World Congress 2025 Aug 20, 2025 Session details

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

Yan Cui

Integrating AI is only 10% of building a production-ready code reviewer. Discover how defensive AWS serverless architecture actually tames context limits, rate caps, and expensive hallucinations.

Pause
Mute Enter Fullscreen
#1 about 3 min

Overview of the AI-powered serverless code reviewer

A demonstration of how the tool scans pull requests to identify security risks and anti-patterns.

#2 about 3 min

High-level architecture for serverless event processing

How GitHub webhooks, EventBridge, Lambda, and AppSync coordinate to handle pull request analysis.

#3 about 5 min

Securing customer source code with Amazon Bedrock

Why privacy guarantees and serverless token-based pricing drove the choice of Bedrock over direct model APIs.

#4 about 3 min

Managing timeouts and limits with async invocations

How handling large pull requests requires durable retries and strict concurrency limits to avoid Lambda timeouts.

#5 about 3 min

Context window limitations in large language models

Why large context windows excel at recall but fail at complex reasoning beyond limited token counts.

#6 about 3 min

Working around API rate limits and model outages

Strategies for maximizing throughput using cross-region inference and managing reliability via fallback provider APIs.

#7 about 3 min

Controlling the high infrastructural costs of AI code analysis

How exclusively scanning changed code lines enables a financially sustainable model for customer AI usage.

#8 about 4 min

Implementing durable execution with local checkpoints

Using a DynamoDB-based idempotency pattern instead of Step Functions while running static analysis parallel to LLM calls.

#9 about 5 min

Handling hallucinations in formatted JSON and code structures

Why LLMs generate imaginary line numbers or outdated fixes and how retrieval constraints impact reliability.

Matching moments

1:55 min

Shifting developer workloads and realistic AI productivity gains

Chris Heilmann +2 · LIVE

6:53 min

Reviewing recent technology and AI tool headlines

Chris Heilmann +1 · LIVE

1:56 min

Analyzing cloud-based AI code completion architectures

Daniel Savenkov Daniel Savenkov · WWC 2024

4:15 min

Security integration and AI skepticism in developer tooling

Chris Heilmann +2 · LIVE

1:58 min

Managing overwhelming artificial intelligence pull requests in open source

Chris Heilmann +2 · LIVE

4:11 min

Filtering AI code generations and automating pull request reviews

Kevin Lewis Kevin Lewis · WWC 2025

Upcoming sessions on this topic

Open session

World Congress 2026 North America

Evals Are Infra: Building AI Systems Developers Can Actually Trust

Phoebe Wang

Member of Technical Staff at OpenAI

Phoebe Wang
Open session

World Congress 2026 North America

When Humans Stop Writing Code: Rethinking Languages, Compilers, and Responsibility

Simon Auer

Organizer of flutter vienna meetup and CEO of marqably

Simon Auer
Open session

World Congress 2026 North America

No Single Model to Rule Them All: Building Resilient AI Agents Across Open & Closed LLMs

Emmanuel Acheampong

Senior Manager Developer Relations at Crusoe AI

Emmanuel Acheampong
Open session

World Congress 2026 North America

DeepAgents: Build Multi-Agent AI Systems That Actually Work

Anagha Rumade, Anjana Umapathy, Apoorva Jaiswal

Anagha Rumade
Anjana Umapathy
Apoorva Jaiswal
Open session

World Congress 2026 North America

Beyond Vibe Coding: Using CLI Tools as Your AI Counterpart in Pair Programming

Ron Veen

Java enthusiast and Special agent for Team Rockstars IT

Ron Veen
Open session

World Congress 2026 North America

Agents Can't Iterate Against Tests That Lie

Rocky Warren

Senior Staff Software Engineer at Clipboard

Rocky Warren