WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
Coffee With Developers • Apr 27, 2026

Building Agents Securely at Scale - Alfonso Graziano

Alfonso Graziano

Alfonso Graziano warns that deploying AI agents blindly is a security nightmare. Stop relying on simplistic tutorials. Learn to implement hard guardrails and continuous evaluations for production-ready LLMs.

Pause
Mute Enter Fullscreen
#1 about 2 min

Building client-facing AI agents for engineering teams

Practical implementations of AI agents focus primarily on serving internal engineering teams and end customers.

#2 about 3 min

Moving beyond simple prompts to reliable agentic systems

Constructing robust AI agents requires recognizing that natural language interfaces must handle unpredictable user queries effectively.

#3 about 2 min

Why simplistic AI agent tutorials fail in production

Most introductory guides ignore critical components like automated evaluations, golden datasets, and continuous user feedback loops.

#4 about 3 min

Implementing security guardrails and OWASP principles for agents

Applying appropriate access controls and addressing new vulnerabilities like indirect prompt injection protects non-deterministic applications.

#5 about 2 min

Essential resources for understanding agentic design and evaluation

Foundational knowledge of large language models and structured frameworks aids in building easily testable AI systems.

#6 about 4 min

Evolving developer roles into tech leads for AI agents

Software engineers must review generated outputs and confidently guide parallel agent workflows instead of blindly trusting automated code.

#7 about 4 min

Risks of granting AI agents complete system permissions

Running experimental agents on personal machines exposes sensitive credentials and local files to unexpected behaviors.

#8 about 3 min

Mitigating hallucinations and sycophancy in tool-calling agents

Restricting tool access and applying framework-level guardrails helps prevent deployed agents from inventing fictitious functions.

#9 about 6 min

Building golden datasets and feedback loops for reliability

Gathering real user interactions and expert annotations forms the foundation for continuously evaluating and improving agent performance.

#10 about 2 min

Refining system prompts to eliminate specific failure modes

Adjusting domain-specific instructions within the prompt configuration significantly boosts evaluation scores and inherently prevents common errors.

#11 about 3 min

Practical enterprise use cases for automating complex workflows

Deploying intelligent agents for complex data search and reproducing repetitive development tasks safely accelerates team productivity.

#12 about 5 min

Learning resources and community engagement for AI engineers

Specialized courses, upcoming literature, and developer conferences offer structured approaches for mastering advanced software integration capabilities.

Matching moments

8:54 min

Preserving engineering fundamentals in agentic development

Chris Heilmann Chris Heilmann +1 · LIVE

2:06 min

Rethinking team structures around AI agent capabilities

Mike Mike · World Congress 2025

4:15 min

Security integration and AI skepticism in developer tooling

Chris Heilmann Chris Heilmann +2 · LIVE

4:37 min

Transitioning to a hybrid human and agent workforce

Thomas Dohmke Thomas Dohmke · World Congress 2025

1:10 min

Identifying emerging security vulnerabilities in generative AI agents

Alejandro Saucedo Alejandro Saucedo · World Congress 2025

3:45 min

Fusing developer experience and platform engineering for agentic SDLC

Julia Kordick Julia Kordick · World Congress 2026 Europe

More from Coffee With Developers

Using Agents to Curate the Content You See Online - Dan Gish thumbnail
12:47
about 1 month ago

Using Agents to Curate the Content You See Online - Dan Gish

Dan Gish

AI Vector Search at Scale - Ewa Szyszka - Ewa Szyszka thumbnail
11:14
about 1 month ago

AI Vector Search at Scale - Ewa Szyszka - Ewa Szyszka

Ewa Szyszka

What is Cross-Origin Storage - Thomas Steiner thumbnail
34:51
about 1 month ago

What is Cross-Origin Storage - Thomas Steiner

Thomas Steiner

Women in AI - Nalini Garg thumbnail
42:19
about 1 month ago

Women in AI - Nalini Garg

Nalini Garg

Agents and People Dynamics in Shared Chats - Sam Liu thumbnail
37:41
about 1 month ago

Agents and People Dynamics in Shared Chats - Sam Liu

Sam Liu

Why Token Reduction Isn’t Cost Reduction - Dave Anderson & Sarel Weinberger, PhD. thumbnail
41:09
about 2 months ago

Why Token Reduction Isn’t Cost Reduction - Dave Anderson & Sarel Weinberger, PhD.

Dave Anderson, Sarel Weinberger, Phd

Related videos

The day the chatbot asked for sudo thumbnail
27:48
World Congress 2026 Europe • 3 months ago

The day the chatbot asked for sudo

Alex Olivier

The AI Agent Path to Prod: Building for Reliability thumbnail
30:48
World Congress 2025 • about 1 year ago

The AI Agent Path to Prod: Building for Reliability

Max Tkacz

AI Agents & Agentic AI thumbnail
26:53
Europe 2026 Virtual • 3 months ago

AI Agents & Agentic AI

Xavier Sala Presas

Running AI at Scale: The Secret Ingredients thumbnail
30:04
World Congress 2026 Europe • 3 months ago

Running AI at Scale: The Secret Ingredients

Boris Hecker, Max Tschochohei, Peter Kürpick, Tomislav Tipurić

The State of GenAI & Machine Learning in 2025 thumbnail
26:47
World Congress 2025 • about 1 year ago

The State of GenAI & Machine Learning in 2025

Alejandro Saucedo

Beyond Chatbots: How to build Agentic AI systems thumbnail
24:22
World Congress 2025 • about 1 year ago

Beyond Chatbots: How to build Agentic AI systems

Philipp Schmid

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.