}
{
DATAJOURNEYHQ ACADEMY
APPLY
Full Curriculum

6 Weeks

Every week you ship something real. By week 6 you have a complete, production grade AI system with real world reach, documented, and yours to own.

FORMAT Remote · async first · weekly live session
COHORT 01 March 25, 2026
01
WEEK 01 < $5 FOUNDATIONS

Reality Check & First Ship

Theme: Feel it before you engineer it.

Most bootcamps start with theory. We start with a working system in production. By Sunday you've shipped a real CrewAI powered tool. That experience + the excitement

WHAT YOU'LL LEARN
The Abstraction Layer

LLMs as stateless text transformers ; tokens, context windows, the agent loop.

The Five Failure Modes

Hallucination, runaway spend, latency, no fallback, prompt drift. Name them before you code.

Cost Anatomy

tokens × price per token × call frequency = your bill. Calculate it before writing a line.

CrewAI: Fast Lane to Multi Agent

Multi agent system in ~50 lines. Use it deliberately ; feel the ceiling, then understand why.

SHIPS SUNDAY
  • AI Reality Map ; system diagram with named failure modes
  • Market Scout ; live public URL (CrewAI + FastAPI)
  • Cost report ; actual spend + projected monthly
STACK
Python CrewAI FastAPI OpenAI API Fly.io
02
WEEK 02 < $10 MARKET

Market Alignment

Theme: Same behaviour. No framework. Full control.

Week 1 gave you a working system fast. Week 2 answers: what was CrewAI actually doing? Rebuild Market Scout using raw OpenAI API calls and explicit orchestration ; same inputs, same outputs, full visibility. Then pivot: find a real market need, talk to one user, and ship a demo they can touch.

WHAT YOU'LL LEARN
Explicit Orchestration

Write the loop that calls the model, parses the response, decides the next step. No magic.

Token Budget Enforcement

Track cumulative spend per request. Hard stop at a ceiling. Log every token.

Structured Outputs

Use response_format with JSON schema. Enforce structure at the API level.

Problem Market Fit

Skill inventory → problem intersection → user interview → targeted demo. Ship by Sunday.

SHIPS SUNDAY
  • Market Scout v2 ; raw API rebuild, live public URL
  • Cost comparison: Week 1 vs Week 2, annotated
  • One page market brief + user interview notes
STACK
Python OpenAI SDK (raw) FastAPI Pydantic v2
03
WEEK 03 < $20 RETRIEVAL

Tooling & RAG

Theme: Your demo has no memory. Fix that.

The Week 2 demo impresses users ; until they ask a follow up. The model has no context from the previous exchange, no access to your data, no way to ground answers in facts. You'll build a retrieval augmented generation pipeline from scratch, evaluate the ecosystem, and make explicit buy vs. build decisions.

WHAT YOU'LL LEARN
Embeddings & Vector Search

Turn text into vectors. Store in pgvector. Query by semantic similarity, not keyword.

The RAG Loop

Embed query → retrieve top k chunks → inject context → generate. Own every step.

Chunking Strategy

Fixed size vs. sentence aware vs. semantic. How you split determines retrieval quality.

Buy vs. Build Matrix

Pinecone, Weaviate, pgvector, LlamaIndex ; evaluated against your actual requirements.

SHIPS SUNDAY
  • RAG enabled system ; live, grounded, with citation logging
  • Chunking experiment report ; method comparison + scores
  • Buy vs. build matrix ; every layer, with rationale
STACK
OpenAI Embeddings pgvector SQLAlchemy FastAPI
04
WEEK 04 < $50 PIPELINES

AI Pipelines & Agents

Theme: Move AI off the request path.

Event driven architecture, graph based agent orchestration, MCP tools, and vector search wired together into a full end to end pipeline. The model stops being a synchronous API call and becomes a durable background process that reasons, acts, and stores results.

WHAT YOU'LL LEARN
Event Driven Architecture

Trigger AI jobs from events. Handle them durably. Keep your API fast.

Agent Workflows

ReAct loops, graph based orchestration, worker + tool nodes wired into reliable pipelines.

MCP Tools

Model Context Protocol: build a tool, register it, let your agent discover and call it.

Semantic Search

Embeddings + pgvector integrated into the pipeline. Agent retrieves relevant context on demand.

SHIPS SUNDAY
  • End to end AI pipeline: event → agent → tool calls → stored result
  • One working MCP tool registered to your agent
  • Technical walkthrough of your system architecture
STACK
Python MCP SDK Message Queue pgvector
05
WEEK 05 < $100 HARDENING

Reliability & Deployment

Theme: Works on my machine → runs in production.

Durable execution, step by step tracing, container setup, and launch prep. Your Week 4 pipeline is impressive ; now make it survive failures, give you full visibility into what happened, and run somewhere that isn't your laptop.

WHAT YOU'LL LEARN
Durable Execution

Retries, resumable steps, idempotent design. Your pipeline survives failures without duplicating work.

Observability

Trace agent runs step by step. See exactly what happened, what state each node produced, where it failed.

Deployment

Container setup, environment config, services talking to each other in a real environment.

Launch Prep

Repo structure, README, setup instructions. If it takes >10 minutes to clone and run, it's not ready.

SHIPS SUNDAY
  • Hardened pipeline ; retry safe, failure tolerant
  • Execution traces ; visible, step by step agent run logs
  • Live deployed project + public repo, clone and run ready
STACK
Docker OpenTelemetry Fly.io / Railway GitHub Actions
06
WEEK 06 CAPSTONE

Build Something That Matters

Theme: You choose the problem. You own the outcome.

No spec. No prescribed stack. Five weeks of foundations, retrieval, pipelines, and hardening — now apply them to something you actually care about. Pick a real problem, build a working solution using whatever combination of tools makes sense, and present it to the cohort.

GOAL

Define a problem worth solving. One sentence. Who has it, what it costs them, why AI is the right lever.

ACTION

Ship a working system. It should be live, usable, and reflect at least three weeks of curriculum. Your decisions, your tradeoffs, your code.

PRESENTATION

Present to the cohort. Walk through the problem, the system, one live demo, and what you'd do differently. 10 minutes. No slides required.