Deesha Tech Academy
Menu

Deesha AI · Course

DTA-26AvailableAI & Agentic AIAgentsWorkflowsMCPMulti-agent patternsLangGraphPython

Agentic AI Engineering — Python

Build agents that carry multi-step work in Python — with state, plans and boundaries

Fee
₹6,000
Duration
40 guided hours
Mode
Online / Offline
Ask about this course

Designed for

  • Python developers who finished the stage-one course and want systems that act
  • Backend engineers whose teams are being asked "can an agent do this"
  • Teams that need agents inside real services, not notebook demos

Course curriculum

10 progressive modules

Duration: 40 guided hours

  1. Foundation
  2. Intermediate
  3. Advanced
  1. FoundationSessions 1–3

    From AI features to agents

    • The agent loop — goal, decide, act, observe, continue, complete
    • What separates an agent from a workflow, precisely
    • The cost of agency, and when not to pay it

    What you will build

    Three real problems routed to prompt, workflow or agent — each decision defended in writing, most of them not agents, which is the lesson.

    Module 1

Batches

Choose a schedule that works for you

No dates yet

Tell us the schedule that would work

We plan batches around demand. Weekend, morning and intensive formats open when enough people ask for them.

Register your interest

Who teaches this

Learn with experienced practitioners

All trainers and mentors

Each batch is assigned its own trainer from this group, named before you enrol.

  • Vishal Shah

    Vishal Shah

    Founder & Principal Trainer

    Two decades building and teaching commerce, banking and cloud platforms — still writing code

    • Java & Spring Boot microservices
    • TypeScript, React, Angular & Next.js
    • Composable commerce (commercetools)
    Full profile →
  • Shrenik Shah

    Shrenik Shah

    Principal Trainer

    Cloud and AI architect who has upskilled over 5,000 engineers in Java, React, Python and cloud

    • Python — Django, Flask, GenAI & agentic workflows
    • Java & Spring Boot
    • React & Angular, micro-frontend architecture
    Full profile →

Detailed course information

Full course brief

Stage one taught your Python stack to think; this course teaches it to act. The loop comes before the framework: you build a bare agent you can explain line by line, then let LangGraph and friends argue for their complexity against your own baseline — with persistent state, reviewable plans, human approval and boundaries throughout.

Who this is for

You need the stage-one course — AI Application Engineering with Python — or equivalent: working model APIs, tool calling and RAG. The Agent Builder Lab is the two-day on-ramp that precedes this course on the pathway.

Where it leads

The agentic stage of the AI Application Engineer pathway — followed by the AI Reliability Lab and the production stage.

Get batch details

Tell us the schedule that would suit you and we will let you know when a batch opens.

This website does not store or send these details. Your email or WhatsApp app will open with the message ready for you to review and send.

Where this leads

More courses

One subject at a time

Browse the Academy catalogue

Need help deciding?

Ask about the curriculum, delivery options or the next batch.

Talk to Academy
Enquire