In this special predictions episode of ShipTalk, host Dewan Ahmed (Principal Developer Advocate, Harness) sits down with Nick Durkin, Field CTO at Harness, to unpack what’s actually coming in 2026—beyond the hype.

They explore whether we’re heading toward the first AI-caused production meltdown, how much trust we should place in AI "confidence," and why many teams may face a wave of AI-driven tech debt before they find balance. Nick shares why the future isn’t about more tools or more gates, but about policy in the pipeline, guardrails instead of roadblocks, and teams finally operating with a shared rulebook.

The conversation also dives into:

• Why DevSecOps may finally go mainstream in 2026
• How MLOps, agents, and prompts become first-class delivery artifacts
• The real risks behind prompt injection, model tampering, and shadow AI
• Whether AI agents become coworkers—or chaos
• What developer experience looks like when IDEs start to feel like chat windows
• How engineers and teams can stay employable and relevant in an AI-native world

This episode is pragmatic, optimistic, and grounded in real-world delivery experience—perfect for engineers, tech leads, architects, and executives navigating the next phase of AI-driven software delivery.

Listen in for a CTO’s clear-eyed predictions on AI, DevSecOps, and what it really takes to ship safely at speed in 2026.

In this episode of the ShipTalk Podcast, host Dewan Ahmed (Principal Developer Advocate at Harness) sits down with Evgeny Ilinykh (Founder of GuidedMind.ai and former Tesla Engineering Manager) to move past the AI hype and get into the engineering reality of Retrieval-Augmented Generation (RAG).

If your AI agents are hallucinating, the problem probably isn't your model—it’s your retrieval layer. Evgeny breaks down how to turn the "black box" of LLMs into a transparent, production-ready system that developers can actually trust.

What we cover:
- The Death of Deterministic Software: Moving from hardcoded paths to agentic AI logic.
- The "Dark Spots" of Vector Space: Why hallucinations are actually retrieval failures.
- Contextual Retrieval: Insights into how system-level context changes the game for accuracy.
- Scaling to Production: Solving the "dirty work" of messy PDFs, table parsing, and chunking.
- Standardizing AI Delivery: Will RAG become as common as CI/CD in the modern dev stack?

RESOURCES & LINKS:
1. Connect with our guest: https://www.linkedin.com/in/eilinykh/
2. Explore GuidedMind.ai: https://guidedmind.ai/
3. Read the Anthropic Research: https://www.anthropic.com/engineering/contextual-retrieval

In this episode of Ship Talk, host Dewan Ahmed (Principal Developer Advocate, Harness) sits down with Marina Petzel, Senior ML Engineer and AI Productivity Lead at Autodesk, to unpack what it actually looks like to ship AI into long-lived, production software.

Marina shares her journey from classic predictive analytics to computer vision and LLMs, and how her team brings intelligent features like Smart Blocks in AutoCAD from ideation to prototype to production on a tight yearly release cadence. She breaks down the often ignored parts of ML work: data pipelines, infrastructure, UX fit, and safety testing, and explains why “garbage in, garbage out” is a law of nature, not just a cliché.

They also dive into AI for developer productivity, multi-agent workflows, red-teaming and prompt safety, and how every engineer, regardless of seniority, can start using AI as a genuine skill multiplier. Marina closes with concrete advice for aspiring ML engineers: build more, read less, follow your curiosity, and share your work publicly so your visibility compounds over time.

Follow Marina's work: https://marina.petzel.tech
Connect with her: https://www.linkedin.com/in/marina-petzel