Acme Learning/

Dashboard

Learning Paths

demo

Seven tracks, A through G — every track taught against Claude and OpenAI side by side.

C
O
Claude + OpenAI · every track
In Progress
3
tracks
Tracks B, C, D in flight
Build first, theorize second
Completed
1
Q1
Track A — Foundations
CLI + prompt library shipped
Hours Learned
24.5
+8.2
+8.2 hours this week
Streak: 12 days
Capstone status
Scoping
Day 1
WhatsApp triage agent
Capstone graded by Track F evals
A

Foundations

Call Claude and OpenAI from a script. Pick the right one per task.

Free forever
8h · 4.2K learners100%
B

Building agents

From "model that answers" to "agent that acts." Plans, tools, recovery.

Pro
18h · 2.8K learners67%
C

Retrieval-augmented generation

Ground answers in private data — embeddings, chunking, citations.

Pro
14h · 2.1K learners45%
D

Voice and text agents

Realtime voice + text chat. Latency budgets, turn-taking, barge-in.

Pro
12h · 1.7K learners22%
E

Connecting agents to data and tools

MCP + safe data access. Let agents read and act on your real systems.

Pro
11h · 1.4K learners0%
F

Evaluating agents

Golden sets, LLM-as-judge, A/B testing. Know when an agent gets better.

Pro
9h · 1.2K learners0%
G

Fine-tuning and model customization

When prompts and RAG aren't enough. OpenAI fine-tune + Claude customization.

Pro
10h · 850 learners0%

What's new this week

A
Claude 4.7 + GPT-4o comparison harness2d ago

Track A CLI now compares both providers head-to-head

B
Claude computer use + OpenAI Agents SDK4d ago

2 new lessons in Track B build the same research agent on each

C
Re-ranking with Voyage + Cohere5d ago

Added to Track C — measurable +12% recall@5 over single-stage

D
OpenAI Realtime API end-to-end6d ago

Track D voice agent: <250ms first audio chunk

E
MCP server kit with auth + scoping1w ago

Track E now ships a starter MCP server template

Tracks update within 48h of major Claude or OpenAI releases.