Deesha Tech Academy
Menu

Deesha AI · SkillLab

WorkshopRuns on requestAI & Agentic AIAgentsTool callingMCPPython

Agent Builder Lab

Two hands-on days building your first real agent — a goal, tools, boundaries and the ability to act — starting from use-case discovery, because the expensive mistake in agentic AI is building an agent for a problem that needed a workflow. You leave with a working tool-using agent and a reusable design template.

Designed for

  • Developers who understand APIs and basic LLM integration
  • Teams being asked "can an agent do this" and needing a real answer
  • Engineers who built a chatbot and want it to actually do things
  • Technical leads scoping their first agentic project
Fee
₹2,700
Duration
2 days · 16 hours
Each day
09:00 – 17:00
Mode
Offline / Online
Request a schedule

The 2 days, hour by hour

10 hands-on sessions — every one ends in a thing

Day 1

09:00 – 17:00

Discover and design

5 sessions

09:00 – 10:15

Draw the line between agent and everything else

AI vs GenAI vs automation vs agentic, the agent loop, honest definitions

Takeaway Four real systems classified correctly — including the "agent" that is actually a cron job.

10:30 – 11:45

Hunt for agentic use cases in real work

use-case discovery, scoring value vs risk, the toolkit

Takeaway Your own work mined for candidates and scored — a ranked shortlist, not a brainstorm.

12:00 – 13:00

Decide what each problem actually needs

prompt vs automation vs workflow vs agent, cost of agency

Takeaway Each shortlisted case routed to the cheapest thing that solves it — most are not agents, and that is the lesson.

14:00 – 15:15

Design the agent before building it

goal and success criteria, tool boundaries, approval points

Takeaway A one-page agent design — goal, tools, boundaries, approvals, success criteria — reviewed by the room.

15:30 – 17:00

Stand up the skeleton

the agent loop implemented, first tool, first trace

Takeaway The loop running with one tool — and its first trace read line by line.

Day 2

09:00 – 17:00

Build and constrain

5 sessions

09:00 – 10:15

Give it real tools

tool selection, schemas the model uses well, MCP tools

Takeaway The agent choosing correctly between three tools — because the schemas made the choice easy.

10:30 – 11:45

Add state and constraints

task state, budgets and stop conditions, runaway prevention

Takeaway A budget and stop condition that end a runaway loop — triggered on purpose, stopped on cue.

12:00 – 13:00

Put a human where it matters

approval gates, consequential actions, escalation

Takeaway The agent pausing for approval before the irreversible step — and proceeding cleanly after it.

14:00 – 15:15

Test against failure, not just success

failure scenarios, tool errors, wrong-tool recovery

Takeaway The agent surviving a failing tool and a misleading input — behaviour verified, not hoped for.

15:30 – 17:00

Template it for the next one

the design template, demo, what a second agent would reuse

Takeaway Your agent demoed, and the reusable design template that makes the second agent a day's work.

By the end of day 2, you are holding

A working single agent that chooses and uses tools within explicit boundaries, its traces readable end to end — plus the use-case scoring toolkit and agent design template you will reuse on every agentic project after this one.

Request a schedule

Agent Builder Lab

Runs on request, for individuals and for teams.

How will you join?

Laptop ready with the prerequisites?

Opens WhatsApp with a message naming this workshop. We confirm your seat and payment by reply — this website stores nothing.

Who runs it

Practitioners, in the room with you

All trainers and mentors

Each workshop names its trainer before you book.

  • 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 →

Running this for a team?

We deliver SkillLabs on site for institutions and engineering teams.

Talk to Deesha

₹2,700

2 days · 16 hours

Request a schedule