EP165: AI Agent versus MCP

✂️Cut your QA cycles down to minutes with QA Wolf (Sponsored)

If slow QA processes bottleneck you or your software engineering team and you’re releasing slower because of it — you need to check out QA Wolf.

QA Wolf’s AI-native service supports web and mobile apps, delivering 80% automated test coverage in weeks and helping teams ship 5x faster by reducing QA cycles to minutes.

QA Wolf takes testing off your plate. They can get you:

• Unlimited parallel test runs for mobile and web apps

• 24-hour maintenance and on-demand test creation

• Human-verified bug reports sent directly to your team

• Zero flakes guarantee

The benefit? No more manual E2E testing. No more slow QA cycles. No more bugs reaching production.

With QA Wolf, Drata’s team of 80+ engineers achieved 4x more test cases and 86% faster QA cycles.

---

This week’s system design refresher:

• AI Agent versus MCP

• How does HTTPS work?

• How to Learn Kubernetes?

• Top 6 most commonly used Server Types

• Amazon Key Architecture with Third Party Integration

• Hiring Now: Top AI Startups and AI Roles

• SPONSOR US

---

AI Agent versus MCP

An AI agent is a software program that can interact with its environment, gather data, and use that data to achieve predetermined goals. AI agents can choose the best actions to perform to meet those goals.

Key characteristics of AI agents are as follows:

1. An agent can perform autonomous actions without constant human intervention. Also, they can have a human in the loop to maintain control.

2. Agents have a memory to store individual preferences and allow for personalization. It can also store knowledge. An LLM can undertake information processing and decision-making functions.

3. Agents must be able to perceive and process the information available from their environment.

Model Context Protocol (MCP) is a new system introduced by Anthropic to make AI models more powerful.

It is an open standard that allows AI models (like Claude) to connect to databases, APIs, file systems, and other tools without needing custom code for each new integration.

MCP follows a client-server model with 3 key components:

1. Host: AI applications like Claude

2. MCP Client: Component inside an AI model (like Claude) that allows it to communicate with MCP servers

3. MCP Server: Middleman that connects an AI model to an external system

Over to you: Have you used AI Agents or MCP?

---

Stop Software Erosion with Smarter Static Code Analysis (Sponsored)

This webinar, "Using Static Code Analysis Correctly", explores how static code analysis can be a powerful ally in maintaining code quality, preventing software erosion, and ensuring long-term maintainability.

Whether you're working in automotive, medical, embedded systems, or other safety-critical industries, you'll gain practical insights into spotting design drift, managing architectural consistency, and avoiding common pitfalls in C and C++ codebases.

In this 40-minute webinar, we break down real-world challenges and demonstrate how thoughtful use of static analysis can help you build more robust, reliable systems from the inside out.

---

How does HTTPS work?

Hypertext Transfer Protocol Secure (HTTPS) is an extension of the Hypertext Transfer Protocol (HTTP.) HTTPS transmits encrypted data using Transport Layer Security (TLS.) If the data is hijacked online, all the hijacker gets is binary code.

How is the data encrypted and decrypted?

Step 1 - The client (browser) and the server establish a TCP connection.

Step 2 - The client sends a “client hello” to the server. The message contains a set of necessary encryption algorithms (cipher suites) and the latest TLS version it can support. The server responds with a “server hello” so the browser knows whether it can support the algorithms and TLS version.

The server then sends the SSL certificate to the client. The certificate contains the public key, host name, expiry dates, etc. The client validates the certificate.

Step 3 - After validating the SSL certificate, the client generates a session key and encrypts it using the public key. The server receives the encrypted session key and decrypts it with the private key.

Step 4 - Now that both the client and the server hold the same session key (symmetric encryption), the encrypted data is transmitted in a secure bi-directional channel.

Why does HTTPS switch to symmetric encryption during data transmission? There are two main reasons:

1. Security: The asymmetric encryption goes only one way. This means that if the server tries to send the encrypted data back to the client, anyone can decrypt the data using the public key.

2. Server resources: The asymmetric encryption adds quite a lot of mathematical overhead. It is not suitable for data transmissions in long sessions.

Over to you: how much performance overhead does HTTPS add, compared to HTTP?

---

How to Learn Kubernetes?

Kubernetes is an open-source container orchestration platform that automates the deployment, scaling, and management of containerized applications.

1. Core Concepts and Architecture
   This includes topics like What is Kubernetes, Cluster, Node, Pod, Control Plane, and Worker Node.

2. Workloads and Controllers
   This includes topics like Pod, ReplicaSet, Deployment, StatefulSet, Job, CronJob, Labels, Selectors, and Autoscalers (HPA, VPA, and Cluster Autoscaler).

3. Networking and Service Management
   This involves topics like Cluster Networking Model, Services (ClusterIP, NodePort, LoadBalancer), Ingress, and Network Policies.

4. Storage and Configuration
   This includes topics like Volumes, PersistentVolume, PersistentVolumeClaim, Storage Classes, ConfigMap, Secret, and Stateful Applications.

5. Security & Access Control
   This involves topics like RBAC, Service Accounts, Secrets Management, Admission Controllers, Pod Security, TLS, and API Access.

6. Tools, Observability & Ecosystem
   This includes topics like kubectl, YAML files, Helm Charts, CI/CD Integration, GitOps, Logging, Monitoring, and EKS.

Over to you: What else will you add to the list for learning Kubernetes?

---

Top 6 most commonly used Server Types

1. Web Server:
   Hosts websites and delivers web content to clients over the internet

2. Mail Server:
   Handles the sending, receiving, and routing of emails across networks

3. DNS Server:
   Translates domain names (like bytebytego. com) into IP addresses, enabling users to access websites by their human-readable names.

4. Proxy Server:
   An intermediary server that acts as a gateway between clients and other servers, providing additional security, performance optimization, and anonymity.

5. FTP Server:
   Facilitates the transfer of files between clients and servers over a network

6. Origin Server:
   Hosts central source of content that is cached and distributed to edge servers for faster delivery to end users.

Over to you: Which type of server do you find most crucial in your online experience?

---

Amazon Key Architecture with Third Party Integration

Amazon Key is a REALLY convenient way to have your packages securely delivered right inside your garage or multifamily property.

We sat down with Kaushik Mani and Vijayakrishnan Nagarajan to learn how a small side project evolved into a global platform: now powering over 100 million secure door unlocks every year.

This story is packed with valuable lessons on:

• Scaling IoT infrastructure across thousands of locations

• Building resilient, field-ready hardware for real-world environments

• Overcoming cold starts and connectivity challenges

• Designing a microservices architecture for global expansion

• Creating a secure, partner-ready platform to support third-party integrations

• And many more

Dive into the full newsletter here.

---

Hiring Now: Top AI Startups and AI Roles

This Week’s High-Impact Roles at Fast-Growing AI Startups

• Software Engineer, AI Platform at Pano AI

• Senior Software Engineer (AI Products) at Mutiny

• Senior Software Engineer, Financial Infrastructure at Vercel

• Senior Software Engineer at Otter.ai

• Senior Software Engineer, ML Infrastructure, Predictive Planner at Waymo

• Senior Full Stack Engineer at Gatik

• Senior / Staff Software Engineer, Simulation Platform at Waabi

• Senior Embedded Software Engineer at Nuro

High Salary SWE Roles this week

• Engineering Manager, ML Performance and Scaling at Anthropic

• Director of Engineering, Data Platform at WorkAsPro

• Engineering Manager - Trust and Safety at TikTok

• Senior Full Stack Software Engineer at Netflix

• VP, GTM Engineering at Linkedin

• Staff Backend Engineer, Invoicing Products at Stripe

• VP, Sales Engineering, Northeast Division at Comcast

• Senior Staff Software Engineer, iOS at Salesforce

Today’s latest ML positions - hiring now!

• Principal Machine Learning Services Engineer at Adobe

• Staff Software Engineer, Machine Learning at Tinder

• Senior Engineering Manager - Machine Learning at Uber

• Senior Machine Learning Software Engineer at Waymo

• Staff Machine Learning Engineer (ML Portfolio) at Affirm

• Machine Learning Engineer at Amazon

• Senior Machine Learning Engineer at Yahoo

• Principal Data Scientist - Machine Learning Engineering at Atlassian

---

SPONSOR US

Get your product in front of more than 1,000,000 tech professionals.

Our newsletter puts your products and services directly in front of an audience that matters - hundreds of thousands of engineering leaders and senior engineers - who have influence over significant tech decisions and big purchases.

Space Fills Up Fast - Reserve Today

Ad spots typically sell out about 4 weeks in advance. To ensure your ad reaches this influential audience, reserve your space now by emailing hi@bytebytego.com.