Coding-school homework grading and learning reports: parents can see the growth
Client Profile
Pain Points
Grading is time-consuming
Every student's code must be run and reviewed line by line.
Progress is hard to quantify
Parents can't see their child's improvement.
Repetitive parent comms
Teachers repeat similar messages to dozens of parents daily.
Live Demo
How We Built It
Auto grading
Run code, detect logic errors, and generate per-problem feedback.
Learning profiles
Turn progress and mastery into visual growth reports.
Automated parent comms
Auto-push learning reports and communication scripts.
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
Grading standards
Defined grading dimensions for coding homework.
Grading system
Built auto grading and feedback.
Reports
Built learning profiles and growth reports.
Parent portal
Opened report access for parents.
Iteration
Optimized reports from parent feedback.
Before vs After
“Parents now see what their child learned each class and where they improved — renewal talks are much smoother.”
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.
ShenzhenAI Resume Coaching & Mock Interviews
Built an AI resume-coaching and mock-interview assistant to improve students' job-search success.
FoshanAI Mistake Notebook & Score Boosting
Built an AI mistake-notebook and personalized score-boosting plan for a K12 tutoring center.