Home › AI Training in Mumbai › Claude Code

Claude Code · Engineering teams

Claude Code training in Mumbai for engineering teams

Hands-on Claude Code training in Mumbai for product teams, GCCs and start-ups, on your own repositories: plan, test, review and ship smaller, safer changes faster.

  • Hands-on
    sessions
  • Built on your
    real work
  • On-site across
    Mumbai & MMR
★ Core habits
✳

Claude Code on your repo

Terminal and IDE

  • CLAUDE.md and plan mode
  • Test-first changes
Plan the change
Write failing tests
Open a small PR
★ Most requested
✳

Extend Claude Code

Commands, subagents, hooks

  • Skills and MCP servers
  • Automation in CI
/new-status command
Review subagent
Hook: run tests
● For tech leads
✳

Team policy

Security and review standards

  • Permissions and secrets
  • Reviewable pull requests
Permission settings
Secrets check
Review checklist
Plan modeSubagents · HooksMCP servers

Tell me about your engineering team and your stack

Your information is safe, we don’t spam or send emails unless necessary

Teams at these organisations have trained with Hitesh

Tata MotorsRelianceAdani GroupMahindraKotakHULFlipkartHitachiHPESiemensSamsungMarks & SpencerThyssenKruppGodrejTata MotorsRelianceAdani GroupMahindraKotakHULFlipkartHitachiHPESiemensSamsungMarks & SpencerThyssenKruppGodrej
MicrosoftGooglePfizerTata Tele ServicesCNH IndustrialSony PicturesLGTimes of IndiaAl GhurairLandmark GroupTransworld GroupHPMorning StarCapitaLandMicrosoftGooglePfizerTata Tele ServicesCNH IndustrialSony PicturesLGTimes of IndiaAl GhurairLandmark GroupTransworld GroupHPMorning StarCapitaLand
Why train on Claude Code

The tool is easy to install and hard to use well

Most engineers can get Claude Code running in minutes. The difference between a team that gets a small speed-up and a team that changes how it ships is in the habits: how tasks are scoped, how context is given, when to plan before coding, how changes are reviewed, and which actions the tool may take without asking.

Mumbai's engineering teams are a mixed group: global capability centres in Powai, Navi Mumbai and the western suburbs working under their parent company's security rules, product companies and fintechs moving fast in Lower Parel and BKC, and IT services teams delivering for clients in many stacks. The training adapts to each, but the core is the same: practical patterns that hold up on a real codebase.

Teams that get most from it

  • Product engineering and platform teams
  • GCC teams with strict security policies
  • Fintech and SaaS start-ups
  • QA and test automation engineers
  • Data and ML engineers
  • Engineering managers and tech leads
The curriculum

Eight modules on your own repositories

A one-day workshop covers modules 1 to 5. A two-day bootcamp covers all eight, with a capstone on a real ticket from your backlog.

MODULE 01

Set-up and mental model

Installing Claude Code, plans and API access, permission modes, and how the agent loop actually works.

MODULE 02

Context that works

CLAUDE.md files, project conventions, pointing the agent at the right files, and keeping context small.

MODULE 03

Plan, then code

Plan mode, breaking work into reviewable steps, and writing tickets the agent can execute well.

MODULE 04

Tests and review

Test-first prompts, running the suite, reading diffs critically, and small, reviewable pull requests.

MODULE 05

Debugging and legacy code

Explaining unfamiliar code, tracing bugs, and safe refactoring of old modules.

MODULE 06

Extending Claude Code

Custom slash commands, subagents, hooks, Skills and MCP servers for your internal tools.

MODULE 07

Automation and CI

Headless runs, scripted tasks and using Claude Code in CI pipelines with the right guardrails.

MODULE 08

Security and governance

Secrets, permission settings, prompt injection from files and web pages, and a team policy for AI-written code.

How a session runs

Real tickets, real repositories

Before

Repo and rules

We agree which repositories and tickets to use, and your security rules for AI tools.

Morning

Core patterns

Set-up, CLAUDE.md, plan mode and test-first work on a warm-up task.

Midday

Your backlog

Each pair takes a real ticket from your backlog through plan, code, test and review.

Afternoon

Extend

A custom command or subagent for one repetitive task in your team's workflow.

End

Team policy

A one-page agreement on how the team will use Claude Code and review its output.

Day 30

Retro

What changed in cycle time and review load, and what to adjust.

Who attends

Tracks for every role in the engineering team

ENGINEERS

Developers

The full hands-on workshop on your own codebase.

LEADS

Tech leads and EMs

Review standards, team policy, measuring impact and coaching the team.

QA AND DATA

Test and data engineers

Test generation, data pipelines and notebook-to-production work.

LEADERSHIP

CTOs and engineering heads

A briefing on productivity, security and rollout across teams.

Formats

ONE DAY

Team workshop

Modules 1 to 5, on-site at your Mumbai office.

TWO DAYS

Bootcamp

All eight modules with a backlog capstone.

FOUR WEEKS

Adoption programme

A kick-off workshop plus weekly clinics on real work.

ONLINE

Distributed teams

For teams split across Mumbai, Pune, Bengaluru and abroad.

Participants who complete the exercises receive a certificate of completion.

Related tools

Claude Code, Codex, Copilot and agents

Teams often ask how Claude Code compares with other AI coding tools. The honest answer is that the habits matter more than the tool: scoping tasks well, giving the right context, keeping changes reviewable and testing everything. Those habits transfer.

If your company has standardised on OpenAI, see Codex training in Mumbai. If you are building agents beyond coding, see agentic AI training in Mumbai. For the non-engineering side of Claude, see the Claude AI workshop and Claude Cowork training.

I'm a Mumbai-based corporate AI trainer, and the author of Generative AI 360°. I've trained 2,00,000+ professionals from 600+ organisations, and I work across Claude, ChatGPT, Copilot, agentic AI and LLM app-building.

Before the session

  • Claude plan or API access for each person
  • Claude Code installed and signed in
  • A repository and tickets you are happy to use
  • Your security rules for AI tools
  • A tech lead to own the team policy
Hitesh Motwani, corporate AI trainer in Mumbai
🏢600+ companies trained📖Author, Generative AI 360°
Meet your trainer

Hitesh Motwani

Corporate AI trainer · Founder, Skillopedia · Mumbai

Mumbai-based corporate AI trainer with 17+ years in training. Leadership teams at Tata Motors, Flipkart and Hitachi, builders at HPE and CNH Industrial, and industry programmes for Adani Group, Marks & Spencer and ThyssenKrupp.

2,00,000+professionals trained
600+companies
16+countries
3,000+training sessions
60+keynotes
4.8/5average rating
  • Author, Generative AI 360°
  • Visiting faculty, K J Somaiya
  • Taught at IIMs & University of London
  • Creator of TAGS_C
  • Mentor, 91 Springboard & WeWork
CMOs at IIM BangaloreDigital transformation for chief marketing officers
Morning StarGenerative AI training for the team
CapitaLand, BengaluruCorporate training programme
KeynotesInforma Middle East, Tech Asia, HR summits
In their words

What participants say about Hitesh

He made sure that every platform he spoke about was taught in detail with live examples. Hitesh has an eye for detail, very helpful and patient with everybody. He made the class environment very friendly and interactive.
HHetal ParekhTraining participant
Hitesh knows his subject really well. His understanding and eye for detail is impeccable. I think every person should attend Hitesh Motwani’s program and any corporate can immensely benefit from his knowledge.
SSangeet KumarCEO, SHK Ventures
Hitesh has helped our organization tremendously by providing us the right strategy and right path to execute digital projects. His method of training is so simple and easy to understand that even non-digital natives like us could understand.
MMr. HansTourism board of an international organisation
A worked example

One ticket, start to finish, the way the training teaches it

An illustrative walk-through of the core habit the workshop builds. The details change with your stack; the shape does not.

The ticket

A payments team needs to add a new refund status to an existing service, update the API response, and make sure the reconciliation report picks it up. Three files are obvious, two are not.

The habit

  1. Context first. The repository has a CLAUDE.md that explains the service layout, test commands and the team's conventions, so the engineer doesn't repeat them in every prompt.
  2. Plan before code. In plan mode, Claude Code reads the relevant files and proposes the change, including the two non-obvious files: a serializer and the report query. The engineer corrects one assumption before any code is written.
  3. Tests first. The engineer asks for failing tests that describe the new status, runs them, then asks for the implementation.
  4. Small diffs. The change is split into two commits that a reviewer can read in five minutes each.
  5. Review it like a colleague's code. The engineer reads every line, asks Claude Code to explain one choice, and rejects an unnecessary refactor it slipped in.
  6. Make it repeatable. The team saves a custom slash command for adding a new status end-to-end, so the next one starts from the same checklist.

The point is not that the tool wrote the code. It is that the engineer stayed in control of scope, tests and review, and the team captured the pattern for next time.

What usually changes after the training

  • Tickets are written so an agent can execute them, which also helps human engineers
  • Pull requests get smaller and better tested, so review load goes down, not up
  • Repetitive work such as tests, migrations and documentation moves to the tool
  • The team has a written policy on what Claude Code may do without asking
  • Engineering managers can see where the time savings actually show up
Questions

Claude Code training in Mumbai: questions

What is Claude Code?

Claude Code is Anthropic's agentic coding tool. It runs in the terminal and in IDEs, reads a codebase, plans and edits code, runs commands and tests, and can be extended with custom commands, subagents, hooks and MCP servers.

Who should attend Claude Code training?

Software engineers, tech leads, QA and data engineers, and engineering managers. A shorter briefing is available for CTOs and engineering heads.

Do you train on our own codebase?

Yes, where your security rules allow it. Otherwise we use a realistic sample repository in your stack. Most exercises are real tickets from your backlog.

Is it safe to use Claude Code on company code?

It can be, with the right settings and policy. The training covers permission modes, secrets, prompt injection risks and a team policy for AI-written code. Your security team should approve the plan and settings you use.

Which Claude plan do we need?

Claude Code works with paid Claude plans and with API access. The right choice depends on team size and usage, which we look at on the scoping call.

Can you run the training on-site in Mumbai?

Yes. Sessions run at your office anywhere in Mumbai, including Powai, Andheri, BKC, Lower Parel and Navi Mumbai, or live online for distributed teams.

How is this different from Codex or GitHub Copilot training?

The habits are similar, the tools differ. This programme is built on Claude Code's own features, such as CLAUDE.md, plan mode, subagents, hooks and MCP. Codex training is available separately.

What does Claude Code training cost?

It depends on team size, format and customisation. You get a quote after a free scoping call. Invoicing is through Skillopedia LLP with GST.

Plan Claude Code training for your Mumbai team

Share your team size, languages and frameworks, where your office is, and whether you already have Claude plans or API access. Prefer to talk first? Book a free call.

Your information is safe. We don’t spam or send emails unless necessary.

INDIA

Based in Mumbai. Engagements are contracted through Skillopedia LLP, with an office at 91 Springboard, BKC. Contact details →

Scroll to Top