Agentic Software EngineeringOverviewConceptual modelCurriculumLearning outcomesAssessmentTooling referenceGlossary
The curriculum

19 modules, one discipline

Each module addresses one part of equipping or verifying the agent, or one part of the rhythm that connects them. Open any module for its full treatment and the capability a graduate gains from it.

01

Part 1. The discipline

Modules 1–5

Establishes the discipline, the human role, mental models of agents, the anatomy of an agentic workflow, and the typology of agentic development environments.

01

What is Agentic Software Engineering?

A discipline shift, not a tooling shift.

Agentic software engineering is a discipline shift rather than a tooling shift, situated within the historical arc from ENIAC patch cables to vibe coding.

arrow_forward
02

The human role

What erodes and what compounds.

What remains irreducibly human in agentic engineering, and what erodes as models improve.

arrow_forward
03

Mental models of agents

How agents actually work.

How agents actually work, at the level of precision a practitioner needs to direct them effectively.

arrow_forward
04

The anatomy of an agentic workflow

From coding to engineering.

A workflow decomposed into its parts: intent, specification, context, plan, execution, verification, audit trail.

arrow_forward
05

The ADE typology

Tooling and permissions.

How ADEs are built and what that means for the human’s responsibility: the six-pillar architecture and three categories.

arrow_forward
02

Part 2. The environment

Modules 6–9

Project conception, web application architecture, interface design and documentation, and the architecture of intelligence in software.

06

Intent and the discipline of project conception

Framing before the agent is invoked.

Most failed agentic work fails before any agent is invoked, because the problem was framed wrongly or not at all.

arrow_forward
07

Modern web application architecture

Enough of each layer to direct an agent.

Frontend, backend, database, deployment, and the request cycle — a mental-model course rather than a programming course.

arrow_forward
08

Interface design and app documentation

Legibility as a control mechanism.

The unifying concept is legibility — the property that makes a system readable and evaluable by someone who did not build it.

arrow_forward
09

Cognified products and the architecture of intelligence

Agent economics.

The distinction between using AI to build software and building software that contains AI — and the economics of inference.

arrow_forward
03

Part 3. The engineering

Modules 10–17

Specifications and the co-evolution spiral, context engineering, safety and recovery, verification before trust, multi-agent decomposition and orchestration, review, and security and governance.

10

Specifications and co-evolution spiral

The deliverable of human work.

In agentic engineering, code is the agent’s output but the specification is the human’s — and the specification is never final.

arrow_forward
11

Context engineering

The agent’s briefing.

Deliberately curating what the agent encounters in its context window, rather than treating context as incidental.

arrow_forward
12

Safety, control, and recovery

Working at speed without catastrophic loss.

Agents act on the world through tools, and tools have real consequences. Safety infrastructure is a prerequisite.

arrow_forward
13

Verification before trust

Every agent output is a hypothesis until checked.

Verification is the structural commitment that makes agentic engineering trustworthy rather than merely fast.

arrow_forward
14

Multi-agent decomposition and orchestration

Implicit versus explicit orchestration.

Every modern ADE already runs multi-agent orchestration internally; the distinction that matters is implicit versus explicit.

arrow_forward
15

Designing multi-agent workflows

Coordination as a design discipline.

From the patterns of Module 14 to their application as a design discipline.

arrow_forward
16

Review and quality

Legacy onboarding.

Code review is the skill of reading and evaluating code one did not write — and in agentic engineering, all significant code is foreign code.

arrow_forward
17

Security, risk, and governance in agentic systems

Architectural problems, not features.

Security and governance in agentic systems are architectural problems. They cannot be added as features after the fact.

arrow_forward
04

Part 4. The market

Modules 18–19

Entrepreneurship and the labour market in the age of AI coding.

18

Entrepreneurship in the age of AI coding

Two mechanisms that compound each other.

How startup economics have changed through cost compression and cognification.

arrow_forward
19

Job search in the age of AI coding

How the developer role is restructuring.

How the developer role is restructuring, and how ASE skills position a practitioner in that change.

arrow_forward
See the learning outcomesarrow_forward

Mikael Alemu Gorsky

Mikael Alemu is an educator and researcher, and the author of two programs: Agentic Software Engineering, on building software with AI agents, and Building AI-Native Agentic Systems, on building software that thinks.

He teaches at the Holon Institute of Technology, near Tel Aviv, where Agentic Software Engineering runs as a credit-bearing course. He is an educator and researcher.

Nine published works, 76 citations. A 350-page textbook under contract with a major academic publisher.

Teaching and programs

Agentic Software Engineering — program, preprint and textbook

The discipline of structured, auditable human-agent workflows for building software. The human frames, specifies and judges. The agent executes. Nineteen modules in four parts, built on a running project called Tribunal, a web application in which agents argue opposing sides of a case and a judge agent decides. Taught for credit at the Holon Institute of Technology.

Agentic Software Engineering curriculum

Building AI-Native Agentic Systems — program, paper and book in writing

How to build systems that hold a language model as a working component, and treat that component as what it is: stochastic, slow and metered. Fourteen modules in four parts, about seventy hours. The running project is the Observatory, a news agency that watches sources, selects what matters and publishes on a cadence.

Research and analytics

Publications — journals and proceedings

Nine works, 76 citations. Research on artificial intelligence in education, with Ilya Levin and Alexei Semenov.

The AI Pravda — LinkedIn newsletter

Critical analysis of artificial intelligence and its effect on work and society. 5,500+ subscribers. The complete archive of 103 issues (2023–2026) is published in full at mgorsky.net/theaipravda.

Subscribe to The AI Pravda on LinkedIn

Pro bono

AI for seniors — free workshop

Helping older adults use everyday AI tools. Delivered to Russian-speaking communities in Israel.

For older adults, artificial intelligence is about preserving quality of life, maintaining autonomy, and sustaining the feeling of independence that defines dignified aging. For seniors who have emigrated, AI becomes a bridge: it can translate documents, explain official letters, help compose emails in the local language, and guide users through government websites. The workshop has been delivered to Russian-speaking communities in Israel, where participants — many of them in their 70s and 80s — discovered that AI could help them read Hebrew documents and communicate with Israeli institutions.

Startup competitions — unpaid time

Judging and mentoring early-stage ventures. Helping teams clarify their value proposition, assess technical feasibility, and prepare for the realities of scaling an AI product.

AC/VC LinkedIn group — community

A group for developers and students working with coding agents. The community shares practical insights, code examples, tool comparisons, and honest assessments of what works in production.

Join the AC/VC LinkedIn group

Recent

Important Links