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
Post-Training Gemini 4 for Real Engineering Work — Melvin Johnson, Google DeepMind
Passing the tests does not mean a coding agent solved the problem. At CODE Summit 2026, Google DeepMind's Melvin Johnson explains Gemini 4 post training for real engineering work, from harder tasks…
Passing the tests does not mean a coding agent solved the problem. At CODE Summit 2026, Google DeepMind's Melvin Johnson explains Gemini 4 post training for real engineering work, from harder tasks and rubric based grading to isolated evaluation environments. He connects reinforcement learning, reward hacking, honest model behavior and feedback from Google's engineers to faster releases, alongside Gemini 4 Carbon and Hydrogen.
Speaker info:
- https://melvin.app/
- https://research.google/people/105147/
- https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-4-hydrogen/
Timestamps:
0:00 - Gemini 4 Carbon and Hydrogen
5:32 - From code completion to real engineering work
7:23 - Harder tasks and richer learning signals
10:00 - Grading agents without rewarding cheating
13:10 - Training agents to report honestly
15:30 - Shipping faster through engineering feedback
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
Memory & Continual Learning @ AI Engineer
Post-training @ AI Engineer
uploads
More episodes from this channel
40x More Merged PRs With 2.7x the Engineers — Walden Yan, Cognition
18.11.2026
Cognition's merged PRs grew 40x in a year while its engineering team grew 2.7x. Walden Yan explains what changed: self-driving PRs by default, small pods that own everything from bug reports to QA, and...
2026 in LLMs — Simon Willison, Datasette
17.11.2026
Simon Willison used AI coding agents to locate a beeping detector buried in 40 boxes. At CODE Summit 2026, the Datasette creator traces three LLM inflection points: reliable coding agents, persistent problem solving and...
New Ways of Working with Codex — Dominik Kundel & Charlie Guo, OpenAI
17.11.2026
An internal video app lets Codex edit footage in DaVinci Resolve and return a cut for review. OpenAI’s Dominik Kundel and Charlie Guo demonstrate connected agent workflows at CODE Summit 2026, from context gathering...
Let's Open Source the World — Brandon Thomas, ArtCraft
16.11.2026
ArtCraft’s first Photoshop approximation took about 24 hours to build, Brandon Thomas says. At CODE Summit 2026, he explains how Rust and AI coding agents power open source alternatives to Adobe’s creative tools, Microsoft...
I love you so jevving much — Diogo Almeida, TypeSafe AI
15.11.2026
Being Einstein 95% of the time and Mr. Bean 5% is Diogo Almeida's analogy for unreliable LLM automation. At CODE Summit 2026, the TypeSafe AI cofounder argues that RLHF optimizes models for human assistance...
All Code Is Slop (Except Mine) — Lauren Tan, SpaceXSI
14.11.2026
11,000 pull requests in one month, with a revert rate around 0.5%. Lauren Tan (poteto) shares how the Grok Bot team at SpaceXSI scales AI coding agents through software architecture, lint rules, automated testing,...
Rethinking Claude Code Best Practices — Lydia Hallie, Anthropic
12.11.2026
The models have gotten really good, and most of what we've added to our Claude Code setups over the past year is now holding them back. In this talk I'll go through what Claude...
Your SKILL.md Is 70% Stuff the Model Already Knows - Nikolay Petrov, Intel
11.11.2026
Adding a line to a skill takes seconds, but removing one is scary, so skills only grow. Nikolay Petrov shows how to see inside a skill: split it into small checkable claims, test the...
225,000 Lines of Tests, Written and Merged by Agents - Kush Agrawal, Duolingo
11.11.2026
Duolingo's iOS app has nearly 2 million lines of code, and its unit test coverage lagged far behind. Kush Agrawal walks through the autonomous pipeline that fixed it: scheduled workflows pick untested code, coding...
Agents Made Code Free. Maintaining It Didn't Get Cheaper. - Dmitry Buykin, Maersk
11.11.2026
Coding agents made writing code almost free, but maintaining it didn't get any cheaper. Dmitry Buykin shares what happens months in, once agents write most of a large production codebase: tests that pass while...
Total Recall: Agent Memory and Harness Engineering — Ignacio Martinez, Oracle
11.11.2026
Ignacio Martinez registered the domain for this workshop on the Saturday before he gave it, and then asked the room not to request the biggest machines on offer, because he was paying for everyone's...
Pick Problems That Survive When AI Solves Coding - Ara Khan, Cline
11.11.2026
What will you work on once frontier labs solve coding? Ara Khan traces the rise of coding agents and where recursive self-improvement takes them next, connecting the feedback loops across evals, agent harnesses, inference...
Your Agent Doesn't Need an LLM for Every Decision - Raymond Weitekamp, OpenProse
10.11.2026
Recursive language models have become a powerful harness pattern for LLMs. Raymond Weitekamp shows how the same idea applies to decision models, the fast classifiers also called System One models, to build far more...
Your Sub-Agents Are a Distributed System. Treat Them Like One. - Girish Konda, Microsoft
10.11.2026
When an orchestrator hands work to sub-agents, you've built a distributed system, and you inherit its classic failures: half-finished work reported as success, guesses read back as facts, rate limits the orchestrator never sees,...
Your Team's Agents Are All Shipping to the Same Code at Once - Patrick Debois, Tessl
10.11.2026
Your whole team runs coding agents now, and all of them land on the same main branch. Continuous delivery wasn't built for that. Patrick Debois maps what breaks when a software factory goes multiplayer,...
Every Company Is Building Agents That Can't Work Together - Justin Schroeder, Standard Agents
10.11.2026
Skills and MCP gave agents a standard way to get context, but the agents themselves are still one-offs: every team builds its own, and none of them can be shared or combined. Justin Schroeder...
Your PR Says the Tests Passed. Prove It. - Stephen Chin & Cassandra Chin
10.11.2026
A pull request can claim that checks passed even when the recorded commands do not establish that the submitted change was tested. Cassandra Chin built Tracetoon to recover the context behind a branch, write...
Every Correction You Give Your Agent Is Data - Brian Douglas, Paper Compute
10.11.2026
A Rust program can compile and still violate the decisions an experienced teammate would catch immediately. Brian Douglas finds that missing knowledge in moments when engineers push back on their coding agents. At Paper...
Your Agent Hates Your CLI - Ayush Bhardwaj, Allos AI
10.11.2026
An agent can hide a failed test behind a successful shell pipeline. It can also trim away the error message and confidently report that everything worked. Ayush Bhardwaj examined roughly 20,000 tool calls from...
Give Your On-Call Its Own AI Teammate - Swaapnika Motapothula, Chinmay Gandhi & Vlad Tsvang, Meta
10.11.2026
Twelve alerts fire at 2 a.m., and a useful assistant can still leave the engineer coordinating every step. Meta's on call team uses that illustrative scenario to explain a different design: one AI teammate...
Innohub TV
Watch this content also on Innohub TV
We picked clips from Innohub TV that continue the same topic.
