retrieval across text, time, and position modalities. Deployed on Nova Carter robot (Jetson Orin).
- Abridge T1
Clinician-assist ambient documentation. Source mapping: every AI-generated summary element traced back to the source utterance. Audit-and-trust layer over episodic memory. Built on proprietary 1.5M+ medical-encounter dataset.
- ASAPP GenerativeAgent T1
Treats memory as first-class architecture. Captures the digital footprint of every interaction; retrieves preference and history at engagement time. Public example: airline knowing a frequent flyer wants aisle seats with her son — preference-aware, not just history-lookup.
- BenevolentAI T1
Target identification / drug repurposing / mechanism tracing. 85+ data sources, petabyte-scale, rebuilt every few weeks. Wet-lab results re-enter the graph and shift downstream predictions — institutional experimental memory closing a feedback loop.
- Causaly T1
Drug discovery / target identification / causal mechanism tracing. The graph is the memory: 7 years of curated biomedical cause-effect relationships compounding with each new ingestion. Scientific RAG retrieves from a versioned causal substrate.
- Character.ai T1
Chat Memories (user-defined facts), auto-memories for c.ai+ subscribers, pinned memories, in-context retention. PipSqueak 2 model (April 2026) reduces in-conversation drift. Memory Visualization meter forthcoming.