Workshop

Introduction To AI Agent Memory

Richmond Alake

Coined Memory Engineering | AI @Oracle

The last job to be done in building agent intelligence is Memory Engineering.

AI agents are the dominant form factor of software today and for the foreseeable future. Engineering them for production means engineering how they retain, reuse, recall, and refine the information pulled from their environment and execution traces.

That is the job of agent memory, and it is what makes agents reliable, believable, and capable.

MIT's Project NANDA calls it the GenAI Divide: 95% of enterprise AI pilots show no P&L impact, and the 5% that cross the divide run systems that retain what they learn, adapt to context, and improve over time.

In other words, memory.

This session is built to put you solidly in the 5%.

Memory is also your biggest tokenomics lever: managing information inside and outside the LLM's context window (through smarter retrieval, storage, and refinement) cuts an agent's operational cost while lifting performance.

The discipline is Memory Engineering.

In one focused session you'll get the vocabulary, mental models, and architecture map on what agent memory is, how it works across Assistant, Workflow, and Deep Research applications, and what the AI Memory Engineer role owns.

What you’ll learn

Go from treating memory as a feature to designing it as infrastructure, with the vocabulary and architecture map of an AI Memory Engineer.

  • Work from a precise definition: memory as infrastructure that is external to the model, persistent, and structured

  • Place memory on the engineering ladder: prompt engineering, context engineering, then Memory Engineering

  • Use a simple test for what counts as memory versus retrieval, state, or cache

  • See how popular AI products and tools such as ChatGPT and Claude leverage memory in their consumer-facing applications.

  • Trace short-term memory (the context window) and long-term memory (external stores) through live product and implementation walkthroughs

  • Implement examples of short- and long-term memory in an agentic application using open-source tools and SDKs from frontier labs

  • Implement the memory types in an agentic application and leave with a reference architecture for your own systems

  • Follow the data-to-memory pipeline: extraction, consolidation, and refinement of raw interactions into durable knowledge

  • Compare storage and retrieval options (vector, graph, relational) and when each one fits

  • Own the full lifecycle: what gets written, consolidated, retrieved, isolated per user, and forgotten

  • See why retrieval (RAG) is one read operation, a single stage of the job, not the job itself

  • Understand every component of an agent memory system, concept to implementation: embedding models, retrieval mechanisms, memory stores etc.

Workshop agenda

  • What is agent memory?

    Agent memory from first principles: what it borrows from neuroscience, a concrete definition and why it drives product performance, the taxonomy across three lenses, and a reference architecture.

  • Implementing memory-aware agents

    Build the memory types into a working agentic application: a detailed implementation with walkthroughs of the key code, plus the core components of an agent memory system in practice.

  • Context and memory engineering, in depth

    The tokenomics toolkit: implement context compaction and reduction, memory evolution and consolidation, and the retrieval strategies that keep an agent's operational costs down.

  • Application modes and the AI Memory Engineer

    Assistant, Workflow, and Deep Research mapped to the memory each demands, and the role emerging around the lifecycle: who is accountable for what your agent writes, recalls, and forgets.

  • Live Q&A and your Memory Engineering roadmap

    Open questions answered live, then the path onward: the reference architecture recap.

Learn directly from Richmond

Richmond Alake

Richmond Alake

Contact

Trains enterprise AI teams. Built courses with Andrew Ng's DeepLearning.AI

See all products from ascxend

Who this workshop is for

  • AI engineers who've shipped an agent prototype and hit the wall: it forgets users, repeats work, and can't improve between sessions.
  • Software engineers moving into agentic AI who want a defined specialism, before "Memory Engineer" starts appearing on job specs.
  • Technical leads and architects deciding how memory fits into their agent stack, and who on the team should own it.

What's included

Richmond Alake

Live sessions

Learn directly from Richmond Alake in a real-time, interactive format.

Lifetime access

Go back to course content and recordings whenever you need to.

Maven Guarantee

Your purchase is backed by the Maven Guarantee.

Frequently asked questions

Maven for Teams

Reimbursement

Get your company to pay

Everything L&D needs: email template, receipts, and certificate of completion.

Get reimbursed

Team discount

Learn with your teammates

Save 20%+ when 2 or more teammates enroll in the same cohort.

Save 20%+ with a team

Private cohort

Run a cohort for your org

A dedicated cohort with a custom schedule and curriculum, tailored to your team.

Book a private cohort

£300

GBP

Oct 1
·

12–2:30pm EDT

Enroll