Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
How we built an AI code reviewer with serverles...
Search
Yan Cui
February 12, 2025
Technology
0
99
How we built an AI code reviewer with serverless and Bedrock
Slides for my talk at the Serverless London meetup on 12-Feb-2025
Yan Cui
February 12, 2025
Tweet
Share
More Decks by Yan Cui
See All by Yan Cui
Money-saving tips for the frugal serverless developer (AWS Community Summit)
theburningmonk
1
180
Money-saving tips for the frugal serverless developer
theburningmonk
1
760
Why the fuzz about serverless (with CompassDigital)
theburningmonk
0
100
Money-saving tips for the frugal serverless developer
theburningmonk
0
120
Efficient patterns for serverless development (AWS Summit London)
theburningmonk
0
140
7 ways to solve Lambda cold starts
theburningmonk
0
63
Saving Money on Serverless: Common Mistakes and How to Avoid Them
theburningmonk
0
58
3 Ways to Improve Serverless Performance
theburningmonk
0
45
Smart and efficient ways to test serverless architectures
theburningmonk
1
280
Other Decks in Technology
See All in Technology
freeeのアクセシビリティの現在地 / freee's Current Position on Accessibility
ymrl
2
210
開発生産性を測る前にやるべきこと - 組織改善の実践 / Before Measuring Dev Productivity
kaonavi
13
5.6k
成長し続けるアプリのためのテストと設計の関係、そして意思決定の記録。
sansantech
PRO
0
120
American airlines ®️ USA Contact Numbers: Complete 2025 Support Guide
airhelpsupport
0
390
United airlines®️ USA Contact Numbers: Complete 2025 Support Guide
unitedflyhelp
0
320
Lakebaseを使ったAIエージェントを実装してみる
kameitomohiro
0
140
[ JAWS-UG千葉支部 x 彩の国埼玉支部 ]ムダ遣い卒業!FinOpsで始めるAWSコスト最適化の第一歩
sh_fk2
2
100
スタートアップに選択肢を 〜生成AIを活用したセカンダリー事業への挑戦〜
nstock
0
230
united airlines ™®️ USA Contact Numbers: Complete 2025 Support Guide
flyunitedhelp
1
400
LLM時代の検索
shibuiwilliam
2
300
ビギナーであり続ける/beginning
ikuodanaka
3
770
事業成長の裏側:エンジニア組織と開発生産性の進化 / 20250703 Rinto Ikenoue
shift_evolve
PRO
3
22k
Featured
See All Featured
[Rails World 2023 - Day 1 Closing Keynote] - The Magic of Rails
eileencodes
35
2.4k
Testing 201, or: Great Expectations
jmmastey
43
7.6k
A Modern Web Designer's Workflow
chriscoyier
695
190k
Rebuilding a faster, lazier Slack
samanthasiow
82
9.1k
It's Worth the Effort
3n
185
28k
KATA
mclloyd
30
14k
Understanding Cognitive Biases in Performance Measurement
bluesmoon
29
1.8k
Why Our Code Smells
bkeepers
PRO
336
57k
GraphQLの誤解/rethinking-graphql
sonatard
71
11k
How To Stay Up To Date on Web Technology
chriscoyier
790
250k
[RailsConf 2023 Opening Keynote] The Magic of Rails
eileencodes
29
9.6k
Typedesign – Prime Four
hannesfritz
42
2.7k
Transcript
How we built an AI Code Reviewer with Serverless and
Bedrock
Yan Cui http://theburningmonk.com @theburningmonk AWS user since 2010
Yan Cui http://theburningmonk.com @theburningmonk running serverless in production since 2016
Developer Advocate @ Yan Cui http://theburningmonk.com @theburningmonk
Yan Cui http://theburningmonk.com @theburningmonk independent consultant
None
evolua.io Demo
Architecture
API Gateway EventBridge Webhook
API Gateway DynamoDB Bedrock EventBridge Webhook
API Gateway DynamoDB Bedrock EventBridge Webhook
API Gateway DynamoDB Bedrock EventBridge Webhook evolua.io
None
API Gateway DynamoDB Bedrock EventBridge Webhook AppSync evolua.io
API Gateway DynamoDB Bedrock EventBridge Webhook AppSync evolua.io
None
API Gateway DynamoDB Bedrock EventBridge Webhook AppSync evolua.io Authoriser
API Gateway DynamoDB Bedrock EventBridge Webhook AppSync evolua.io Authoriser
API Gateway DynamoDB Bedrock EventBridge Webhook AppSync evolua.io Authoriser
API Gateway DynamoDB Bedrock EventBridge Webhook AppSync evolua.io Authoriser
API Gateway DynamoDB Bedrock EventBridge Webhook AppSync evolua.io Authoriser
Challenges (for an AI code reviewer) Handling sensitive data for
customers
Challenges (for an AI code reviewer) Large fi les. Large
PRs with many fi les. Handling sensitive data for customers
Why Bedrock?
Security
Security Data is encrypted at rest.
www.wiz.io/blog/wiz-research-uncovers-exposed-deepseek-database-leak
aws.amazon.com/bedrock/faqs
Security Data is encrypted at rest. Inputs & Outputs are
not shared with model providers. Inputs & Outputs are not used to train other models.
API Gateway DynamoDB Bedrock EventBridge Webhook AppSync evolua.io Authoriser Fallback
Primary
privacy.anthropic.com/en/articles/7996885-how-do-you-use-personal-data-in-model-training
Serverless
Serverless Usage-based AND provisioned throughput pricing
None
None
1M Input Tokens 1M Output Tokens $0.14 v3 r1 $0.28
$0.55 $2.19 Sonnet $3.75 $15.0 Haiku $0.80 $4.00
Very cost ef fi cient!
Very cost ef fi cient! Data is stored in China.
Very cost ef fi cient! Data is stored in China.
Data might be used to train other models.
www.wiz.io/blog/wiz-research-uncovers-exposed-deepseek-database-leak
Very cost ef fi cient! Data is stored in China.
Data might be used to train other models. Operationally immature.
None
No token-based pricing yet
No token-based pricing yet “GPU-based instance type like ml.p5e.48xlarge is
recommended”
ml.p5e.48xlarge 💰💰💰💰💰💰💰💰💰💰 💰💰💰💰💰💰💰💰💰💰 💰💰💰💰💰💰💰💰💰💰 💰💰💰💰💰💰💰💰💰💰 💰💰💰💰💰💰💰💰
Other capabilities Guardrails Knowledge base (managed RAG) Agents Cross-region inference
Model evaluations
None
None
None
API Gateway DynamoDB Bedrock EventBridge Webhook AppSync evolua.io Authoriser Fallback
Primary
Lessons
Webhook
Webhook Analyse changes
Webhook Analyse changes Feedback
Condensed view…
None
Lambda timed out after 15 mins
Succeeded on automatic retry
Webhook Analyse changes Feedback LLM limits GitHub limits AWS limits
Lesson: AI is 10% of the problem
None
Reasoning ability
Context window Max response tokens API rate limit Reasoning ability
Context window Max response tokens API rate limit Reasoning ability
Cost Performance
Context window Max response tokens API rate limit Reasoning ability
Cost Performance Important selection criteria for LLMs
Doing cool AI stuff! Working around AI limits
Doing cool AI stuff! Working around AI limits Stop playing
with my bowl…
Context window Max response tokens API rate limit Reasoning ability
Cost Performance
Claude 3.5 Sonnet’s default throughput is 50 per minute
Claude 3.5 Sonnet’s default throughput is 50 per minute Can
be raised to 1,000 per minute
Claude 3.5 Sonnet’s default throughput is 50 per minute Can
be raised to 1,000 per minute Bedrock has cross- region inference
Mitigate API rate limit Raise account limits. Use Bedrock cross-region
inference.
Mitigate API rate limit Raise account limits. Use Bedrock cross-region
inference. Limit no. of parallel requests per PR.
Mitigate API rate limit Raise account limits. Use Bedrock cross-region
inference. Limit no. of parallel requests per PR. Fallback to Anthropic & less powerful models (Claude 3 Sonnet, Claude 3.5 Haiku)
Future work: incorporate other models (Nova, DeepSeek, etc.)
Future work: incorporate other models (Nova, DeepSeek, etc.) Also good
for cost control!
Lesson: LLMs are still quite expensive
None
Dif fi cult to build a sustainable and competitive business
Cost control Only analyse changed lines.
Cost control Only analyse changed lines. Good for cost control
Good for UX
Cost control Only analyse changed lines. Limit free users to
few PRs per month.
API Gateway DynamoDB Bedrock EventBridge Webhook
API Gateway DynamoDB Bedrock EventBridge Webhook Built-in retries & DLQ
Lambda timed out after 15 mins
Lambda timed out after 15 mins Reprocess fi les on
retry…
Lambda timed out after 15 mins Reprocess fi les on
retry… Duplicated side- effects (e.g. Github comments)
Cost control Only analyse changed lines. Limit free users to
few PRs per month. Use checkpoints to avoid re-processing fi les on retries
const issues = await executeIdempotently( `${event-id}-${filename}-analyze`, () => analyzeFile(file) );
... await executeIdempotently( `${event-id}-${filename}-add-gh-comment`, () => addReviewComment(filename, comment) );
Webhook Analyse changes Feedback Why not Step Functions?
Webhook Analyse changes Feedback Why not Step Functions? Checkpoints is
just easier 🤷
Lesson: Latency is a challenge
Models take 10s of seconds to analyse each fi le
Wasted CPU cycles in Lambda
Future work: try other models
Future work: make use of these CPU cycles
Lesson: Be ware of hallucinations
“Give me JSON in this format”
None
“Give me JSON in this format” “Nope!”
None
Non-existent codes, invalid URLs
Non-existent line numbers
Future works
Go to evolua.io to try it out. We’d love your
feedback!
Questions?