One-Day Intensive

Context Engineering

10.23.26 | 10:00 AM - 4:00 PM PDT · 6 hours in one focused day

What You'll Master

  • Engineer the full context lifecycle — what goes in, why, budget, persist, defend
  • Build a FAISS vector store and RAG retrieval from scratch
  • Compress long docs with summarization pipelines and sliding-window management
  • Give agents a 5-tier hierarchical memory that persists
  • Red-team your context — beat 10+ jailbreak/injection attacks, add Constitutional AI
Pay What You Can →

🔒 Secure checkout via Stripe

💼 Employer footing the bill? We'll invoice you from Manifold with corporate-friendly titles.

🎓 0 scholarship seats available — you can still apply! · sponsor one →

Overview

“Context” is the whole game — and most people fill it with noise. This hands-on Python intensive walks the full lifecycle of model context: what goes in, why, how to budget it, how to persist it, and how to defend it. By 4pm you'll have built, from scratch, a token-budget tracker, a FAISS vector store with RAG retrieval, multi-stage summarization pipelines, a sliding-window context manager, a 5-tier hierarchical memory system, and a red-team suite that throws 10+ jailbreak and injection attacks at your own agents — plus a Constitutional AI critique-revise loop to defend them. You'll leave knowing what “context” actually means, and how to engineer it.

Who this is for & what you'll need

🟣 Pro engineeringBuilt for working engineers.
💻 💪 Capable or 💵 subscriptionUse your own capable machine, or a paid hosted option below.
On your own machineInstall LocalLM and run open-source LLMs locally for free (for those with the hardware).
Or use the hosted optionOr use the OpenAI API / ChatGPT Plus, with Google Colab (Oobabooga) for the open-model work.

Where This Class Leads

What you leave able to do

  • re architect an agent as a stateless reducer
  • reconcile a failing retrieval by reranking and rewriting
  • reconcile a working set with the context window it must fit
  • reconcile an agents run with a tool that failed
  • select among agent architectures
  • synthesise a memory hierarchy for an agent
  • synthesise an agent that carries notes across its own runs

How you show it. Paired runs of the same multi-step task with the note store kept and cleared, where the cleared run repeats a step the noted run skips, plus the note text the agent wrote and the later turn that cites it.

It sits on 4 paths

🤖 Build production AI systems from prompt to deployment. 4 of 12 after AI Alignment · before Claude Model Context Protocol 💼 Replace repetitive business operations with AI (a mini-MBA in AI). 4 of 4 after Custom GPTs 🧑‍💼 Founder with an AI-first company. 5 of 7 after Automate Your Email: No Code AI Automation · before Intro to Agents 🧙 Build strange systems that change how people think. 6 of 8 after Automate Your Email: No Code AI Automation · before The Dark Arts (Red Team)

About 120 hours of practice sit behind this one. See what your hours buy.

Join Us

One-Day Intensive
Suggested $ 400 · pay what you can
  • Your seat in the class
  • Lifetime access to materials
  • Sponsors 1 scholarship seat for someone else

A minimum price keeps out spam. Need to pay less? Apply for a scholarship — no one is turned away for lack of funds.

Pay What You Can

🔒 Secure payment via Stripe

Want to schedule this class for your team?

Contact us: liz@themultiverse.school