← Back to workKHAS-ERDENE TSOGTSAIKHANContact
04AI course recommendations + extension infra

CourseLynx

Worked across CourseLynx’s AI assistant, catalog ingestion, backend reliability, and Chrome extension infrastructure for a student-facing product supporting 40,000+ users across 16+ universities.

  • LangChain
  • Vector search
  • JSON Schema
  • Chrome Extension
  • CSV ingestion
  • REST APIs
CourseLynx Canvas invite sender extension flow
Proof artifactExtension proof - Canvas invite sender

Software Engineering Intern

01 / Problem

What needed to change

Course discovery is fragmented across university catalogs, degree pages, search portals, and constantly changing requirement data. The product needed recommendations that felt conversational without hallucinating course facts.

02 / What I built

The engineering response

LangChain agent workflows with tool calling, vector retrieval, web scraping, REST API integrations, JSON/schema validation, deterministic fallbacks, CSV ingestion scripts, idempotency checks, validation logging, duplicate prevention, and Chrome extension ownership across content scripts, backend APIs, privacy-safe onboarding checks, and supported university domains.

03 / Impact

The signal

Supported a product serving 40,000+ users across 16+ universities, raised structured assistant response validity to 84%, covered core workflows with 30+ unit/integration tests, reduced import failure risk with safer ingestion logs, and owned Chrome extension infrastructure from supported-domain checks to backend integration.

04 / What I learned

The durable insight

Production AI products need structure around the model: valid outputs, predictable tools, clean ingestion, safe rendering, and defensive extension behavior matter as much as the recommendation itself.

Engineering depth

How I engineered it

The constraints, reliability decisions, and system boundaries behind the visible product.

  1. 01

    Separated flexible LLM reasoning from trusted course data by routing student intent through tools, catalog retrieval, and schema-validated response objects.

  2. 02

    Built ingestion reliability around idempotency, duplicate prevention, validation logs, and tests so 16+ university catalogs could be maintained without silent data drift.

  3. 03

    Owned Chrome extension flows defensively: supported-domain checks, privacy-safe onboarding, content scripts, and backend calls that fail predictably instead of breaking the student experience.

  4. 04

    Measured agent quality at the interface boundary with structured-response validation and deterministic fallbacks, increasing valid assistant outputs while keeping retrieved course facts grounded in university data rather than model memory.

System architecture
01Student query→
02Tool routing→
03Catalog retrieval→
04Schema validation→
05Extension workflow