Model Online / On-Site
Duration
Modules 4 modules

Course Objective & Scope

Many engineering teams have had AI coding licences for months yet remain stuck at single-line autocomplete and copy-paste chat—and when they try autonomous agent modes, they hit broken builds and unreviewable diffs. This intensive bridge programme takes developers from basic assistant usage to disciplined agentic coding in one cohesive track.

Moving across maturity levels (L1 autocomplete → L2 context-pinned inline edits → L3 planned multi-file changes → L4 closed-loop coding agents), authoring AGENTS.md rules, running Plan-Act-Verify loops and preparing clean PRs are practised hands-on.

Who Should Attend?

  • Software engineers ready to move beyond basic Copilot/Cursor autocomplete to agentic workflows
  • Tech leads establishing a shared AI coding standard across their squad
  • Full-stack, backend, frontend and mobile engineering teams
  • Prerequisite: active software development and Git experience

Key Takeaways

  • Match task complexity to the right interaction mode (inline completion, multi-file edit or CLI agent)
  • Feed precise symbol, type and architectural context to maximise first-pass accuracy
  • Enforce plan approval before multi-file edits to keep architectural control
  • Wire test and linter execution into the agent loop for self-verifying implementation
  • Author a starter AGENTS.md and pre-PR verification checklist for their repository

Curriculum

The Four Maturity Levels of AI-Assisted Coding
  • Contrasting autocomplete, context-pinned edits, multi-file composer and autonomous agents
  • Choosing the right mode for each task to avoid context overhead and broken diffs
Precision Context Pinning and Repository Rules
  • Pinning files, symbols, type definitions and canonical examples
  • Defining architectural guardrails in AGENTS.md and .cursor/rules
Agentic Coding with the Plan-Act-Verify Loop
  • Running read-only discovery and reviewing the implementation plan before code edits
  • Closing the loop with compiler, typechecker and unit-test execution
End-to-End Task Lab and Clean PR Delivery
  • Completing a real feature or bug fix through small Git checkpoints
  • Diff review, security sanity checks and documenting the team workflow standard

Other Courses in This Category

  • Designing Repository Instructions, Rules and AGENTS.md

    Hands-on training on designing modular, path-scoped and testable AGENTS.md, CLAUDE.md, .cursor/rules and .github/copilot-instructions.md files so coding agents consistently follow team architecture and standards.

    AI-Assisted Software Development Corporate
    Live Course
    5 modules
    View
  • Spec-Driven Development (SDD) with Coding Agents

    Training on making structured specifications (SPEC.md, OpenAPI, JSON Schema, TypeSpec, state machines and executable acceptance tests) the primary engineering artifact that drives coding agents deterministically.

    AI-Assisted Software Development Corporate
    Live Course
    5 modules
    View
  • Feature Delivery, Refactoring and Migrations with Coding Agents

    Practical playbook for executing the three core engineering workloads with coding agents: end-to-end multi-file feature delivery, large-scale refactoring and framework/SDK/database migrations combining codemods with agent loops.

    AI-Assisted Software Development Corporate
    Live Course
    5 modules
    View
  • Agentic Testing and Autonomous QA Workflows

    Hands-on training in autonomous QA workflows using Playwright MCP, browser-driving testing agents, self-healing E2E tests and autonomous exploratory testing across UI and API user journeys.

    AI-Assisted Software Development Corporate
    Live Course
    5 modules
    View
  • AI-Assisted Code Review and Human Approval Workflows

    Solving the PR review bottleneck in AI-accelerated teams through stacked diffs, low-noise AI review bots, evidence-backed PR templates and risk-tiered human approval workflows.

    AI-Assisted Software Development Corporate
    Live Course
    5 modules
    View
  • Sandboxing, Tool Permissions and Safe Execution for Coding Agents

    Advanced training on running autonomous coding agents safely on developer machines and servers using container/microVM sandboxes, filesystem/network egress controls, least-privilege MCP permissions and secret isolation.

    AI-Assisted Software Development Corporate
    Live Course
    5 modules
    View

Get in touch