INTERMEDIATE · 8 MODULES · 64 LESSONS

The AI Coding Tools Landscape

Place any AI coding tool on the map, test it on your own tasks, and pick your team's tools with criteria that last.

For you if
You already use a coding agent and can't tell whether each week's new release is better.
By the end
You'll know how to separate the model from the tool, compare options by cost per accepted task, and record the team's decision.
You need
Experience with a coding agent, Git, and Python 3.12. No paid subscription required.
  1. 01The Map and the Cutoff Date8 LESSONS
    1. Introduction: A Map That Changes Every Month
    2. The Surfaces of an AI Coding Tool
    3. Model and Harness: Why the Same Model Performs Differently
    4. 2026 in Six Moves
    5. Reading Primary Sources: Docs, Changelog and Pricing
    6. How They Charge: Seat, Credits, Pool and API Price
    7. Data and Privacy as a Buying Criterion
    8. Project: The Dated Tool Card
  2. 02Agents inside the editor8 LESSONS
    1. Introduction: the bench tool
    2. Cursor
    3. GitHub Copilot in the editor
    4. JetBrains: Junie and AI Assistant
    5. Zed and the Agent Client Protocol
    6. IDEs built around the agent: Antigravity and Devin Desktop
    7. Comparing two editor agents on the same repo
    8. Project: comparative dossier of two editor agents
  3. 03Agents in the Terminal8 LESSONS
    1. Introduction: The Hand Tool
    2. The Common Anatomy: Permissions, Sandbox, and Non-Interactive Mode
    3. Codex CLI
    4. Copilot CLI and Cursor CLI
    5. Claude Code on the Map
    6. The Successors: Antigravity CLI and Kiro CLI
    7. Scripts and CI: Non-Interactive Mode Compared
    8. Project: Your Team's CLI Matrix
  4. 04Open source and your own model8 LESSONS
    1. Introduction: tools you can open and repair
    2. What open source gives you and what it doesn't
    3. Cline
    4. OpenCode
    5. Aider and working commit by commit
    6. Foundations and projects that die
    7. Local models and BYOK: when they're worth it
    8. Project: exit plan
  5. 05Cloud, Background, and Pull Request Agents8 LESSONS
    1. Introduction: the house-call service
    2. Copilot cloud agent and third-party agents on GitHub
    3. Codex cloud
    4. Cursor cloud agents and Bugbot
    5. Managed PR review: what it does and what it doesn't
    6. The cost you don't see: minutes, credits, and retries
    7. Permissions and risks of the unsupervised agent
    8. Project: the cloud agent policy
  6. 06Standards that make you portable8 LESSONS
    1. Introduction: the workshop's standard measures
    2. AGENTS.md: who reads it and how
    3. One source, many tools
    4. MCP: the shared tool layer
    5. ACP: any agent in any editor
    6. Portable specs: Spec Kit and Kiro specs
    7. What is not portable
    8. Project: the portable repo
  7. 07Evaluating without opinions8 LESSONS
    1. Introduction: the shop's test bench
    2. What public benchmarks measure
    3. Productivity evidence and its scope
    4. Your task set
    5. Rubric and metrics
    6. Cost per accepted task
    7. Designing a team pilot
    8. Project: the evaluation harness
  8. 08Final project: the team toolkit8 LESSONS
    1. Introduction: from the toolbox to the shop agreement
    2. Team requirements
    3. The shortlist
    4. The weighted matrix and its sensitivity
    5. One tool or several
    6. The monthly cost of the toolkit
    7. Keeping the decision alive
    8. Project: the toolkit decision record
Reviews

What students say

These reviews are from enrolled students who completed at least 50% of the course. We moderate reviews only on content grounds (spam, offensive language, personal data), never for being critical or negative.

No approved reviews yet.

Be the first to share your experience!

SEC. 06 · THE STUDIO

Why this studio exists

For decades, building software belonged to technical profiles with years of training, and getting a digital product into the real world took companies months or years. No-code and AI have narrowed that gap, but the knowledge is still held by a few.

Tech Benders exists to open that knowledge up, so business teams and non-technical teams can put their ideas into production with the right technical decisions behind them. AI does what you ask of it. Without a technical base, what it builds may not scale with your company’s ecosystem, and its costs can run away over time.

The team knows the pains of large organizations and the speed at which they have to move. It brings solution architecture, data engineering, product built end to end from back end to front end, and daily work with AI. Software that solves what you need in days, not months, with the cost of AI kept in check.

Founders

The studioRead about Tech Benders →

Write to ushi@techbenders.io

Made with Wislab