June 17, 2025
Enterprise AI, Phase 2 Labs

Parsing, Matching, and Acting with Context: A Foundation for the Future of AI Labor Unlocking New Possibilities with Multi-Modal AI The Resume Sizzler, developed by P2 Labs, is more than a resume builder—it's a glimpse into the future of applied intelligence. A few years ago, extracting meaningful insights from unstructured data at scale was nearly impossible. Built on advanced multi-modal AI, this system transforms unstructured data into actionable insights, enabling businesses to automate complex workflows, extract meaning from documents, and make smarter...

BY
0
May 23, 2025
Engineering, Phase 2 Labs

What is the Sequential Thinking MCP Server from Anthropic? The Sequential Thinking MCP Server is one of many Reference MCP Servers released by Anthropic to demonstrate the capabilities of their MCP protocol. This server in particular serves the purpose of providing structure to help augment a given AI’s thinking process. The Sequential Thinking server does not do any of it’s own “thinking” or decomposing of a problem. Instead it deterministically receives structured input from an AI, validates the data in the...

BY
1
May 22, 2025
Artificial Intelligence, Phase 2 Labs

Office Manager Magic, Powered by Multi-Modal AI Introduction AI isn’t a futuristic concept, it’s practical labor, available today. Not just for call centers or simple tasks, but for real, dynamic work that used to require a person. This isn’t about replacing people; it’s about helping teams do more with less. The following example highlights how a LangGraph-powered system is already handling quoting and scheduling—tasks that apply to nearly any business. The bigger point: AI agents are here, and they’re ready to do...

BY
0
May 12, 2025
Phase 2 Labs

In a recent exploration by Braxton Nunnally from Phase 2 Labs, it was examined how Zep—a memory management tool—can help AI systems retain and recall important information over time. This kind of “organizational memory” allows AI to move beyond one-off interactions and instead offer consistent, informed responses that build on past context. Common Business Pain Point: "Our AI tools don’t retain context or past interactions—users repeat themselves, teams lose knowledge, and we miss opportunities to respond more intelligently." What the Team Learned: AI Needs...

BY
0
May 12, 2025
Phase 2 Labs

In a recent analysis by Alan Ramirez, Phase 2 Labs explored how organizations can reduce the operational costs of Large Language Models (LLMs) by implementing context caching—a method that stores and reuses the static parts of AI prompts. This strategy minimizes redundant processing, leading to significant cost savings. Common Business Pain Point: “Our AI tools are powerful, but the cost of running them is escalating quickly—especially as usage grows across departments.” What the Team Learned: Understanding Context Caching: By separating static (unchanging) and dynamic...

BY
1
April 28, 2025
Engineering, Phase 2 Labs

In today's AI-driven landscape, creating systems with long-term memory capabilities has become increasingly important. Whether you're building a customer service chatbot that remembers interactions with its users and maintaining history longer than the context window are crucial parts of a successful system. While there are many components that go into building a fully functional long-term memory solution, Zep can be a powerful tool to help developers implement long-term memory in their AI applications. What is Zep? Zep is an API-based solution that...

BY
1
April 28, 2025
Engineering, Phase 2 Labs

Introduction Large Language Models (LLMs) have revolutionized how organizations process and generate natural language content, but their operational costs can become significant at scale. One of the most effective techniques for reducing these costs is context caching, which allows reuse of static prompt components across multiple requests. This article examines how the three major AI providers—Google (Gemini), Anthropic (Claude), and OpenAI—implement context caching, with detailed analysis of their technical approaches, pricing structures, and practical limitations. The Technical Fundamentals of Context Caching When interacting...

BY
2
April 28, 2025
Engineering, Phase 2 Labs

Unless you've recently spent your free time nose-deep in GitHub repos or interrogating ChatGPT like it's a barista who got your coffee order wrong, you may not be familiar with MCP servers. That’s okay. Two weeks ago, I wasn’t either. But thanks to a casual, "Hey, can you connect Notion to our project via an MCP server?" from a teammate (and my relentless need to avoid looking clueless), I dove headfirst into the rabbit hole. What I discovered is something potentially...

BY
7
April 8, 2025
Engineering, Phase 2 Labs

Imagine you’re an inventory manager for a retail business and you need to quickly verify stock levels for an unexpected large order while away from your computer. Instead of logging into a dashboard, navigating through menus, and analyzing spreadsheets, you simply send a text message: "Do we have enough iPhones to fulfill an order for 100 units?" Within seconds, you receive a reply: "You have 157 iPhones currently in stock, so you can fulfill this order. Based on your current sales rate of...

BY
2
April 2, 2025
Engineering, Phase 2 Labs

Introduction There’s been a lot of excitement lately in our P2 Labs team about the possibilities opened up by Anthropic’s Model Context Protocol, which enables AI tools to connect to a rapidly growing range of external tools and services. One question we've been exploring: how effectively can AI-powered coding assistants handle real-world development tasks when given access to the same resources a human would? The Experiment Since we’ve also been doing some work lately updating our Resume Sizzler demo, that provided use with...

BY
2