But don’t worry, they still need developers to keep them running smoothly, especially when they fall back on human or legacy comms.

Platforms like AWS and Infobip, which announced their strategic partnership at this year’s Shift Conference in Zadar, orchestrate these digital personalities – keeping them compliant, connected, and (mostly) well-behaved in the wild world of business messaging.

Let’s see how.

We’re rewriting the future of customer interaction – right now

“We’re in an interesting moment in tech – three mega-trends are colliding to shake up marketing, sales, support, and more,” says Ivan Ostojic, Chief Business Officer at Infobip.

First, people love chatting – not just with friends, but with businesses too. ChatGPT, Anthropic, and friends have trained them to expect smart, fast answers. Three years ago, only some people preferred chatting with businesses – today, 7 out of 10 do.

Second, app fatigue is real. Even though apps are exhausting, people actually open and click on messaging – 90%+ open rates! Businesses are turning chat into super apps, packing in ads, rich media, payments, calendars, and almost everything an app can do, with way less friction.

Third, agentic AI is everywhere – chatbots, human helpers, personalized marketing, creative tools, and even fraud detection.

Put it together: on the demand side, people want seamless, instant interactions. On the supply side, messaging + AI make massive automation possible. And that equals huge opportunities for businesses – and for developers like you who’ll be building it.

Voice APIs are transforming AI experiences

So, messaging + AI are set to transform marketing, commerce, and support. Developers will build smart agents everywhere – banking, retail, travel… even sports and entertainment, where fans jump in first.

Talking about sports, Ostojic shared an example of a project built by Infobip, AWS and partners for Formula 1: a digital twin of driver Ollie Bearman. Fans can message him on WhatsApp and get interactive replies, including voice responses cloned from his real voice.

Real-time APIs even deliver live updates, like current race results. Fans can text or voice-message and get realistic answers, making it highly interactive and engaging.

And keep in mind this tech isn’t just for F1 – imagine Santa sending kids personalized voice messages at Christmas, or customer support replying instantly in the voice of a brand ambassador. The sky’s the limit.

How do all these agents play nice together?

All of these trends – chat-happy consumers, messaging turning into super apps, and AI taking real actions – set the stage for a bigger question: how do all these agents work together?

That question was at the heart of a panel discussion at the Shift Conference with Ervin Jagatic (Product Director, Infobip) and Andrei Shakirin (Senior Solutions Architect, AWS). “A couple of years ago, generative AI was the buzz. Now it’s agents – the hype is similar, but we started with conversational AI,” says Jagetic.

AI used to just generate tone or products. Now it takes real actions – making purchases, sending hyper-personalized messages, and more. With many agents coming in the next 4–5 years, integration is key. That’s why Infobip is teaming up with AWS to build an agent marketplace where AI agents can communicate and connect.

MCP or agent-to-agent protocol?

Sometimes agents need to talk to each other to fetch data or execute actions. There are two main ways to do this – MCP (Model Context Protocol) or an agent-to-agent protocol, Shakirin explains:

MCP works like this: the MCP server has tools – a function with a description and arguments. The MCP client, built into the agent, reports these tools to the LLM. The model decides if it needs a tool, sends a structured response back, the agent calls the tool on the server with arguments, and returns the result.

Essentially, the model tells the agent: “I need to call something to get data or execute an action.”

Agent-to-agent communication can also run through MCP, where the server might be an API, database, or another agent – you can chain calls between them. MCP was invented by Anthropic two years ago, but Google’s newer agent-to-agent protocol adds “agent cards” for discovering capabilities, async tasks with state tracking, and negotiating data formats like images or video.

When to use which?

For simple, synchronous, text-based chat where MCP is already set up, stick with MCP. For async communication, multiple calls, richer data, or negotiation, use the agent-to-agent protocol. Both have their place. At Infobip, we love MCP (especially in Java), but we support both – says Jagetic.

Don’t forget DEVELOPERS

Remember, developers are front and center – working with clients, partners, and more. So, is there a career path here?

Andrei Shakirin, says yes:

By 2026, we’ll see tons of verticalized agents – finance, banking, healthcare – built for specific use cases. Building them means mastering workflows, tasks, and integrations. It’s a whole new frontier and a huge business opportunity.

And for developers who want to get into this space, Shakirin says you need much more than just LLM communication. You need to:

• Store communication history.
• Use retrieval-augmented generation for additional data.
• Integrate MCP so models can call tools or execute actions.
• Ensure security, traceability, and monitoring.

These are common building blocks across apps, so frameworks like LangChain, LangGraph, and AutoGen save you from reinventing the wheel.

Most are Python-based, but Java frameworks like Spring AI matter too – agents are moving from prototypes to enterprise systems, where Java and Kotlin dominate. Deployment is easy: DIY on AWS or use Amazon Bedrock Agent Framework, which handles runtime, memory, auth, scaling, and multi-framework support. Developers can self-manage or let Bedrock do the heavy lifting.

To see MCP in action, check out Infobip’s MCP servers for communication APIs, or use the open-source Infobip OpenAPI MCP framework to expose your own APIs to agents. 

Want to know what else was discussed at Infobip Shift at Zadar in 2025? Find out here!

The post 3 Mega Trends Shaping How Developers Build AI Agents – Especially VoiceAI appeared first on ShiftMag.

Over three exciting days at the Krešimir Ćosić Hall in Višnjik, Zadar, approximately 5.000 attendees of the Infobip Shift Conference will dive into a dynamic lineup of lectures, panels, workshops, and networking events – all focused on today’s hottest topics.

From AI and software development to cybersecurity, engineering leadership, and startup culture, there’s something for every forward-thinking professional.

With six parallel stages and a variety of thematic tracks, the program is designed to spotlight the key trends shaping the future of software development.

Learn about Agent Experience (AX) from the term creator himself

This year’s edition once again features top names from the global IT scene, including Matt Biilmann Christensen, co-founder and CEO of Netlify – a platform at the forefront of modern web application development, serving over a billion unique monthly visitors.

Matt is one of the world’s foremost advocates of a new concept called Agent Experience (AX), which enables collaboration between developers and AI agents in software creation. Biilmann states:

Agent experience will become just as important in the future as user experience (UX) has been in past decades.

According to him, the rise of AI capable of writing code represents a moment akin to Gutenberg’s printing press, a technology that once made exclusive knowledge accessible to everyone.

Just as literacy transformed society, software literacy is poised for explosive growth as AI removes technical barriers. We’re shifting from a world where only a few could develop software to one where almost anyone can.

Audience favorites are back – including Debbie O’Brien and Kristijan “Kitze” Ristovski

Alongside Matt, the Shift Conference will feature Medhat Dawoud, senior software engineer at Miro – a global platform for online collaboration and visual project management used by over 60 million people worldwide.

Returning to Shift is Debbie O’Brien, a long-time Microsoft manager specializing in developer tools. O’Brien is well-known in the developer community for her work on the Playwright testing framework and other tools that significantly impact developers’ daily workflows.

Also making a comeback to the stage are:

• Kristijan “Kitze” Ristovski, founder of Sizzy and a longtime crowd favorite at Shift,
• Vitaly Friedman, editor-in-chief of Smashing Magazine and a prominent figure in the global front-end community,
• Harry Roberts, internationally recognized web performance expert and author of CSS Wizardry.

Startup program, EXPO zone, and after-parties

Special attention will once again focus on the Startup Tribe stage, featuring investor panels and pitch competitions for emerging tech startups.

Additionally, the EXPO hall will showcase the latest innovations from leading tech companies, while a variety of side events, after-parties, and networking activities promise an unforgettable experience for all attendees – both on and off stage.

Find out more details at the conference’s official website, and stay tuned to our event-related content!

The post Infobip Shift 2025 Takes Over Zadar with Tech Stars from Netlify, Miro & Microsoft appeared first on ShiftMag.

Meet Branded Caller from Infobip.

Unlike regular caller ID that might flash a name (or worse, just a number), Branded Caller puts verified, visual brand info front and center. Think: the company’s logo, a recognizable display name, and even a quick note about why they’re calling. No more mystery calls.

For developers, this isn’t just a nice-to-have feature – it’s a serious upgrade to the voice call experience.

By integrating Branded Caller, you’re helping businesses increase answer rates, build trust, and fight fraud, all while working inside a secure and standardized ecosystem built for interoperability and long-term use.

Why developers should care about branded calling?

With call fraud on the rise in the U.S., Branded Caller has stepped up by using cryptographic security under the STIR/SHAKEN protocol to verify caller numbers and significantly reduce spoofing and robocalls.

As Ryan McQueary (Manager of Voice Engineering, Infobip) explains, STIR/SHAKEN is a set of industry standards that enhance call verification by cryptographically signing voice calls – a critical step for ensuring call authenticity.

Here’s how it works from a technical standpoint:

When a call is placed, the originating service provider sends a verification request to an Authentication Service (AS). This request includes key details like the originating and receiving phone numbers, timestamp, and an important metric called the trust level or Attestation Level.

This trust level indicates how reliable the call is:

• Both the network and caller are trusted.
• The network is trusted, but the caller is not.
• Neither the network nor the caller is trusted.

The Authentication Service then returns an Identity Header, which includes a cryptographic signature and certificate. This data travels along with the call through the phone network. Before the call reaches the recipient, the terminating provider verifies this signature and trust level.

Based on the verification results, the provider can decide to mark the call as “trusted,” block it, label it as “SPAM Likely,” or flag it for further action.

For developers, this process offers a powerful way to build secure, trusted communication apps and services that can help businesses reduce fraud while improving customer trust and engagement.

STIR/SHAKEN – one protocol to rule them all

Early branded calling systems, or “legacy” approaches, explains McQueary, relied on a patchwork of databases, carrier deals, and handset partnerships. They showed logos or caller names but were fragmented, lacked cryptographic security, and varied in accuracy across networks and devices.

Legacy systems didn’t securely embed branding into call signaling, and before STIR/SHAKEN, there was no standard way to transport and validate branding across carriers – making calls vulnerable to tampering.

STIR/SHAKEN changes all that.

It builds a higher level of trust for carriers and users by ensuring the displayed brand identity stays legit and can’t be easily faked.

And because STIR/SHAKEN is based on industry – wide standards, it works seamlessly across carriers, mobile systems, and networks. Regulators, carriers, and standards bodies back it as the universal solution, making cryptographically signed branding more trusted wherever calls go.

How do I wire Branded Caller into my stack?

So, how do you plug Branded Caller into your existing setup, and what’s needed to make it work?

First off, Infobip acts as the Originating Service Provider and signs calls using a Signing Agent from the CTIA ecosystem. They picked SecureG to handle this crypto magic, making sure calls are legit and trusted.

Next, they team up with an Onboarding and Vetting Agent, NumHub, which lets customers securely add their brands to the mix. Think of it as the bouncer making sure only the right brands get in.

Security’s no joke here, Infobip runs a strict KYC (Know Your Customer) check before handing out Virtual Local Numbers. They follow CTIA’s standards to keep everything reliable and above board.

And it’s not just about old-school phone calls (PSTN). Infobip also supports cool OTT channels like Viber Business Calls and WhatsApp Business Calling, showing off verified business names and logos. That way, businesses can reach customers wherever they’re most likely to pick up.

Want to learn more about Branded Caller? We’re here to help!

The post Developers, Make Your Calls REALLY Legit with Branded Calling appeared first on ShiftMag.

Albert Brennan (All Hands AI), Stefania Druga (Google DeepMind), Eno Reyes (Factory), Adrienne Tacke (Viam), Talia Nassi (Akamai), and Louis Knight-Webb (Bloop) are just a few of the top developers and innovators who will take the stage at Infobip Shift conference in Miami.

This year’s focus is on Artificial Intelligence, exploring its impact on development and the creative processes driving it.

“AI has become a vital tool for developers, unlocking endless opportunities for innovation,” said Ivan Brezak Brkan, Director of Developer Experience and Content:

Developers are leading the charge in using AI to transform entire industries. They are not only creating cutting-edge large language models (LLMs) but also leveraging AI to elevate existing digital products.

Shift Miami will be Florida’s only event where developers and tech executives can explore how AI is shaping today’s economy.

Talks, workshops, and networking opportunities await

“As Miami establishes itself as a hub for tech innovation, attendees can expect interactive discussions and hands-on experiences that will help shape the future of technology,” said Ethan Gustav, Infobip’s Group President of North America.

This year’s program will include talks, panels, an EXPO hall, and countless opportunities to connect with other engineers and industry professionals.

With a diverse crowd of engineers, product owners, startup founders, and more, Shift will set the standard for hands-on learning, networking, and the exchange of groundbreaking ideas. Brkan adds:

We remain committed to connecting and supporting developers worldwide through unique local experiences.

Infobip Shift Miami 2025 is one such experience – an exclusive AI conference in the heart of Miami!

Register for Infobip Shift Miami if you want to learn how to use AI to create top-tier technology products.

The post AI Takes Over Miami: Join us at Shift 2025! appeared first on ShiftMag.

AI is leveling up, and it’s not just about what large language models (LLMs) can create – text, images, and videos. The real disruption? Giving computers agency. Instead of just following commands, they’re becoming autonomous agents, perceiving the world and taking action on their own.

Enter Agent Experience (AX), a term coined by Matt Biilman, CEO of Netlify.

Just like we’ve seen with “user experience” (UX) and “developer experience” (DX), AX is all about making products work seamlessly for AI agents. It’s about designing platforms that are easy for agents to use, with clean APIs and machine-ready documentation.

The future of AI isn’t about slapping on some flashy AI features, says Matt – it’s about crafting experiences that let agents work their magic, unlocking tons of value for users along the way.

How to make your products agent-friendly

As AI agents become more common, Matt envisions two approaches for how they interact with software:

• A closed vertical approach, where companies tightly integrate their own agents into their software,
• An open approach, where companies make their software accessible to external agents.

Currently, companies like Netlify, Clerk, ClarityText, and Neon are adopting AX to enhance collaboration between human users and AI agents, improving productivity and innovation. These early adopters are leading the charge in making their platforms more agent-friendly, recognizing the potential of AX to shape the future of software interaction.

Matt Billman explains why AX is crucial, saying:

Too many companies are focusing on adding shallow AI features all over their products or building yet another AI agent.

The real breakthrough will be thinking about how your customers’ favorite agents can help them derive more value from your product. This requires thinking deeply about agents as a persona your team is building and developing for.

He points out that companies focusing on AX will not only future-proof their products but also gain a huge competitive edge as AI agents become an integral part of the digital landscape.

Focus on AX or fall behind

According to Matt, generic SaaS tools are on their way out, and custom-built internal apps are the future. As development gets cheaper, the number of web apps will skyrocket.

For software companies, the key shift is this: design the AX of your product or get left behind by tools that let customers seamlessly collaborate with agents.

He talks about how Netlify grew by focusing on the shortest path from code to production. Now, their focus is on AX:

What is the shortest path for an agent to go from user input to URL in production? How do we make our primitives and APIs simple for LLMs to build with?

What new workflows are needed to make the collaboration between developer and agent not just efficient, but delightful?

Open agent ecosystem

It’s not just about Netlify – Matt says the whole industry needs to push the AX of the web forward. As we move from manual development to AI-assisted co-creation, AX will be crucial to serving users and helping developers create at scale.

So, ask yourself: What could an open AI agent audience unlock for your product? How could focusing on AX make a bigger impact? The industry, says Matt, needs to come together to build an open agent ecosystem and make AX a priority for a more connected digital world.

Matt Biilman will be speaking at Shift Conference taking place on September 14-16 in Zadar, Croatia, if you want to hear first-hand from him on why Agent Experience is important and how to make your platforms AX-friendly.

The post Instead of adding shallow AI features, focus on Agentic Experience (AX) appeared first on ShiftMag.

Ever heard of chaos engineering? It’s a part of software resilience, focused on accepting that mistakes are inevitable and preparing to bounce back stronger rather than stressing over them.

As Kelly Shortridge (Senior Director of Portfolio Product Management at Fastly) says, failures aren’t disasters – they’re just opportunities to learn.

The trick is to adapt quickly by making small, manageable changes, thinking beyond isolated code, and keeping an eye on the bigger picture.

This video is a part of ShiftMag’s video series, Engineer Explains.

We’ve asked experienced engineers to share how they would explain some basic and some less basic tech terminology to different tech job titles or at three levels of experience — from junior developer to CTO.

More videos from the Engineer Explains series:

• Feature Flags Explained
• JAMstack Explained
• Observability Explained
• Large Language Models Explained
• DevOps Explained
• DevRel Explained
• Network APIs Explained
• Verifiable Credential Explained
• Mob Programming Explained
• Machine Learning Explained
• RUST Explained
• Career Tips for Tough Times ft. ‪Pragmatic Engineer‬

The post Engineer Explains: Turning mistakes into wins with CHAOS ENGINEERING appeared first on ShiftMag.

This is one of the insights from DORA’s new 2024 State of DevOps report!

This year focuses on how AI tools are changing the game, the importance of platform engineering, and why understanding developers is essential for improvement.

These are some of the takeaways from the research.

Empower developers to work more independently

For the second year in a row, this research highlights that AI tooling is actually lowering software delivery performance. But the explanation may surprise you; it’s not just that AI code is unreliable.

The real link between AI tooling and weaker delivery performance is the tendency for AI-driven coding to result in larger batches of code.

AI simply makes it easier to churn out more code in less time, leading to more complex deployments.

Also, software delivery throughput and quality are becoming less aligned, and overall performance appears to be slipping compared to last year.

And to address this issue, organizations should invest in tools and processes that empower developers to work more independently – like better documentation and self-serve platforms.

While these developer platforms may slow down delivery at times, they ultimately enhance both individual and team performance.

We code faster, but meetings are still dragging on as usual

And here’s a surprising twist: while AI adoption boosts individual productivity, flow, and job satisfaction, it may also decrease time spent on valuable work. Yup, you read that right!

We may be coding faster, but admin work and endless meetings aren’t going anywhere.

Now, here’s where the real magic happens: documentation. It’s the secret weapon for leveling up your development game.

DORA’s research shows a solid link between good documentation and better performance. They estimate that a 25% bump in AI adoption could lead to a 7.5% boost in documentation quality – making it more reliable and easier to navigate.

Key to platform engineering success? Put developers first

This year’s report also digs into platform engineering and what it means for developers.

A key factor in the success is to approach platform engineering with user-centeredness (users in the context of an internal developer platform are
developers), developer independence, and a product mindset.

Here are the highlights:

1. Internal platforms can help individuals and teams get more done, but they might also slow things down and introduce some instability. Still, companies using these platforms often deliver software faster and perform better overall.
2. To make internal platforms work, you need to understand your developers. Think about their goals, not just the tasks they need to finish. The more independence they have, the better!
3. Good leaders make a huge difference. When they have a clear vision and support their teams, it leads to happier, more productive developers.

Overall, software delivery seems to be facing challenges in 2024, reflecting the tough conditions many companies are dealing with in today’s economic climate. Buckle up!

The post DORA: Only 10% of developers see big productivity boost by AI appeared first on ShiftMag.

Errors are unavoidable, but it’s ineffective error handling that can truly damage a business. If your app frequently crashes, users will lose confidence quicker than you can address the issues.

This makes it essential to prioritize how errors are managed during a program’s runtime.

Abiodun Olowode, Engineering Manager at Cleo, simplifies error handling for all levels—from entry-level developers to seasoned engineers and CTOs.

This video is a part of ShiftMag’s video series, Engineer Explains.

We’ve asked experienced engineers to share how they would explain some basic and some less basic tech terminology to different tech job titles or at three levels of experience — from junior developer to CTO.

More videos from the Engineer Explains series:

• Feature Flags Explained
• JAMstack Explained
• Observability Explained
• Large Language Models Explained
• DevOps Explained
• DevRel Explained
• Network APIs Explained
• Verifiable Credential Explained
• Mob Programming Explained
• Machine Learning Explained
• RUST Explained

The post Engineer Explains: ERROR handling strategies every developer must know appeared first on ShiftMag.

You’ve probably heard the meme about Rust: you can rewrite everything in it. Well, the myth is true!

Rust is hugely popular right now, topping Stack Overflow’s 2023 survey as the most loved programming language. And that says a lot!

As Francesco Ciulla, Developer Advocate, says, Rust is great for systems programming, web development, and deploying smart contracts on blockchain platforms like Solana. Its efficiency makes it perfect for refactoring legacy code and boosting performance across various use cases.

Watch this video to dive into machine learning across three expertise levels: junior developer, senior developer, and CTO.

This video is a part of ShiftMag’s video series, Engineer Explains.

We’ve asked experienced engineers to share how they would explain some basic and some less basic tech terminology to different tech job titles or at three levels of experience — from junior developer to CTO.

More videos from the Engineer Explains series:

• Feature Flags Explained
• JAMstack Explained
• Observability Explained
• Large Language Models Explained
• DevOps Explained
• DevRel Explained
• Network APIs Explained
• Verifiable Credential Explained
• Mob Programming Explained
• Machine Learning Explained

The post Engineer Explains: Francesco Ciulla breaks down why you should try RUST appeared first on ShiftMag.

Ever wondered how computers get so smart without you typing out every little thing? That’s what we call machine learning!

It’s like giving your computer a brain upgrade so it can learn cool stuff on its own – no step-by-step coding needed. It’s a bit like teaching kids new words: show them an apple and say ‘apple,’ then a pear and say ‘pear,’ and they eventually learn to recognize new fruits on their own.

Watch this video to dive into machine learning across three expertise levels: junior developer, senior developer, and CTO.

This video is a part of ShiftMag’s video series, Engineer Explains.

We’ve asked experienced engineers to share how they would explain some basic and some less basic tech terminology to different tech job titles or at three levels of experience — from junior developer to CTO.

More videos from the Engineer Explains series:

• Feature Flags Explained
• JAMstack Explained
• Observability Explained
• Large Language Models Explained
• DevOps Explained
• DevRel Explained
• Network APIs Explained
• Verifiable Credential Explained
• Mob Programming Explained

The post Engineer Explains: 3-minute crash course on Machine Learning appeared first on ShiftMag.