Agentic Coding & Harness Engineering

The full EB-1 … EB-11 topic catalog for custom team programs and workshops. Browse every module and topic; combine ad hoc for your organisation.

Topics are combined ad hoc for corporate programs and workshops — there is no fixed public duration. Tell us your goals and we design the track.

Discuss a custom program

All modules

EB-1

Context Engineering

The discipline of providing the right information, tools, and memory, in the right format, before the model reasons. If the model is the engine, context is the fuel mixture — and getting it wrong is the single most common cause of unreliable agents.

19 topics

EB-2

Harness Engineering Core

The harness is the body around the model's brain — the orchestration loop, the tool layer, state, permissions, and every configuration surface that turns a chat model into an autonomous engineering agent. In current practice the harness has become the critical infrastructure layer, and the same model can perform very differently depending on the harness it runs in.

16 topics

EB-3

Agent Architecture & SDLC

How agents are structured and where they fit into the software development lifecycle.

5 topics

EB-4

Tool Use & Execution Environments

Giving an agent the ability to act — and containing the consequences when it does.

7 topics

EB-5

Memory, State & Continuity

How agents remember within a task, across tasks, and across sessions.

5 topics

EB-6

Evaluation, Failures & Tuning

Agents fail differently from traditional software — usually silently — so measuring them requires a discipline of its own. *Reference module for the structured format: every topic below is split into **Theory**, **Use cases**, and **Practical exercises** (concept-check → applied), and the block closes with a put-into-practice **capstone**.*

7 topics

EB-7

Multi-Agent Coordination

When one agent is not enough, how do several agents divide work, share context, and produce a coherent result?

5 topics

EB-8

Guardrails & Accountability

The less a human watches, the more the guardrails must carry the load. This module is the safety and governance counterweight to the autonomy taught everywhere else in the course.

5 topics

EB-9

UX/UI Design of AI Interfaces

*(Advanced track only.)* The interface is the accountability layer between human intent and autonomous action. An agent without a well-designed supervision surface is a black box, regardless of how good its internals are.

8 topics

EB-10

Compound Engineering & the Dark Factory

Two opposing answers to the same question: what does engineering become when agents write the code? **Compound engineering** keeps the human at the high-leverage ends of the loop and makes the system measurably smarter every cycle. The **dark factory** removes the human from the deployment path entirely and lets specs flow to production in the dark. This module is the synthesis of the whole course — it composes the harness (EB-2), evaluation (EB-6), guardrails and audit (EB-8), and memory (EB-5) into a working methodology and a working pipeline, and it closes the human-in-the-loop thread that runs through EB-1, EB-7, EB-8, and EB-9.

13 topics

EB-11

Dynamic Workflows, Loop Engineering & Verification Engineering

The 2026 frontier of how agentic coding work is *driven* and *trusted*. Three closely linked ideas: the harness can now write itself per task (**dynamic workflows**); the unit of instruction is shifting from the one-shot prompt to a self-running cycle with a goal and a stop condition (**loop engineering**); and the bottleneck moves from generating code to proving it is correct (**verification engineering**). This module is the moving edge of the course — it operationalises the harness (EB-2), multi-agent coordination (EB-7), evaluation (EB-6), and the dark factory (EB-10) into the practices teams are adopting right now. Because the tooling here changes monthly, every topic is taught concept-first so it survives the next release.

9 topics

Teaching methodology

How EasySpecs structures delivery — concept before tool, spiral depth, failure-first labs.

Read teaching methodology →