Battle of the Bots:

AI Agent Showdown

Calvin Hendryx-Parker, CTO, Six Feet Up

Travis Frisinger, Technical Director of AI, 8th Light

AI Coding Assistants

The New Pair-Programming Partners

Rapid Evolution over the last year:

More than 97% of respondents reported having used AI coding tools at work

– Github AI in Software Survey

Why This Matters

• AI coding assistants are transforming how we build software
• Choosing the right tool can mean the difference between frustration and flow
• Let’s find out which one delivers for real-world developers!

The Contenders

• Aider
• Goose
• Claude Code
• Cursor
• Devin

What is AI Agent?

An AI agent is a system that can:

• Perceive its environment through tools/APIs
• Make decisions autonomously
• Take actions to achieve specific goals
• Learn from interactions and feedback
• Chain multiple operations together

Agents Continued

Key characteristics:

• Tool use capabilities (file system, web search, code execution)
• Planning and reasoning about complex tasks
• Persistent memory within a session
• Self-improvement through feedback loops

Agents Continued

Styles:

• IDE: Feels like Copilot on steroids. It has smooth integration inside your editor, low-friction for everyday coding.
• CLI: Runs in your terminal where you drive the conversation. Great for deliberate workflows and bigger refactors.
• Autonomous: Tools that pursue higher-level goals across multiple steps. Handy for repetitive tasks, but still hit-or-miss.

What is MCP?

MCP Examples

• A suite of specialized MCP servers for AWS:
  • Saves the cost of having all the AWS docs in your own context
• Use Playwright from your AI Tools
  • Control a browser and grab the context from various web pages

In practice

• Connect your AI assistant to AWS MCP servers
• Ask natural language questions about AWS services
• Get contextually accurate answers based on latest documentation
• Generate AWS CLI commands, CloudFormation templates, or IAM policies
• Troubleshoot AWS-specific issues with current best practices

DEMO: The Prompt

This project was bootstrapped with scaf and has a NextJS frontend in the frontend dir and a Django backend in the backend dir.

The scaf template only supports a GraphQL API. Refactor the app to use a REST API.

Tool introduction: Aider

• Developed by Paul Gauthier
• Open-source (GitHub: paul-gauthier/aider)
• Supports multiple LLM models (OpenAI GPT-4, Claude, Llama)
• Semi-agentic with git integration
• No MCP support currently
• Supports /voice interactions
• Use Multiple Models in the same session

DEMO: Aider

• Specify conventions in CONVENTIONS.md
• Use different models for architect and edit mode simultaneously
• Use external editor with /editor
• Run commands and add to output with /run
• Show cost with /tokens
• Clear context with /clear
• Start with --lint-command and --test-command run your test suite after each time the AI edits your code

Tool introduction: Goose

• Developed by Block Inc. (formerly Square)
• Open-source (GitHub: block/goose)
• Supports multiple LLM models (OpenAI, Claude, Ollama)
• Fully agentic with integrated tooling
• Supports MCP
• Supports OpenRouter! (https://openrouter.ai)

DEMO: Goose

• Specify conventions in .goosehints: Global: ~/.config/goose/.goosehints Local: .goosehints
• Session support: Start a session: goose session -n rest-api Exit a session: type exit Resume session: goose session -r rest-api
• Permission Modes: Completely Autonomous / Manual Approval / Smart Approval / Chat Only
• Clear context by exiting /exit

Tool introduction: Claude Code

• Developed by Anthropic
• Proprietary model and tooling
• Uses only Claude models (Claude 3 Opus/Sonnet/Haiku)
• Fully agentic with reasoning capabilities
• Supports MCP (Model Context Protocol)

DEMO: Claude Code

• Allow tools: claude config add allowedTools "Bash(git:*),Bash(cat:*),Bash(grep:*)"
• Specify conventions in CLAUDE.md
• Doesn’t use git to commit changes. TIP: Ask it to “Review the staged changes with git diff --staged and git commit using conventional commit standard”
• Show cost with /cost
• Compact and clear context with /compact and /clear

Tool introduction: Cursor

• Developed by Cursor team
• Proprietary editor with open-source components
• Supports both OpenAI and Anthropic models
• Fully agentic with project navigation
• Supports MCP

DEMO: Cursor

• Specify conventions in Cursor Rules: ./cursor/rules https://docs.cursor.com/context/rules-for-ai
• Explore-Plan-Build loop

Tool Introduction: Devin

• Developed by Cognition Labs
• Closed-source, commercial tool (not open-source)
• Marketed as the “first AI software engineer”
• Fully autonomous execution (planning, coding, testing, deployment)
• No MCP support; tightly integrated proprietary stack
• Focused on end-to-end task delivery vs. code assistance

Demo: Devin

• Provide task in natural language: “Build a web app for X”
• Devin creates repo, chooses stack, and scaffolds project automatically
• Runs code, fixes errors, and deploys without human intervention
• Interfaces with issue trackers and CI/CD pipelines directly
• Tradeoff: less user control, harder to audit/debug than IDE/CLI-first tools

Agentic Coding Models

Tool Comparison

Key Takeaways

• No single assistant is best for every workflow
• MCP is enabling richer, more context-aware coding
• Open source tools are catching up fast
• Try several and see what fits your style!

Talk To Us