veda.ng

AI Agents as Automators

AI agents don't just follow rules. they reason, plan, and adapt. Learn to use Claude, Antigravity, and GPT as autonomous workflow executors that handle ambiguity and make decisions.

The AI Agent Loop

Observe, Think, Act, Learn: the cycle that replaces rigid rule-based automation

1
Observe

Read current context: user request, data from APIs, error messages, previous results

2
Think

Plan the next action. The LLM reasons about tools to call, order of operations, potential failures

3
Act

Execute the plan: call an API, run a query, send a message, write a file, browse a page

4
Learn

Evaluate the result. Did it work? If not, adjust the plan and loop again with new context

Antigravity
File read/write
Terminal commands
MCP servers
Web browsing
Image generation
Claude Code
Code editing
Git operations
MCP servers
File system
Web search
GPT + Tools
Function calling
Code interpreter
Web browsing
DALL-E
File upload

Traditional automation follows rigid rules: "if X, then Y." AI agents break this limitation. They observe context, reason about what to do, take action using tools, and learn from the result. This makes them perfect for automations that require judgment, natural language understanding, or handling edge cases.

If you've taken the Agentic Web course, you understand the theory. This module is about putting agents to work as practical automators.

The operational difference between a script and an agent is adaptability. A script that processes job listings breaks when the API changes its response format. An agent reads the new format, adjusts its parsing logic, and continues processing. This strength is why agents are replacing brittle rule-based automation in production workflows. The tradeoff is cost and latency: every agent action involves an LLM inference call. The decision framework is straightforward: use agents for tasks that require reasoning, and use scripts for tasks that are purely mechanical.

Tool Calling in Practice

How an agent decomposes a natural language request into API calls

User Prompt

"Find all open engineering jobs at Stripe and add them to my spreadsheet"

Agent Reasoning

I need to: (1) call the Stripe jobs API, (2) filter for engineering roles, (3) format the data, (4) write to Google Sheets

Tool Call 1

fetch("https://api.stripe.com/jobs") → Returns 47 positions

Tool Call 2

filter(jobs, department="Engineering") → 12 matches

Tool Call 3

sheets.update("Jobs!A2:E13", formattedData) → 12 rows written

Result

"Done. Added 12 engineering positions from Stripe to your Jobs spreadsheet."