About this channel
AI Engineer focuses on the practical difficulties of building software with AI and making agents work reliably. The channel's talks examine browser automation, model selection, memory, tool access…
AI Engineer focuses on the practical difficulties of building software with AI and making agents work reliably. The channel's talks examine browser automation, model selection, memory, tool access and the effects of generated code on development teams. Its central subjects are the gaps between an impressive capability and a system that performs consistently within a real workflow.
Developers and engineering leaders will recognise many of the questions being raised. Does a coding agent actually help a team deliver faster? Why can a browser agent with a high success rate still fail as part of a larger task? How should a system choose a model, retrieve current information or retain useful memory? The material is suited to people who need to make architecture and process decisions around those questions, with individual speakers presenting a particular argument or set of observations.
Derek Meegan's browser-agent talk tackles reliability, while Jakub Hojsan's session examines coding agents working with outdated information. A talk by Dylan Couzon turns to ownership of agent memory. These specific engineering concerns sit beside discussions of MCP, communication between agents and the limits of treating a protocol as a complete solution. Named speakers and organisations give the episodes the form of technical presentations rather than general news summaries.
The organisational strand considers evidence about AI in software development, the changing role of code review and what a chief AI officer is expected to do. That widens the channel's scope from how to construct an agent to how a team should evaluate and govern its use. Viewers can move between implementation questions and debates about productivity, using the talks to examine both the systems they build and the assumptions behind their development process.
Latest episode
Stop Giving Your Agent Tools. Give It a Sandbox - Mikyo King, Arize AI
Classic tool-calling agents fill their context with tool catalogs and raw outputs. Code mode gives the agent a sandbox and lets it search for and compose tools in code, returning only what it needs…
Classic tool-calling agents fill their context with tool catalogs and raw outputs. Code mode gives the agent a sandbox and lets it search for and compose tools in code, returning only what it needs. Mikyo King, head of open source at Arize AI, explains why code mode works, how Arize built it into Phoenix (Bash, a Python sandbox, SQL and even UI control), its hidden costs (secrets, permissions, durability, double sandboxing), and how Harbor evals showed 43% fewer tokens and 31% lower cost.
Chapters:
0:00 Intro
0:36 The line between engineers and everyone else is dissolving
1:52 The classic tool-calling agent
3:03 What is code mode?
4:37 Why code mode works
6:11 How Phoenix uses code mode
8:19 The hidden costs of code mode
10:42 Open problems
11:44 Evaluating code mode with Harbor
12:55 Results: 43% fewer tokens, 31% lower cost
13:59 Takeaways
Mikyo King
https://arize.com
Join us in SF for the second annual AIE CODE summit: https://aie.codes our last flagship summit of 2026. Applications live now!
YouTube Shorts
AI Architects @ AI Engineer
AIE World's Fair 2026 Complete Playlist
Anthropic @ AI Engineer
Coding Agents @ AI Engineer
Data (Datasets and RL Environments) @ AI Engineer
FDE (Forward Deployed Engineering) @ AI Engineer
Post-training @ AI Engineer
uploads
More episodes from this channel
What a $900M Bank Error Teaches Us About AI Agents - John Feminella, Two Sigma
27.10.2026
In 2020, Citibank accidentally sent about $900 million to Revlon’s lenders instead of an $8 million interest payment, even though the procedure, the warning pop-up and three approvers all did what they were supposed...
Why Are We Still Governing AI Agents Like Software? - Tim Tyler, Gravitee
27.10.2026
Nobody would hire a worker with no ID, no manager and shared passwords, yet that's how most companies deploy AI agents. Tim Tyler of Gravitee presents the Agent Accountability framework, which governs agents like...
300 Agents, 60 People: How We Secured Our Own AI Agents - Aiden Sochowski, Runlayer
27.10.2026
Runlayer is a company of about 60 people running 300+ agents every day. Founding engineer Aiden Sochowski shares what they found once they put a gateway in front of everything and logged every session...
How a Trading Firm Ships New AI Models the Same Day - Noyan Tokgozoglu, Optiver
27.10.2026
At Optiver, a change rolled out to traders shows up in P&L within hours, so AI has to move fast and still be measurable. Noyan Tokgozoglu, head of AI Engineering, walks through Optiver's on-prem...
Agents That Self Improve While You Sleep - Fuad Ali, Arize AI
26.10.2026
In this workshop, Fuad Ali of Arize AI shows how to build a self-improvement loop for AI agents: trace everything, let Signal (an always-on agent) read your traces on a schedule and file deduplicated...
How to Test Your Agents on Real Tasks With Harbor - Xander Song, Arize AI
26.10.2026
Xander Song, an engineer at Arize AI who works on Phoenix, introduces Harbor, an open source framework for evaluating agents on realistic tasks with real data in isolated sandboxes. He explains tasks, Docker environments,...
How to Build an AI Code Review Agent - Daksh Gupta, Greptile
26.10.2026
Daksh Gupta, co-founder of Greptile, which reviews about 1% of all pull requests on GitHub, shares what Greptile tells companies that want to build their own review agent. Starting from a simple sandbox-plus-webhook setup,...
Build Your Own Team of Managed Agents - Jack Wotherspoon, Google DeepMind
26.10.2026
Jack Wotherspoon, developer experience engineer at Google DeepMind, introduces Gemini Managed Agents: coding agents that run in cloud sandboxes from a single API call instead of on your laptop. He covers the Interactions API,...
How to Build Voice Agents That Don't Fall Apart When You Interrupt - Jesse Hall, LiveKit
26.10.2026
Jesse Hall of LiveKit shows how to build voice agents for financial services that feel human, not robotic. He explains why model leaderboards mislead (they score components, but you ship a conversation), why you...
How to Write Your First AI Eval - SallyAnn DeLucia, Arize AI
25.10.2026
A hands-on workshop from SallyAnn DeLucia, head of product at Arize AI, on moving from vibe checks to real evals. She covers what an eval is and how it differs from a unit test,...
What Does an AI Engineer Do Now? - Aparna Dhinakaran, Arize AI
25.10.2026
Aparna Dhinakaran of Arize AI revisits what an AI engineer actually does as the field moves from writing features to running factories of agents. The job now is building the loop: evals that review...
Can Your AI Analyst Keep a Secret? - Aaron Linsky, Bridgewater & Nikhil Benesch, turbopuffer
25.10.2026
An AI analyst at a firm like Bridgewater needs private documents, but every email, memo and research note carries its own permissions. Aaron Linsky (head of product engineering, Bridgewater Associates) explains why the Vault's...
How to Build Financial Agents That Work Across the Web - Jay Sahnan & Arik Bird, Browserbase
25.10.2026
Some of the most important financial data sits behind logins and anti-bot walls, with no API. Jay Sahnan and Arik Bird of Browserbase show how browser agents solve this through three case studies: Ramp...
Do Not Let Models Invent Numbers - Vinoo Ganesh, Kepler
25.10.2026
In finance, you never show a figure you can't trace. Vinoo Ganesh, CEO of Kepler (previously Palantir and Citadel), explains Kepler's architecture where models cite numbers but never write them: retrieval finds the source,...
Why Frontier Models Fail as Buy-Side Analysts - Janie Gu, Google DeepMind & Suyeol Yun, LinqAlpha
25.10.2026
Janie Gu, product manager at Google DeepMind leading Kaggle Benchmarks, explains why most AI benchmarks are broken: they don't reflect real work, they're expensive to keep current, and their scores can't be verified. After...
AI Writes the Code. So What's Left for Engineers? - Laurie Voss, Arize AI
24.10.2026
Laurie Voss, head of developer relations at Arize AI and co-founder of npm, argues that coding agents made writing code nearly free, so the bottleneck keeps moving: first to code review, then to operations...
Your Agent Fix Just Broke Something Else - Sofia Jakovcevic, Arize AI
24.10.2026
A one-line prompt change made a support agent 17 points safer and 17 points worse at finishing tasks. Sofia Jakovcevic, forward deployed engineer at Arize AI, explains why agents fail at runtime rather than...
How Bridgewater Turned 100 Million Documents Into an Edge - Sam Green & Aaron Linsky, Bridgewater
24.10.2026
Bridgewater Associates built the Vault: more than 100 million documents from 135 external sources plus the firm's own memos and meetings, cleaned, permissioned and tagged to its internal ontology. Sam Green (team lead, Applied...
Can AI Understand a Distressed Credit? - Harneet Kaur, Axim Intelligence
24.10.2026
Harneet Kaur, founder and CEO of Axim Intelligence and a former distressed credit investor, tests whether frontier models can reason about a live distressed situation: iHeartMedia. Given the same context, two top models disagreed...
Proving Alpha: How a Hedge Fund Measures AI's ROI - Hari Kumar, Contour Asset Management
24.10.2026
Hari Kumar, head of AI at Contour Asset Management, a $6B fundamental long/short fund focused on tech, media and telecom, tackles the hardest question in AI adoption: what are we actually getting for the...
Continue reading
You may also like
Innohub TV
Watch this content also on Innohub TV
We picked clips from Innohub TV that continue the same topic.
