Skip to content
PROGRAM 37 · TEAM TRAINING

AI & Data for Software Teams

Ship faster with AI pair programming, without shipping bugs.

Important: AI-generated code must be reviewed, tested and checked for security before it is merged. Company and client code goes only into tools the company has approved.

8 sessions3 modules4 hands-on projects3 days · 9 am–5 pmCertificate on completion
CHOOSE A FORMAT
Request a proposalSee the curriculum

Who this course is for

  • Software engineers, developers and team leads
  • QA engineers and testers
  • DevOps, support and technical documentation staff
  • Product teams in software houses, outsourcing firms, fintech, e-commerce and bank IT

What your team will be able to do

  • Use AI coding assistants on a real codebase with review discipline
  • Generate tests, documentation and code explanations in a fraction of the time
  • Review pull requests and spot security issues with AI support
  • Deploy four working automations for your own engineering team
How it runs

3 days at your office, 8 sessions

Three sessions a day plus a hands-on build lab every afternoon. Day 3 ends with capstone presentations.

Day 1

9:00 am – 5:00 pm

AI chatbots and coding assistants

9:00–10:30S1Prompt engineering for software teams
10:30Tea break
10:45–12:15S2AI pair programming & testing
12:15Lunch & prayer
1:00–2:30S3Code review, documentation & clients
2:45–4:30LABBuild lab: an AI-built feature with tests on your repo
4:30–5:00Q&A and day recap

Day 2

9:00 am – 5:00 pm

Analysis, then the first two builds

9:00–10:30S4Formulas & engineering data cleaning
10:30Tea break
10:45–12:15S5Engineering analytics & delivery insight
12:15Lunch & prayer
1:00–2:30S6Projects 01 & 02: Assistant and alerts
2:45–4:30LABBuild lab: delivery dashboard, assistant and alerts
4:30–5:00Q&A and day recap

Day 3

9:00 am – 5:00 pm

Last two builds and the capstone

9:00–10:30S7Project 03: Change & release approvals
10:30Tea break
10:45–12:15S8Project 04: Requirement & bug extraction
12:15Lunch & prayer
1:00–3:00LABCapstone build clinic
3:15–4:30LABCapstone presentations
4:30–5:00Certificates and next steps
Group: 10–40 people from one organisationSame content and projects in both formatsBangla delivery with English technical termsEvery session ends with a deliverable
Curriculum

8 sessions, one build in each

3 modules · 8 sessions · 4 hands-on projects

PART 1AI Chatbots for Software WorkSessions 1–3

Chatbot Landscape & Tool Selection

  • Gemini, ChatGPT, Claude, Copilot and DeepSeek: strengths for software work (code generation, code explanation, long technical documents, test cases)
  • Free vs paid tiers; a workflow that needs no international payment card
  • Bangla vs English output quality; when to draft in English and translate
  • Which tool for a long document, which for a formula, which for a polished letter

Prompt Engineering Fundamentals

  • What a prompt is; why the same question gives different answers
  • The four-part structure: role, context, task, output format
  • Role prompting: act as a senior developer, code reviewer, QA engineer or technical writer
  • Controlling output: length, tone, language, table or bullet format

Advanced Prompting Techniques

  • Few-shot prompting: teaching the model with examples of your own software work
  • Step-by-step reasoning for multi-part tasks such as tracing a bug across three services or estimating a feature for a client proposal
  • Constraint prompting: what to include, what to exclude, what to never assume
  • Chained prompts: breaking a new feature (requirement → design → code → tests → review → release note) into a sequence of smaller steps

Iteration & Prompt Library Building

  • Why the second prompt matters more than the first; refining instead of restarting
  • Diagnosing a bad output: vague instruction, missing context or wrong tool
  • Building reusable prompt templates for repeated software tasks
  • Testing a prompt before it goes into daily use

Data Privacy & Verification Discipline (Core)

  • What must never be pasted: API keys, secrets and connection strings, client source code without approval, customer data and logs with personal details, unreleased client contracts
  • Anonymising data before prompting; safe vs unsafe software use cases
  • Hallucination awareness; verifying every figure, date, name and legal reference
  • The verification rule: AI drafts, a person checks before anything leaves the building
DELIVERABLEa personal prompt library of 10 templates for your repeated software tasks.
PART 2Software Data Analysis in Excel & Google SheetsSessions 4–5
PART 3Applied Projects: AI Assistants & AutomationSessions 6–8
Applied projects

Four automations, running in your organisation

01Session 6

Engineering Standards Assistant

New developers, QA and support engineers get answers from your coding standards, API docs and runbooks, with the section cited.

  1. INStandards, API docs & runbooks
  2. AIGrounded Gemini assistant
  3. OUTAnswer with the section cited
Built with Google AI Studio
02Session 6

Licence, Certificate & Release Alerts

SSL, domain, licence and contract renewals, key rotation and release deadlines checked daily, with alerts 30, 15 and 7 days ahead.

  1. INLicence & release tracker
  2. RUNDaily Make scenario
  3. OUTAlert to the responsible owner
Built with Make · Sheets · Gmail
03Session 7

Change & Release Approval Workflow

Change requests with a rollback plan routed to the tech lead, high-risk changes to a second approver, and freeze days enforced.

  1. INChange request form
  2. RULESApproval routing script
  3. OUTApproved change on the calendar
Built with Apps Script · Forms
04Session 8

Requirement & Bug Report Extraction

Emailed bug reports and requirement documents become draft tickets with severity suggested, duplicates checked and rows ready to import to Jira.

  1. INBug reports & requirement docs
  2. AIGemini structured extraction
  3. OUTDraft tickets ready for Jira
Built with Gemini API · Drive

Capstone presentation

Each person presents one automation built for their own workplace.

Day 3 afternoon
Applied across every session

Responsible & Ethical AI in Software

Fairness & Non-Discrimination

  • Where bias enters software decisions: data, wording, criteria and past patterns
  • Proxy discrimination: address, age, gender or background inferred indirectly

Privacy & Data Protection

  • Data minimisation: collect only what the decision requires
  • Retention and deletion of user, customer and client data

Code Quality, Security & Intellectual Property

  • Client code and data handled only under the client's agreed terms
  • Open-source licences respected in AI-suggested code

Accountability & Human Oversight

  • Human-in-the-loop by design: AI recommends, a named person decides
  • Who owns an AI-assisted decision when it is challenged

Workforce Impact & Your AI Use Policy

  • Talking to software teams about AI without triggering job-loss fear
  • Reskilling and role redesign as AI absorbs routine work
Outcomes

By the end, your team can

  • Choose the right AI tool and write prompts that work first time
  • Maintain a prompt library covering your repeated software tasks
  • Use AI coding assistants on a real codebase with review discipline
  • Generate tests, documentation and release notes with AI help
  • Track delivery, quality and effort with a clean engineering dashboard
  • Build and deploy automations with Make, Apps Script and the Gemini API
  • Apply fairness, transparency and privacy to every AI-assisted decision

And leaves with

A team AI coding workflow and PR review checklist
Documentation and test generation templates
An engineering delivery dashboard
A grounded engineering standards assistant your colleagues can use
A licence, certificate & release alert engine that reaches the right owner
Four deployed automations running in your own organisation
A written AI use policy for your own engineering team

Tools your team will use

Chatbots
ChatGPTGeminiClaudeCopilotDeepSeek
Content
CanvaGammaCapCutGoogle Slides
Data
Microsoft ExcelGoogle SheetsPower Query
Workspace
GmailCalendarMeetFormsDrive
Automation & AI builds
MakeGoogle AI StudioApps ScriptGemini API
Software tools
Claude CodeGitHub CopilotCursorGitHub or GitLabJira

What participants need

  • A laptop with Excel and a Google account
  • Working knowledge of at least one programming language and Git
  • One real work file to practise on from Session 2
  • No coding background required; free tiers only

How your team will learn

  • build-along classes (you work while the trainer works)
  • practise on your own workplace file, not dummy data
  • every session ends with a deliverable
  • Bangla delivery with English technical terms
  • recordings, prompt library and setup guides
  • certificate after capstone submission
Request a proposal

Bring this program to your engineering team

Tell us about your team. We reply within one working day with a plan built around your own documents and workflows.

  1. 1 · A short discovery call with your engineering lead
  2. 2 · We tailor examples to your masked files
  3. 3 · Offline at your office, or online live classes
Chat on WhatsApp
Request a proposal