Supabase's Pedro Rodrigues on AI Agents and Context

Pedro Rodrigues from Supabase discusses how 'Skills' and the MCP framework improve AI agent context and performance. Learn key principles for building effective product skills.

9 min read
Pedro Rodrigues presenting on AI agents and Supabase skills at AI Engineer Europe.
Image credit: AI Engineer Europe / Supabase· AI Engineer

Pedro Rodrigues, an AI tooling engineer at Supabase, recently presented at AI Engineer Europe on the topic of "Combine Skills and MCP to Close the Context Gap." His talk focused on the crucial role of providing AI agents with the right guidance and context to perform tasks effectively.

Supabase's Pedro Rodrigues on AI Agents and Context - AI Engineer
Supabase's Pedro Rodrigues on AI Agents and Context — from AI Engineer

Visual TL;DR. AI Agent Guidance Gap addressed by Supabase Skills. Supabase Skills works with MCP Framework. MCP Framework enables Effective AI Agents. Supabase Skills example of Teach AI Supabase. Teach AI Supabase uses Docs over SSH. Docs over SSH improves Effective AI Agents. Effective AI Agents leads to Get Started. Supabase Skills evaluated by Evaluate Skill Performance.

  1. AI Agent Guidance Gap: agents are smart but need the right guidance to perform tasks
  2. Supabase Skills: folders with instructions, scripts, and resources for agents to load
  3. MCP Framework: framework to improve AI agent context and performance
  4. Teach AI Supabase: writing Supabase skills to teach agents about the product
  5. Docs over SSH: experimental approach for providing context to AI agents
  6. Effective AI Agents: closing the context gap for better agent performance
  7. Evaluate Skill Performance: measuring how well AI agents perform with skills
  8. Get Started: principles for building and implementing AI agent skills
Visual TL;DR
Visual TL;DR — startuphub.ai AI Agent Guidance Gap addressed by Supabase Skills. Supabase Skills works with MCP Framework. MCP Framework enables Effective AI Agents. Effective AI Agents leads to Get Started addressed by works with enables leads to AI Agent Guidance Gap Supabase Skills MCP Framework Effective AI Agents Get Started From startuphub.ai · The publishers behind this format
Visual TL;DR — startuphub.ai AI Agent Guidance Gap addressed by Supabase Skills. Supabase Skills works with MCP Framework. MCP Framework enables Effective AI Agents. Effective AI Agents leads to Get Started addressed by works with enables leads to AI Agent GuidanceGap Supabase Skills MCP Framework Effective AIAgents Get Started From startuphub.ai · The publishers behind this format
Visual TL;DR — startuphub.ai AI Agent Guidance Gap addressed by Supabase Skills. Supabase Skills works with MCP Framework. MCP Framework enables Effective AI Agents. Effective AI Agents leads to Get Started addressed by works with enables leads to AI Agent Guidance Gap agents are smart but need the rightguidance to perform tasks Supabase Skills folders with instructions, scripts, andresources for agents to load MCP Framework framework to improve AI agent context andperformance Effective AI Agents closing the context gap for better agentperformance Get Started principles for building and implementingAI agent skills From startuphub.ai · The publishers behind this format
Visual TL;DR — startuphub.ai AI Agent Guidance Gap addressed by Supabase Skills. Supabase Skills works with MCP Framework. MCP Framework enables Effective AI Agents. Effective AI Agents leads to Get Started addressed by works with enables leads to AI Agent GuidanceGap agents are smartbut need the rightguidance to perform… Supabase Skills folders withinstructions,scripts, and… MCP Framework framework toimprove AI agentcontext and… Effective AIAgents closing the contextgap for betteragent performance Get Started principles forbuilding andimplementing AI… From startuphub.ai · The publishers behind this format
Visual TL;DR — startuphub.ai AI Agent Guidance Gap addressed by Supabase Skills. Supabase Skills works with MCP Framework. MCP Framework enables Effective AI Agents. Supabase Skills example of Teach AI Supabase. Teach AI Supabase uses Docs over SSH. Docs over SSH improves Effective AI Agents. Effective AI Agents leads to Get Started. Supabase Skills evaluated by Evaluate Skill Performance addressed by works with enables example of uses improves leads to evaluated by AI Agent Guidance Gap agents are smart but need the rightguidance to perform tasks Supabase Skills folders with instructions, scripts, andresources for agents to load MCP Framework framework to improve AI agent context andperformance Teach AI Supabase writing Supabase skills to teach agentsabout the product Docs over SSH experimental approach for providingcontext to AI agents Effective AI Agents closing the context gap for better agentperformance Evaluate Skill Performance measuring how well AI agents perform withskills Get Started principles for building and implementingAI agent skills From startuphub.ai · The publishers behind this format
Visual TL;DR — startuphub.ai AI Agent Guidance Gap addressed by Supabase Skills. Supabase Skills works with MCP Framework. MCP Framework enables Effective AI Agents. Supabase Skills example of Teach AI Supabase. Teach AI Supabase uses Docs over SSH. Docs over SSH improves Effective AI Agents. Effective AI Agents leads to Get Started. Supabase Skills evaluated by Evaluate Skill Performance addressed by works with enables example of uses improves leads to evaluated by AI Agent GuidanceGap agents are smartbut need the rightguidance to perform… Supabase Skills folders withinstructions,scripts, and… MCP Framework framework toimprove AI agentcontext and… Teach AI Supabase writing Supabaseskills to teachagents about the… Docs over SSH experimentalapproach forproviding context… Effective AIAgents closing the contextgap for betteragent performance Evaluate SkillPerformance measuring how wellAI agents performwith skills Get Started principles forbuilding andimplementing AI… From startuphub.ai · The publishers behind this format

Understanding the "Skill Issue"

Rodrigues began by highlighting a common challenge in AI agent development: agents are smart, but they need the right 'guidance.' This guidance comes in the form of 'Skills,' which are essentially folders containing instructions, scripts, and resources that agents can discover and dynamically load to complete tasks. These skills are designed to address specific needs, such as security pitfalls, stale knowledge, or missing workflows.

Related startups

He explained that Supabase has been actively working on building these skills for their product. The process involved writing a Supabase skill, which meant teaching AI agents about the Supabase product. Rodrigues noted that this endeavor was more complex than his previous experience writing his master's thesis, emphasizing the challenges in creating comprehensive and effective documentation for AI agents.

Principles for Building Effective AI Agent Skills

Rodrigues outlined three key principles for building successful product skills for AI agents:

  • Describe intent, not means: Instead of telling agents how to do something, it's more effective to tell them what needs to be achieved and where to find the information. This involves providing clear instructions and pointing them to the right resources. For example, instead of detailing a specific search query, guide the agent to search Supabase documentation.
  • If it can be skipped, it will be: This principle emphasizes the importance of including critical information directly within the skill file (inline) if it's essential and unlikely to change. Reference files are optional, but agents should be able to skip them if they are not needed. Security rules, for instance, are not optional and should be included inline.
  • Be opinionated: Rodrigues stressed that product teams know their products best and should encode workflows that make sense for their specific use cases. This means being decisive about how agents should interact with data, such as using direct SQL queries for certain tasks or running advice before making changes.

Supabase Docs over SSH: An Experimental Approach

The presentation also touched upon an experimental feature: Supabase Docs over SSH. This offers a more intuitive way for agents to query documentation using a familiar bash interface. The idea is to allow agents to interact with documentation as if it were a local file system, enhancing their ability to retrieve and process information relevant to Supabase. Rodrigues mentioned that this feature is still experimental and they are actively seeking feedback.

Evaluating Skill Performance

To measure the effectiveness of their skills, Supabase conducted evaluations across various scenarios. They tested six Supabase-specific scenarios, four agent-only scenarios, and three test conditions. The evaluations compared a baseline performance, an 'MCP Only' condition (likely referring to a specific AI model or framework), and an 'MCP + Skill' condition. The results indicated that skills significantly improved agent performance across different models and tasks, particularly in areas like code generation and understanding complex data schemas.

Rodrigues highlighted that the data clearly shows that skills, when properly implemented, are crucial for bridging the context gap and enabling AI agents to perform tasks more accurately and efficiently. He encouraged the audience to consider how they could apply these principles to build their own product skills.

Getting Started with Supabase Skills

For those interested in learning more or getting started with Supabase agent skills, Rodrigues pointed to the Supabase blog and their GitHub repository. He also mentioned an ongoing giveaway where attendees could win a Mac Mini by scanning a QR code and signing up for Supabase. The presentation concluded with a Q&A session, where Rodrigues addressed questions about the practical implementation and distribution of these skills within organizations.

© 2026 StartupHub.ai. All rights reserved. Do not enter, scrape, copy, reproduce, or republish this article in whole or in part. Use as input to AI training, fine-tuning, retrieval-augmented generation, or any machine-learning system is prohibited without written license. Substantially-similar derivative works will be pursued to the fullest extent of applicable copyright, database, and computer-misuse laws. See our terms.