Skip to content
New this month 24 fresh C++, C#, F#, JavaScript, TypeScript and Lua courses just landed. Browse new releases Use code WELCOME10 for 10% off your first order · 14-day refund
WisdomCharms — home
Cart 0 items in cart
AI & Machine Learning Advanced New

Agentic Systems Engineering: Planning, Memory and Tool Loops

Design agents that plan, remember and stop, instead of looping until the budget is gone.

7 students

PR Created by Priya Raman

  • Last updated August 2026
  • English
  • 17h 30m of material
  • 131 lessons

What you will learn

8 concrete outcomes

Every bullet below is something you will have built, shipped or be able to explain by the time you finish the last lesson.

  • Implement single-step, ReAct, planner and supervisor architectures and compare them
  • Design working, episodic and semantic memory with clear boundaries
  • Compact long-running context without losing the original constraints
  • Add human approval gates before any consequential action
  • Replay a run deterministically from a stored trace to debug it
  • Sandbox code execution so an agent cannot damage your environment
  • Cap cost per run and stop cleanly when the budget is exhausted
  • Evaluate agents on outcomes rather than on a plausible-looking transcript

Course curriculum

8 modules · 131 lessons · 17h 30m of material

16 lessons running 2h 6m in total. Each lesson ships with the finished source files and a short written recap, so you can follow along in your own editor and skim the module again later.

Lesson-by-lesson titles, code downloads and exercises live inside the course library you get access to straight after checkout.

16 lessons running 2h 12m in total. Each lesson ships with the finished source files and a short written recap, so you can follow along in your own editor and skim the module again later.

Lesson-by-lesson titles, code downloads and exercises live inside the course library you get access to straight after checkout.

17 lessons running 2h 16m in total. Each lesson ships with the finished source files and a short written recap, so you can follow along in your own editor and skim the module again later.

Lesson-by-lesson titles, code downloads and exercises live inside the course library you get access to straight after checkout.

17 lessons running 2h 18m in total. Each lesson ships with the finished source files and a short written recap, so you can follow along in your own editor and skim the module again later.

Lesson-by-lesson titles, code downloads and exercises live inside the course library you get access to straight after checkout.

17 lessons running 2h 12m in total. Each lesson ships with the finished source files and a short written recap, so you can follow along in your own editor and skim the module again later.

Lesson-by-lesson titles, code downloads and exercises live inside the course library you get access to straight after checkout.

16 lessons running 2h 10m in total. Each lesson ships with the finished source files and a short written recap, so you can follow along in your own editor and skim the module again later.

Lesson-by-lesson titles, code downloads and exercises live inside the course library you get access to straight after checkout.

16 lessons running 2h 10m in total. Each lesson ships with the finished source files and a short written recap, so you can follow along in your own editor and skim the module again later.

Lesson-by-lesson titles, code downloads and exercises live inside the course library you get access to straight after checkout.

16 lessons running 2h 6m in total. Each lesson ships with the finished source files and a short written recap, so you can follow along in your own editor and skim the module again later.

Lesson-by-lesson titles, code downloads and exercises live inside the course library you get access to straight after checkout.

8 modules · 131 lessons

17h 30m total length

Requirements

Short list, and deliberately so. If you meet these you can start today.

  • Strong Python, including asynchronous programming
  • Prior experience with tool use or function calling
  • Familiarity with retrieval and evaluation concepts
  • Comfort operating services in production

About this course

An agent is a loop with a budget and a stopping rule. Everything else is detail, but the details are where systems succeed or quietly waste thousands of dollars overnight.

You build progressively harder architectures and measure each one. A single-step tool caller. A ReAct-style reasoning and acting loop. A planner that decomposes a goal before executing. A supervisor coordinating specialist sub-agents. A reflection loop that critiques its own output before returning. For each, you measure success rate, token cost, wall-clock latency and failure modes on the same benchmark tasks, so complexity is only added when the numbers justify it.

Memory is treated as a first-class design problem. Working memory within a task, episodic memory across sessions, semantic memory over a knowledge base, and the compaction strategies that keep a long-running agent inside its context window without losing the constraint it was given twenty steps ago. You will implement retrieval over an agent's own history and see how quickly naive approaches poison the loop.

The hard operational material comes last: safe interruption, human approval gates for consequential actions, replaying a run deterministically from a trace, sandboxing code execution, per-run cost caps, and evaluating an agent on outcomes rather than on the plausibility of its transcript.

Topics covered

Frequently asked questions

Still unsure about something? Write to misteryjj100@gmail.com and a human answers, usually the same working day.

Architectures are built in plain Python first so the mechanics are visible, then compared against LangChain and LangGraph implementations of the same design.

It is demanding. Take the tool use and function calling course first if you have never implemented a tool loop yourself.

A task suite with graders ships with the course, so every architecture you build is scored on the same problems and the comparisons are real.

Checkout is handled on our provider's secure payment page. The moment your payment clears we email your personal access link and access code to the address you used at checkout, and the same link appears in your account library. There is nothing to install and nothing to wait for.

Email misteryjj100@gmail.com within 14 days of your purchase, quote your order number, and we refund the full amount to your original payment method. No form to fill in and no questions about how much of the course you watched.

What students say

No reviews yet

Nobody has reviewed this course yet, so there is no score to show. Buy it, work through it, and your review could be the one that helps the next developer decide.

Browse the catalog

Your instructor

PR

Priya Raman

Applied AI and machine-learning engineer

  • 236 students taught
  • 13 courses published
  • 4.3 instructor rating
  • Machine learning
  • RAG
  • Fine-tuning
  • LLM agents

Priya builds language-model features for a document-heavy SaaS product, which means she has taken retrieval and fine-tuning from a promising notebook to something on call at three in the morning. She teaches the mathematics only where it changes a decision you are about to make, and spends the rest of the time on data quality, evaluation and the cost of an agent that loops. Her courses run on a laptop and a modest API budget, so nobody has to rent a cluster to follow along. She publishes reproducible notebooks alongside every module.

See every course by Priya Raman
$149 USD

One-time payment · lifetime access

The WisdomCharms dispatch

One useful email a week. No fluff, no spam.

New course releases, discount codes before anyone else, and a short, practical breakdown of one technique — a prompt pattern, a C++ idiom, a TypeScript trick — that you can use the same day.

  • Subscriber-only launch pricing
  • Unsubscribe in one click
  • We never sell your address

By subscribing you agree to our Privacy Policy. Questions? Write to misteryjj100@gmail.com.