DEV Community

Kowshik Jallipalli profile picture

Kowshik Jallipalli

Building at the edge of agentic systems, LLM infrastructure, and autonomous workflows. I write deep-dives — no fluff, just the hard parts nobody documents well.

Education

Fast.ai

Pronouns

he, him

Work

Agent Systems Developer

Teaching Agents My Actual Engineering Workflow: Secure Adaptive Orchestration

Teaching Agents My Actual Engineering Workflow: Secure Adaptive Orchestration

Comments
5 min read
The Sandboxed "Ralph Wiggum" Loop: Securely Letting Agents Fix Code Until Tests Pass

The Sandboxed "Ralph Wiggum" Loop: Securely Letting Agents Fix Code Until Tests Pass

1
Comments
4 min read
Shipping Agent Skills Like NPM Packages: Secure, Reusable Expertise

Shipping Agent Skills Like NPM Packages: Secure, Reusable Expertise

2
Comments
5 min read
From Black Box to Traceable Swarm: OpenTelemetry Patterns for AI Agents

From Black Box to Traceable Swarm: OpenTelemetry Patterns for AI Agents

3
Comments
4 min read
Agentic CI: How I Test AI Workers Like Services (Securely)

Agentic CI: How I Test AI Workers Like Services (Securely)

1
Comments
5 min read
Letting Agents Run the First Draft of My SDLC (Safely)

Letting Agents Run the First Draft of My SDLC (Safely)

1
Comments
4 min read
Objective-Validation Protocol: Designing Audited Human Checkpoints in Agent Workflows

Objective-Validation Protocol: Designing Audited Human Checkpoints in Agent Workflows

Comments
5 min read
Agentic CI: How I Test and Gate AI Agents Before They Touch Real Users

Agentic CI: How I Test and Gate AI Agents Before They Touch Real Users

Comments
4 min read
Watching Your Agents Work: Logs, Traces, and Metrics for Reliable AI Workflows

Watching Your Agents Work: Logs, Traces, and Metrics for Reliable AI Workflows

2
Comments
4 min read
Hardening AI Features: Practical Defense against Prompt Injection and Risky Tools

Hardening AI Features: Practical Defense against Prompt Injection and Risky Tools

1
Comments
5 min read
AI‑Assisted Frontend: Safely Refactoring React Components with Code Agents

AI‑Assisted Frontend: Safely Refactoring React Components with Code Agents

1
Comments
4 min read
Safe Text-to-SQL: Giving an Agent Database Access Without Dropping Tables or Leaking PII

Safe Text-to-SQL: Giving an Agent Database Access Without Dropping Tables or Leaking PII

2
Comments
5 min read
Giving Your AI Memory That Doesn't Suck: Implementing Semantic Caching and Conversation State

Giving Your AI Memory That Doesn't Suck: Implementing Semantic Caching and Conversation State

Comments
4 min read
Claude Code Agent Teams: Hierarchical Orchestration

Claude Code Agent Teams: Hierarchical Orchestration

Comments 1
1 min read
🚀 Why Perplexity's New "Computer" Just Changed the AI Agent Game

🚀 Why Perplexity's New "Computer" Just Changed the AI Agent Game

Comments
3 min read
I’m open-sourcing a protocol to automate neighborhood fairness. Here is the logic.

I’m open-sourcing a protocol to automate neighborhood fairness. Here is the logic.

Comments
3 min read
loading...