How Specialized Models Drive Developer Productivity | Tabnine’s Brandon Jung

What are the limitations of general large language models, and when should you evaluate more specialized models for your team’s most important use case?This week, Conor Bronsdon sits down with Brandon Jung, Vice President of Ecosystem at Tabnine, to explore the difference between specialized models and LLMs. Brandon highlights how specialized models outperform LLMs when it comes to specific coding tasks, and how developers can leverage tailored solutions to improve developer productivity and code quality. The conversation covers the importance of data transparency, data origination, cost implications, and regulatory considerations such as the EU's AI Act.Whether you're a developer looking to boost your productivity or an engineering leader evaluating solutions for your team, this episode offers important context on the next wave of AI solutionsTopics:00:31 Specialized models vs. LLMs01:56 The problems with LLMs and data integrity12:34 Why AGI is further away than we think16:11 Evaluating the right models for your engineering team23:42 Is AI code secure?26:22 How to adjust to work with AI effectively 32:48 Training developers in the new AI worldLinks:Brandon Jung on LinkedInBrandon Jung (@brandoncjung) / XTabnine (@tabnine) / XTabnine AI code assistant | Private, personalized, protectedManaging Bot-Generated PRs & Reducing Team Workload by 6%Support the show: Subscribe to our Substack Leave us a review Subscribe on YouTube Follow us on Twitter or LinkedIn Offers: Learn about Continuous Merge with gitStream Get your DORA Metrics free forever

Engineering teams are already seeing efficiency gains by leveraging Gen AI solutions like Copilot, but the next wave of AI workflows has the potential to 10X productivity.This week, we’re exploring the world of Agentic AI with Amir Behbehani, Chief AI Engineer and Founder of Memra. Agentic AI can be defined as AI agents or systems that have the capacity to make decisions or take actions on their own based on the objectives they are programmed to achieve. These AI systems act independently, gathering information, processing it, and then choosing or executing actions without direct human intervention.Amir shares how Memra is leading the way in developing AI agents capable of handling complex tasks, decision-making, and improving productivity across industries. He also discusses the implications of AI in reshaping how businesses operate, and how organizations can prepare for a future where AI plays a central role in both day-to-day operations and high-level strategic decisions.Whether you're an AI enthusiast, an engineering leader, or curious about the future of automation, this episode offers a deep dive into the possibilities and challenges of Agentic AI and what it means for the future of work.Chapters:01:23 Defining Agentic AI 07:02 Frameworks for thinking about Agentic AI 12:52 Unpacking AI as a black box 13:58 How Agentic AI will benefit software engineers 22:55 What would be a good starting point to leverage agents on an engineering team?26:46 Will agents replace freelancers and the gig economy?36:20 What is the synthetic marketplace?40:11 How Agentic AI impacts writing codeLinks:Supercharge Your Operations with AI-Powered Agents | MemraAmir BehbehaniManaging Bot-Generated PRs & Reducing Team Workload by 6%Support the show: Subscribe to our Substack Leave us a review Subscribe on YouTube Follow us on Twitter or LinkedIn Offers: Learn about Continuous Merge with gitStream Get your DORA Metrics free forever

According to a LinkedIn study, engineers with strong soft skills are promoted 13% faster than those with only technical skills. Given how AI will continue to reshape market demands for developers and engineering leaders, how can you adapt to these changes and further your career?This week we’re joined by Aarathi Vidyasagar, VP of Engineering at LinkedIn, to explore the growing importance of soft skills and how leadership, communication, and empathy are becoming just as critical as technical expertise.Aarathi shares how LinkedIn is preparing engineers to thrive in this new environment, focusing on upskilling teams to navigate AI and empower collaboration and innovation through strong interpersonal skills. She offers valuable takeaways into building engineering teams that balance hard technical abilities with the soft skills needed to lead, mentor, and work effectively in diverse teams.For anyone interested in the future of engineering and the rising demand for soft skills, this episode offers an important perspective on how to equip your teams for long-term success in an AI-driven world.Episode Highlights:00:56 How industry changes have impacted the need for communication and soft skills 04:31 How software development is going to continue to change 12:33 Generalists vs Specialists 15:52 How is LinkedIn positioned for the new era of hiring?31:11 How is LinkedIn approaching developer experience and productivity?36:33 How to support devs in automating migrations Show Notes:Aarathi on LinkedInClosing the Tech Talent GapManaging Bot-Generated PRs & Reducing Team Workload by 6%Support the show: Subscribe to our Substack Leave us a review Subscribe on YouTube Follow us on Twitter or LinkedIn Offers: Learn about Continuous Merge with gitStream Get your DORA Metrics free forever

Gen AI for dev teams has been a focal point of conversation for the last few years, but the technology and application are both still very nascent. How can you find the best Gen AI use case for your team, and implement it safely?This week, our host Dan Lines sits down with Peter McKee, Vice President of Developer Relations and Community at Sonar. They explore the benefits and risks associated with Gen AI, and whether this new tooling is most impactful for junior or senior developers. Regardless of the persona, there needs to be an emphasis on quality control, static code analysis, and the new coaching strategies to help the influx of new code.Tune in to hear Dan and Peter offer practical advice for engineering leaders on safely experimenting with and integrating Gen AI tools to enhance productivity without sacrificing quality.Episode Highlights:00:33 The ins and out of being a VP of Developer Relations and Community04:48 The Importance of wisdom and experience when applying Gen AI08:32 Is there more of a risk for junior developers in this age?19:51 How tooling can help with the influx of Gen AI Code 26:02 The safe ways to roll out Gen AI to developers29:21 Where to start applying Gen AI for your team Show Notes:Peter McKee (@pmckee) / XPeter McKeeBetter Code & Better Software | Ultimate Security and Quality | SonarDownload The Engineering Leader’s Guide to Accelerating Developer ProductivitySupport the show: Subscribe to our Substack Leave us a review Subscribe on YouTube Follow us on Twitter or LinkedIn Offers: Learn about Continuous Merge with gitStream Get your DORA Metrics free forever

In an organization as big as Shopify, how can you pioneer exceptional developer experience not only for your team but also for external developers using your product?This week we’re joined by Eytan Seidman, Director of Product at Shopify to unpack Shopify's approach to building elite engineering teams. Eytan highlights how Shopify’s high-context, high-autonomy culture empowers engineers and product managers to innovate and drive impact. By leveraging a mission-driven culture, Shopify ensures that internal and external developers can contribute effectively to the platform, without being bottlenecked back by inefficient processes or developer experience.Tune in this week, and discover how you can implement the same processes that have made Shopify so successful.Episode Highlights:00:50 What makes engineering and product roles at Shopify special?03:31 How Shopify onboards new hires to drive impact09:05 Pioneering developer experience at Shopify13:28 How Shopify defines success for their platform 17:50 Building high-context, empowered teams29:35 Leveraging AI and LLM’s as a growth opportunity35:29 Advice for product and engineering leaders thinking about their next career stepShow Notes:Eytan Seidmanx.com/eytanseidmanShopifyShopify Developers Platform—Build. Innovate. Get paid.Download your copy of the 2024 Software Engineering Benchmarks Report hereSupport the show: Subscribe to our Substack Leave us a review Subscribe on YouTube Follow us on Twitter or LinkedIn Offers: Learn about Continuous Merge with gitStream Get your DORA Metrics free forever

Both the aerospace and defense sectors are renowned for long project timelines rife with silos and hurdles that get in the way of productivity. With over 20 years of experience at Lockheed Martin and elsewhere, Robin Yeman literally wrote the book Industrial DevOps on how to implement DevOps principles at traditional behemoths to build faster, safer systems.As Space Domain Lead at Carnegie Mellon's Software Engineering Institute, Robin’s pioneering work reveals how applying DevOps principles can significantly improve speed, quality, and collaboration at traditional enterprises. She emphasizes the importance of cross-functional teams, modular architectures, and a growth mindset in driving innovation and overcoming the challenges of digital transformation within the aerospace and defense sectors.Tune in to gain practical insights about the application of DevOps in large-scale systems, the role of organizational design in fostering communication, and how these principles have helped government software teams.Episode Highlights: - 01:12 Robin’s book Industrial DevOps- 04:00 How did Robin’s work at Lockheed Martin lead to Carnegie Mellon?- 05:46 How should you get started thinking about industrial DevOps?- 08:01 How Robin’s research came together across varied experiences- 10:25 What patterns can you adapt to be more successful?- 16:54 Quantitative vs. qualitative data when making long term plans- 20:27 Shifting left in Industrial DevOpsShow Notes: Robin YemanIndustrial DevOpsWiring the Winning Organization - IT RevolutionDownload your copy of the Gen AI Impact Report todaySupport the show: Subscribe to our Substack Leave us a review Subscribe on YouTube Follow us on Twitter or LinkedIn Offers: Learn about Continuous Merge with gitStream Get your DORA Metrics free forever

Scaling new product lines within a growing company can be both an opportunity and quite challenging. Semgrep's Head of Engineering Adam Berman joined us this week to share his own experience developing Semgrep's second product line.Adam was instrumental in developing Semgrep's second product line, and he shares practical strategies for moving from a single-product to a multi-product organization. He unpacks the challenges of organizational design, the importance of fast iteration and feedback loops, and how to build a cohesive company identity with so many moving parts.If you want to learn how to effectively scale products and how to drive product growth, this episode is a must-listen.Episode Highlights: 1:10 The challenges of new product lines 4:25 Scaling teams for success and strategies for growth7:30 Finding the right balance between practicality and innovation12:15 A startup within a startup mentality 18:40 Learning through experimentation23:55 Key considerations when navigating product market fit28:20 Driving growth in engineering teamsShow Notes: Adam Berman on LinkedInAdam Berman (@adamberman_13) / XSemgrepDownload your copy of the Essential Guide to Software Engineering Intelligence Platforms Support the show: Subscribe to our Substack Leave us a review Subscribe on YouTube Follow us on Twitter or LinkedIn Offers: Learn about Continuous Merge with gitStream Get your DORA Metrics free forever

This week, co-host Conor Bronsdon sits down with Amanda Sopkin, Engineering Manager at Asana. Amanda shares her journey from software engineer to manager, discussing the pivotal moment she chose to pursue management over an individual contributor path. We cover the indicators of a successful manager, the red flags to watch for, and the importance of mentorship.Amanda emphasizes the value of finding the right fit for team members, tailoring leadership styles, and developing a balanced team. Tune in for insights on managing senior versus junior engineers, promoting team members, and striking a balance between professional growth and personal fulfillment.Episode Highlights:00:49 Amanda’s Path to Engineering Management 04:58 How to tailor your leadership style to your team06:40 Unlocking the potential of your team13:25 Keeping track of your team members individual needs17:43 Management career goals20:31 What Amanda is passionate about within engineeringShow Notes:Amanda Sopkin on LinkedInAmanda Sopkin on Twitter / XAmanda Sopkin’s websiteAmanda Sopkin on GitHubAsana Project Management SoftwareSupport the show: Subscribe to our Substack Leave us a review Subscribe on YouTube Follow us on Twitter or LinkedIn Offers: Learn about Continuous Merge with gitStream Get your DORA Metrics free forever

“If you're not careful, cloud computing can lose more money faster than any invention in history” - Mark Robinson, Infrastructure Engineer at PlaidThis week, guest host Ben Lloyd Pearson sits down with Plaid’s Mark Robinson to learn how he helped Plaid save 25% in costs by optimizing existing resources and eliminating waste in cloud computing.Mark explains the importance of understanding your cloud bill, identifying areas of overspend, and implementing changes that lead to significant savings. From the basics of tagging resources to the intricacies of optimizing network and storage costs, Mark offers practical tips that can help you uncover countless optimization opportunities.Tune in to learn about the rewards of improving cloud cost efficiency, the role of organizational buy-in, and the benefits of making cost optimization a company-wide value.Episode Highlights: 00:56 How did cloud computing get so expensive?02:34 Digging into what your costs actually are04:55 How can you account for the various services you use?07:35 Where are organizations going to get the most value out of?12:26 Cloud costs relation to better code quality16:08 Blockers in organizations to cost savings19:32 Getting buy-in from leadership on cutting cloud costsShow Notes:Download your copy of the Essential Guide to Software Engineering Intelligencehttps://www.finops.org/https://www.linkedin.com/in/mark-robinson-944084bSupport the show: Subscribe to our Substack Leave us a review Subscribe on YouTube Follow us on Twitter or LinkedIn Offers: Learn about Continuous Merge with gitStream Get your DORA Metrics free forever

AI is the biggest hype cycle happening in tech right now, but how do you know what’s actually going to make an impact for your product and team vs. what’s just new and shiny?This week, LinearB COO & Co-founder Dan Lines sits down with Louis Brandy, Member of Technical Staff OpenAI and ex-VP of Engineering at Rockset. Louis shares his unique perspective on the evolution of AI, drawing from his experiences with early days AI work at Meta and now with OpenAI following their acquisition of Rockset. He shares grounded insights into the realities of AI, separating fact from fiction in an industry often clouded by buzzwords and unrealistic expectations.Listeners will learn about the practical applications of AI, the challenges and opportunities it presents, and how to go past the hype to find AI's potential. Whether you're an AI enthusiast, a skeptic, or a professional looking to understand the true impact of AI for engineering teams, this episode offers an insightful look at one of the most talked-about topics in tech today.Episode Highlights: 00:32 Louis Brandy's background with AI at Meta04:31 The current AI hype cycle13:09 How should engineering leaders think about AI and the pressure to use it?17:58 How to know if you’re falling into the hype cycle25:50 AI vs. human code34:42 Real time when it comes to AI38:36 What should an IC do about AI in their career path?Show Notes:OpenAI Acquires RocksetDownload your copy of the Essential Guide to Software Engineering Intelligence PlatformsSupport the show: Subscribe to our Substack Leave us a review Subscribe on YouTube Follow us on Twitter or LinkedIn Offers: Learn about Continuous Merge with gitStream Get your DORA Metrics free forever