The Limits of Prompting: ArchitectingTrustworthy Coding Agents
Prompt engineering has its limits. Learn how a multi-agent architecture, enriched with deep context, boosted our AI agent's suggestion acceptance rate from 12% to over 60%.
#1about 2 minutes
Prototyping a basic AI code review agent
A simple prototype using a GitHub webhook and a single LLM call reveals the potential for understanding code semantics beyond static analysis.
#2about 2 minutes
Iteratively improving prompts to handle edge cases
Simple prompts fail to consider developer comments or model knowledge cutoffs, requiring more detailed instructions to improve accuracy.
#3about 5 minutes
Establishing a robust benchmarking process for agents
A reliable benchmarking pipeline uses a large dataset, concurrent execution, and an LLM-as-a-judge (LLJ) to measure and track performance improvements.
#4about 2 minutes
Decomposing large tasks into specialized agents
To combat inconsistency and hallucinations, a single large task like code review is broken down into multiple smaller, specialized agents.
#5about 6 minutes
Leveraging codebase context for deeper insights
Moving beyond prompts, providing codebase context via vector similarity (RAG) and module dependency graphs (AST) unlocks high-quality, human-like feedback.
#6about 3 minutes
Introducing Awesome Reviewers for community standards
Awesome Reviewers is a collection of prompts derived from open-source projects that can be used to enforce team-specific coding standards.
#7about 1 minute
Key takeaways for building reliable LLM agents
The path to a reliable agent involves starting with a proof-of-concept, benchmarking rigorously, using prompt engineering for quick fixes, and investing in deep context.
Related jobs
Jobs that call for the skills explored in this talk.
Matching moments
03:29 MIN
The evolution from prompt engineering to context engineering
Engineering Productivity: Cutting Through the AI Noise
04:43 MIN
The limitations and frustrations of coding with LLMs
WAD Live 22/01/2025: Exploring AI, Web Development, and Accessibility in Tech with Stefan Judis
02:27 MIN
An overview of an AI-powered code reviewer
How we built an AI-powered code reviewer in 80 hours
03:31 MIN
Effective prompting and defensive coding for LLMs
Lessons Learned Building a GenAI Powered App
02:58 MIN
Shifting from traditional code to AI-powered logic
WWC24 - Ankit Patel - Unlocking the Future Breakthrough Application Performance and Capabilities with NVIDIA
02:21 MIN
The danger of over-engineering with LLMs
Event-Driven Architecture: Breaking Conversational Barriers with Distributed AI Agents
04:56 MIN
Understanding when prompting fails and how LLMs process requests
The Power of Prompting with AI Native Development - Simon Maple
01:13 MIN
Automating code reviews with static analysis and LLMs
Panel Discussion: Responsible AI in Practice - Real-World Examples and ChallengesIntroductionIn the ever-evolving landscape of artificial intelligence, the concept of "responsible AI" has emerged as a cornerstone for ethical and practical AI implementation. During the WWC24 Panel discussion, three eminent experts—Mina, Bjorn Brin...
Eli McGarvie
The Prompt Engineer ✍️The next biggest programming language is… English. If you’ve been on social media lately (Twitter or LinkedIn) you would have seen the term “Prompt Engineering” thrown around a lot. You might have even seen people who are self-proclaimed Prompt Engin...
Alan Smithee
GitHub Copilot: Beyond the Basics – 10 Ways to Elevate Your CodingWelcome to an in-depth exploration of GitHub Copilot and its capabilities. If you're a software developer or someone intrigued by AI's potential to revolutionize coding, this post is for you. GitHub Copilot, an AI-powered code completion tool, offers...
Daniel Cranney
One billion (bad?) developers: How AI is changing the way we learn to codeAI has transformed so many aspects of programming, with IDE-integrated code assistants now capable of building complex projects from simple prompts.While AI makes it easier for newcomers to dive into coding, could it also hinder their learning by enc...
From learning to earning
Jobs that call for the skills explored in this talk.
28:07
26:30
31:12
32:26
33:28
30:48
04:17
25:32
