tecnovy AI Suite

Code Review with AI

Here a pull request review splits into two unequal parts. The agents take the first pass: one each reads the diff for security, tests, architecture and style, measured against your own criteria, and their findings arrive bundled in the pull request. The judgement stays with a person: weighing findings, balancing trade-offs, saying yes or no. From the first agent to a running pipeline, the workflow takes shape in this workshop.

Attendance certificate4.8/5 on ProvenExpert

What this module delivers.

By the end of tecnovy's Code Review with AI, a review workflow runs in your sample repository, built step by step: your criteria as checkable rules, specialised agents, merged findings. For tech leads, senior developers and DevOps.

How the training runs

Method: Step-by-step build in a sample repository, from one agent to pipeline
Basis: tecnovy curriculum, checked against Anthropic and GitHub docs (November 2026)
Outcome: tecnovy certificate of participation at 80% attendance, no examination

Dates & booking

Choose a date that fits

No public dates are scheduled yet.

New dates are published regularly. Join the waitlist or plan an in-house course for your team.

Request in-house training

Fit

Who this module is designed for

Typical roles

As a tech lead or senior developer you review many pull requests and want agents to take the first pass.
You own code quality, security or the platform for a team that works with AI coding tools.
You work in DevOps and want to move checks into the CI/CD pipeline.

Prerequisites

No prerequisites

You can start right away. What you need: hands-on experience with Claude Code or GitHub Copilot, confident use of Git and pull requests plus a CI/CD platform.

Consider instead GitHub Copilot Advanced For teams that want to set up Copilot's built-in code review through a ruleset, as part of a wider Copilot rollout with instruction files and policies.

Curriculum

Code Review with AI in Detail

Five parts lead from your review criteria, through specialised agents and their orchestration, to integration into pull requests and day-to-day operation. You build the workflow step by step in a sample repository, and by the end it runs.

01What makes a good review

Before an agent checks anything, you decide what gets checked.

Review goals: correctness, security, maintainability, architecture
Where AI is strong in a review and where it goes wrong
Writing your own review criteria as checkable rules

02Specialised review agents

Each agent gets exactly one angle on the pull request.

Defining agents for security, tests, architecture and style
Giving each agent a role, context and a checklist
Reducing false positives

03Orchestration

Several separate findings become one result that reviewers can read quickly.

Running agents in parallel or in sequence
Merging, weighting and de-duplicating findings
A result that takes minutes to read

04Integration into pull requests and CI/CD

The workflow starts on its own and reports where the team works.

Starting the review workflow automatically on new pull requests
Comments on the pull request and status checks
How it works with branch rules and human approval

05Operation and improvement

You measure cost, run time and benefit and assess security risks.

Measuring cost, run time and benefit
Improving the agents from team feedback
Security: access rights, secrets, outside contributions

Outcome

What you will be able to do afterwards

01
You write your review criteria as rules that an AI agent can check.
02
You build review agents for security, tests, architecture and style, each with its own role, context and checklist.
03
You recognise where AI is reliable in a review and where it goes wrong, and cut down false positives.
04
You run several agents in parallel or in sequence and merge their findings, weighted and without duplicates.
05
You start the workflow automatically on new pull requests, with comments and status checks.
06
You decide how the workflow works alongside branch rules and human approval.
07
You measure cost, run time and benefit, and improve the agents from your team's feedback.

tecnovy Teilnahmezertifikat

Confirms your attendance and the curriculum covered in the training. Issued by tecnovy, shareable on LinkedIn.

Open the Certificate Showroom tecnovy →

Offer scope

What is included

Included

Templates for review agents and pipeline configurationAgent definitions with checklists and a pipeline configuration that you adapt to your own repositories.

Why tecnovy

What you get on top with us

No Slideshow, Hands-On!

Promised: no PowerPoint marathon. We work in groups, tie theory to practice, and you get real project examples from our experienced trainers plus the exchange with like-minded people.

Certificate Showroom

Get your certificate of participation and, if you have one, add your exam certificate from E-Learning. Fully automated, beautifully designed. Just for you, only at tecnovy.

Flexible Date Change

If you are not able to attend the course, you can rebook your training free of charge up to one week before the start of the training.

Attend Twice, Pay Once

You are welcome to attend the training online again within a year as a refresher.

Learn from Experts

We always guarantee you the use of didactically and methodically first-class qualified trainers who draw their knowledge from training experience as well as professional practical and project experience.

FAQs

Frequently asked questions

01Does the workflow replace human reviews?

A person still gives the approval in tecnovy's Code Review with AI workshop; the agents deliver a structured first pass. Anthropic itself says of its own review service that a review with no findings does not mean the code is error-free or secure (as of November 2026).

02Why build your own workflow when ready-made AI reviews exist?

Because the ready-made services leave little room: Anthropic's Code Review is available only on Team and Enterprise plans with repositories on GitHub and chooses its models itself, and Copilot code review is GitHub's own mix of models and prompts, which you steer through files such as copilot-instructions.md (as of November 2026). In tecnovy's Code Review with AI workshop you build a workflow with your own criteria and agents that runs in your pipeline.

03Which tools and access do the exercises need?

tecnovy's Code Review with AI workshop works with Claude Code or GitHub Copilot and a CI/CD platform such as GitHub Actions. Claude Code needs a Pro, Max, Ultra, Team or Enterprise subscription, a Claude Console account, or access through Amazon Bedrock, Google Cloud or Microsoft Foundry, not the free plan; a pipeline needs its own credentials, such as an API key from the Claude Console (as of November 2026).

04Does this work with GitLab or Azure DevOps?

The principles from tecnovy's Code Review with AI workshop carry over, because the workflow rests on criteria, agents and a pipeline. For GitLab there is a Claude Code integration with GitLab CI/CD that GitLab maintains and that, according to Anthropic, is still in beta (as of November 2026).

05What does running an AI review cost?

It depends on the number and size of pull requests and on how many agents run: each run uses tokens at the AI provider and time on the CI runners, and Copilot code review consumes AI credits. Anthropic names a maximum number of turns per run, job timeouts and fewer parallel runs as limits (as of November 2026); in tecnovy's Code Review with AI workshop you measure the cost and run time of your workflow.

06What security questions does an AI review in the pipeline raise?

Three are central in tecnovy's Code Review with AI workshop: which rights the agents get in the repository, where keys are kept as secrets, and what happens with outside contributions. On public repositories GitHub withholds secrets from runs triggered by fork pull requests, and by default the Claude Code GitHub Action starts on issues and pull requests only for people with write access (as of November 2026).

07Do I need to take an advanced course first?

It is not required, but tecnovy's Code Review with AI workshop assumes hands-on experience with Claude Code or GitHub Copilot, ideally at the level of Claude Code Advanced or GitHub Copilot Advanced. You also need Git, pull requests and a CI/CD platform.

08Does the workshop end with an examination?

tecnovy's Code Review with AI workshop ends with the tecnovy certificate of participation, which you receive at 80% attendance, not with an examination. Neither Anthropic nor GitHub awards a certification for it.

09What comes after the workshop?

After Code Review with AI, tecnovy's workshop MCP Servers in the Coding Environment connects further systems such as ticket systems and documentation to Claude Code and GitHub Copilot through the Model Context Protocol (MCP).

What does your training at tecnovy look like?

AI Code ReviewCode Review with AI

No dates yet

We will let you know as soon as the next date is scheduled.