Skip to content
NeuralForge

03Projects

AI engineering projects that prove what you can build.

Each project brief defines a real problem, a reference architecture, the stack, implementation stages, how to evaluate it and what to hand in. Visuals and metrics are illustrative demo material.

Category

Showing 6 of 6 projects

  • fig. — RAG query path
    1. query
    2. retrieve
    3. rerank
    4. generate
    5. cite
    P.01RAGDemo project

    Knowledge Assistant with RAG

    Build an assistant that answers questions over a private document set, retrieves the passages it relies on and cites them in every answer. You own the full pipeline, from ingestion to source-aware responses.

    • Chunking
    • Embeddings
    • Vector search
    • Citations
    • Context budgets
    • Grounding
    View project brief
  • fig. — bounded agent loop
    1. 1

      plan

    2. 2

      select tool

    3. 3

      validate args

    4. 4

      execute

    5. 5

      observe

    6. loop while goal not met
    P.02AgentsDemo project

    Tool-Using AI Agent

    Build an agent that completes multi-step tasks by calling a small set of well-defined tools, with explicit workflow state, step limits and predictable failure handling.

    • Tool calling
    • Workflow state
    • Step budgets
    • Retries & fallbacks
    • Human handoff
    • Guardrails
    View project brief
  • fig. — eval pass rate by prompt versionIllustrative
    Eval pass rate by prompt version (illustrative)Groundedness rises from 62% at v1 to 89% at v6, dipping at v4. Format validity rises from 81% to 99%. The release threshold is 85%.50%60%70%80%90%100%release threshold 85%v1v2v3v4v5v6prompt versionregression
    • groundedness
    • format validity
    P.03EvaluationDemo project

    LLM Evaluation Bench

    Build a repeatable evaluation harness that runs test cases against prompts and models, scores the results and tracks regressions between versions.

    • Test cases
    • Rubric grading
    • Regression tracking
    • Baselines
    • CI gates
    View project brief
  • fig. — structured outputIllustrative

    output · TicketTriage

    {

    "category": "billing",

    "priority": "high",

    "order_id": "48213",

    "needs_human": true

    }

    • ✓ valid JSON
    • ✓ schema v3
    • ✓ enum values
    • retries: 0 / 2
    P.04LLM AppsDemo project

    Support Ticket Triage with Structured Outputs

    Build a service that classifies incoming support tickets and extracts key fields into a validated JSON schema, ready for routing and reporting.

    • Structured outputs
    • JSON Schema
    • Classification
    • Extraction
    • Validation
    View project brief
  • fig. — chunking with overlap
    1. ## 4. Refunds
    2. Annual plans can be refunded within
    3. 30 days of purchase. Refunds go to
    4. the original payment method.
    5. ### 4.1 Duplicate charges
    6. If a card is charged twice, the
    • c-041 · lines 1–4
    • c-042 · lines 4–8
    • overlap · line 4
    P.05RAGDemo project

    Semantic Search API

    Build a search API that combines embeddings with keyword search, reranks results and serves them behind a FastAPI service with clear relevance metrics.

    • Embeddings
    • Hybrid search
    • Rank fusion
    • Reranking
    • Relevance metrics
    View project brief
  • fig. — request traceIllustrative
    • POST /answer2380 ms
    • embed_query
    • vector_search
    • rerank
    • llm.generate1880 ms
    0 ms2400 msTTFT 820 ms
    P.06DeploymentDemo project

    LLM Observability Pipeline

    Instrument an LLM application with tracing, then build dashboards and alerts for cost, latency, errors and output quality signals.

    • Tracing
    • Token cost
    • Latency percentiles
    • Alerting
    • Redaction
    • Runbooks
    View project brief

Move from experimenting with AI to engineering it.

Build the foundations, projects, and habits needed to design more dependable AI applications.

Explore ProgramsBrowse Learning Paths