WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
World Congress 2026 Europe • Jul 10, 2026 • Session details

Teaching an LLM to review code … like a Senior Engineer!

Kesha Mykhailov

Are out-of-the-box LLMs sabotaging your pull requests with noisy nitpicks? Discover how one team built an evaluation flywheel to train an AI that reviews code like a senior engineer.

Pause
Mute Enter Fullscreen
#1 about 4 min

Building reliable AI agents for business value

Demonstrable success in automated customer resolution proves that highly effective agents require relentless experimentation and custom models.

#2 about 3 min

Why generic LLMs fail at code reviews

Standard language models produce verbose and irrelevant code feedback because they lack foundational knowledge about unique organizational frameworks.

#3 about 2 min

Leveraging historical context to customize code agents

Automating pull request comments using raw historical design guidelines leads to overwhelming noise without proper deployment testing.

#4 about 2 min

Building an offline evaluation framework for code reviews

Running simulated evaluations inside isolated containers captures structural issues before untested bots can pollute live repositories.

#5 about 3 min

Refining AI prompts through batch evaluations

Using an automated judge to measure severity and correctness helps eliminate false positives triggered by overly rigid prompt formatting.

#6 about 2 min

Gathering human signals to validate agent helpfulness

Mining direct interface feedback and implied commit changes reveals true metrics for an automated reviewer's operational value.

#7 about 3 min

Expanding AI agents to handle pull request approvals

Deconstructing the approval process assigns distinct tasks to specialized sub-agents for catching fundamental bugs and architectural violations.

#8 about 2 min

Designing agent-first interfaces for developer workflows

Constructing specialized interaction protocols ensures that automated assistants can curate evaluation datasets without disrupting natural programming habits.

#9 about 4 min

Preventing deployment risks using deterministic commit limits

Limiting automatic approvals to exceptionally short architectural changes forces developers to embrace continuous delivery and mitigate production flaws.

#10 about 4 min

Shaping sociotechnical systems with character-driven automation

Injecting distinguished personas into pipeline tooling cuts through alert fatigue and naturally encourages engineers to divide dense assignments.

#11 about 2 min

Managing unexpected consequences in automated workflow gating

Intense mechanical bottlenecks frequently cause frustration but inadvertently push engineers to preserve intricate logic rationale inside version histories.

#12 about 3 min

Strategic requirements for implementing enterprise AI agents

Successfully scaling an intelligent code assistant demands continuous background iteration frameworks alongside explicit social reinforcement techniques.

#13 about 4 min

Retaining knowledge sharing inside generative coding environments

Tracking granular design choices during automated coding sessions enables experienced developers to mentor juniors asynchronously.

Matching moments

2:32 min

Reducing pull request cycle times with artificial intelligence

Andrew Boyagi Andrew Boyagi · World Congress 2025

1:57 min

Enforcing automated code reviews to manage accelerated delivery

Harald Kirschner Harald Kirschner · Coffee With Developers

1:31 min

Replacing traditional code reviews with interactive agents

Victor Savkin Victor Savkin · World Congress 2026 Europe

3:26 min

Introducing LLMs as judges for automated testing

Sebastian Messingfeld Sebastian Messingfeld · World Congress 2026 Europe

1:31 min

Automating pull request feedback with AI code review agents

Merrill Lutsky Merrill Lutsky · World Congress 2025

1:55 min

Shifting developer workloads and realistic AI productivity gains

Chris Heilmann Chris Heilmann +2 · LIVE

More from World Congress 2026 Europe

Building the Nervous System of AI - Michael Kagan (NVIDIA) thumbnail
29:17
3 months ago

Building the Nervous System of AI - Michael Kagan (NVIDIA)

Michael Kagan, Sead Ahmetović

Five Things in Tech that Matter Now - WeAreDevelopers World Congress 2026 Closing Keynote thumbnail
19:41
3 months ago

Five Things in Tech that Matter Now - WeAreDevelopers World Congress 2026 Closing Keynote

Christian Heilmann

The Sound of Your Secrets: Teaching Your Model to Spy, So You Can Learn to Defend thumbnail
32:06
3 months ago

The Sound of Your Secrets: Teaching Your Model to Spy, So You Can Learn to Defend

David vonThenen

Super scaling for the Super Bowl: How to survive 30 million users hitting your backend in 30 minutes thumbnail
35:13
3 months ago

Super scaling for the Super Bowl: How to survive 30 million users hitting your backend in 30 minutes

Irina Branovic

Running Secure Life Science Research at Scale using Hybrid GPU HPC and Kubernetes 🧬 thumbnail
24:23
3 months ago

Running Secure Life Science Research at Scale using Hybrid GPU HPC and Kubernetes 🧬

Jeremy Murray

Angstfreude - AI and Corporate Culture - The Thrill and the Threat thumbnail
30:26
3 months ago

Angstfreude - AI and Corporate Culture - The Thrill and the Threat

Axel Ebert, Karin Krobath

Related videos

Completing the Feedback Loop thumbnail
21:03
World Congress 2026 Europe • 3 months ago

Completing the Feedback Loop

Nimrod Kor

The Limits of Prompting: ArchitectingTrustworthy Coding Agents thumbnail
24:05
World Congress 2025 • about 1 year ago

The Limits of Prompting: ArchitectingTrustworthy Coding Agents

Nimrod Kor

5 things I wish I hadn’t done building my AI agent thumbnail
20:16
World Congress 2026 Europe • 3 months ago

5 things I wish I hadn’t done building my AI agent

Shachar Azriel

AI Killed DevOps... What Now? - Lee Faus thumbnail
57:43
Coffee With Developers • 10 months ago

AI Killed DevOps... What Now? - Lee Faus

Lee Faus

How we built an AI-powered code reviewer in 80 hours thumbnail
28:07
World Congress 2025 • about 1 year ago

How we built an AI-powered code reviewer in 80 hours

Yan Cui

Evals vs. Evil - AI and Package Security - Laurie Voss thumbnail
16:57
Coffee With Developers • 2 months ago

Evals vs. Evil - AI and Package Security - Laurie Voss

Laurie Voss

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.