Skip to content
SamplePreview build: teacher profiles, ratings, reviews and lesson counts are sample data.
Log inFind a tutor

Teacher since October 2025

Hiroshi Tanabe

I teach how AI agents are built: the loop, the tools, the memory, and when a plain workflow is the better choice

9

tutors built

4.5Sample

average from 18 reviews

310Sample

lessons taught by their tutors

About Hiroshi

I build and teach the inner workings of AI agents. Most of my working life has been spent on backend systems, so I approach agents the way I approach any distributed system: what runs, in what order, what can fail, and what it costs. I like to start every topic with a drawing of the loop on a whiteboard and a small, boring example that works before we add anything clever. I am openly sceptical of complexity for its own sake. If a fixed sequence of steps solves your problem, I will tell you to build that instead of an agent, and I will show you why. My students leave with a mental model they can apply to any framework.

Knows about

  • agent architecture
  • tool calling loops
  • tool design
  • planning and decomposition
  • context and memory management
  • multi agent systems
  • long running tasks
  • cost and latency control

Tutors by Hiroshi

9 tutors

The Tool Calling Loop, Explained Step by Step

The Tool Calling Loop, Explained Step by Step

See exactly what happens, message by message, when a model calls a tool and gets the result backBeginnerAI agents4.5(4)83 lessonsSampleHiroshi TanabeFreeAgent or Workflow? Choosing the Right Design

Agent or Workflow? Choosing the Right Design

Decide in ten minutes whether your idea needs an agent, a fixed workflow or a single good promptBeginnerAI agents4.7(3)75 lessonsSampleHiroshi Tanabe$4Designing Tools an Agent Can Actually Use

Designing Tools an Agent Can Actually Use

Write tool names, descriptions, inputs and error messages that make agents choose and call tools correctlyIntermediateAI agents4.7(3)52 lessonsSampleHiroshi Tanabe$7Agent Cost and Latency Control

Agent Cost and Latency Control

Find where your agent spends money and time, then cut both without losing qualityIntermediateAI agents4.0(3)43 lessonsSampleHiroshi Tanabe$8Long Running Agent Tasks That Survive Failure

Long Running Agent Tasks That Survive Failure

Build agent tasks that run for hours, checkpoint progress and resume cleanly after crashes or timeoutsAdvancedAI agents4.7(3)35 lessonsSampleHiroshi Tanabe$13Planning and Task Decomposition for Agents

Planning and Task Decomposition for Agents

Teach agents to break big goals into checkable steps, revise the plan and know when they are doneIntermediateAI agents4.5(2)22 lessonsSampleHiroshi Tanabe$7Agent Concepts for Product and Project Leads

Agent Concepts for Product and Project Leads

Understand agents well enough to scope, plan and review an agent project with your engineersAll levelsAI agentsNewHiroshi Tanabe$5Agent Memory and Context Management

Agent Memory and Context Management

Keep long agent runs focused by managing what goes into the context window and what lives outside itAdvancedAI agentsNewHiroshi Tanabe$11Multi Agent Systems: When They Pay Off

Multi Agent Systems: When They Pay Off

Judge when splitting work across several agents helps, and when it only multiplies cost and confusionAdvancedAI agentsNewHiroshi Tanabe$12

Recent reviews

What students said about Hiroshi's tutors.