K12 AI mistake notebook and score boosting: a unique path for every student
Client Profile
Pain Points
Inefficient mistake collection
Mistakes are scattered, time-consuming to collect, and rarely reused.
Hard to tier teaching
Large student gaps make uniform teaching ineffective.
Improvement is unquantified
After all that tutoring, gains are unclear and parents churn.
Live Demo
How We Built It
Auto mistake collection
Photo uploads auto-collect mistakes by knowledge point.
Weak-point diagnosis
Diagnose weak points from mistake distribution and generate study paths.
Stage reports
Auto-generate stage reports that quantify progress.
Not betting on one AI — combining the right few
For a real business scenario, we don't lock in a single technical path up front. We evaluate candidate paths on the same benchmark, then design a hybrid so each path does what it's best at.
General LLM API
Public-cloud models such as GPT-4o / Qwen / DeepSeek
- ✓Out-of-the-box, minimal integration cost, cheap to start
- ✕Limited generalization to vertical domains, unstable field-level accuracy, separate compliance design
Industry fine-tuned model
Domain fine-tuning of open-source models on industry data
- ✓Grasps industry semantics, much higher accuracy, private deployment
- ✕Needs labeled data plus ongoing training and upkeep
RAG + rule engine
Retrieval-augmented knowledge plus business rule checks
- ✓Highly targeted, explainable, best latency and cost
- ✕Requires continuous data-loop investment
Fusion, not selection
What we deliver is not a single model but a fused pipeline of primary path + semantic correction + graceful fallback: routine cases are handled by the industry model in seconds; low-confidence fields are re-understood by an LLM; on service anomalies the system degrades to a general API and flags manual review — achieving accuracy, cost, latency and controllability at once.
An explainable, degradable, evolvable AI pipeline
We treat AI engineering as a pipeline, not a black box: every step has clear responsibilities, inputs/outputs and fallbacks. The five-step pipeline plus four-layer architecture below is the technical skeleton.
Ingestion & access layer
Multi-channel access with unified auth, idempotency and masking
AI inference layer
Multi-path inference plus a confidence router switching by features
Business orchestration layer
Connecting results to real business flows with rule checks and closure
Data loop layer
Every online error flows back; models iterate monthly
Tech Stack
Delivery Process
Question bank mapping
Built knowledge-point to question-bank mapping.
Mistake system
Built mistake collection and similar-problem recommendation.
Diagnosis model
Trained weak-point diagnosis.
Pilot classes
Trial in 2 classes.
Rollout
Covered all students.
Before vs After
“Every student's mistakes and weak points are clear at a glance, so tutoring has direction and gains are visible.”
Where It Fits
Related Cases
AI Teaching Assistant & Content Generator
Built an AI teaching assistant and content-generation platform for a training provider to cut costs and boost efficiency.
GuangzhouAI Homework Grading & Learning Reports
Deployed a homework-grading and learning-report system to ease teacher load and improve parent communication.
ShenzhenAI Resume Coaching & Mock Interviews
Built an AI resume-coaching and mock-interview assistant to improve students' job-search success.