AI Agents Built Around Your Knowledge
Turn your private knowledge and expertise into AI agents that can answer questions, assist workflows, and support real-world tasks.
Built for trusted knowledge and guided workflows.
Turn your private knowledge and expertise into AI agents that can answer questions, assist workflows, and support real-world tasks.
Built for trusted knowledge and guided workflows.
Why not just use ChatGPT directly?
AI tools like ChatGPT already have tremendous knowledge, language and reasoning capabilities, especially when you provide the right context, documents, or information together with your question or task.
But as private knowledge grows and workflows become more specialized, ad hoc prompting becomes difficult to manage. Real-world domains often need trusted knowledge retrieval, reusable workflows, structured reasoning, and consistent ways to handle recurring tasks.
Answer questions about guest services, local transportation, and operational rules.
Review reports, identify potential risks, and support safety-related decisions.
Remember stories, personal notes, creative ideas, and experiences accumulated over time.
AI agents can focus on trusted retrieval, guided tasks, or a combination of both.
For known questions, the agent retrieves grounded answers directly from your structured knowledge base, sometimes without calling an LLM.
Example: “How to use Wifi?”
For complex requests, the agent applies reusable expert intents to guide LLM reasoning and task execution.
Example: “Select the appropriate expert intent, then apply it to the task data.”
i80agent supports different agent patterns. Some requests go directly to trusted knowledge. Others require guided task processing. More advanced use cases can coordinate multiple agents through an orchestrator.
Retrieval and task capabilities can work independently or together. More advanced systems may coordinate multiple agents through an orchestrator.
i80agent is designed for domains where the most important knowledge lives inside private documents, workflows, business processes, and domain expertise.
Cooking stories, memories, journals, creative processes, research notes, and personal archives.
Hotel guest assistants, restaurant knowledge systems, service operations, and internal SOP access.
Document review, risk analysis, workflow guidance, and operational support.
Internal support agents, HR onboarding, product documentation, and team knowledge systems.
What started as a personal experiment has grown into a broader exploration of how domain-specific AI agents can be built, refined, and eventually made accessible to others.
I am building this in my spare time alongside a regular job, so progress comes in waves and moves more slowly than I would like. But life, cooking, travel and curiosity are also part of the journey.
Built the first working knowledge agent based on my personal cooking stories.
Extended the same architecture to a real-world hotel assistant use case.
Rebuilt the Alex Cooking agent into the Spontaneous Cooking by Alex set-menu dinner experience.
Continued improving retrieval quality, answer structure, embeddings, and practical usability.
Paused active development to rethink the foundation as AI tools and capabilities evolved faster than expected.
Began rebuilding i80agent using ChatGPT, OpenAI Codex, Claude Chat, and Claude Code, with a stronger focus on Retrieval Agents, Workflow Agents, and Orchestrator Agents.
Expanded the i80agent concept beyond knowledge retrieval by introducing expert workflows and guided AI reasoning. Rebuilt the i80.com website using OpenAI Codex without writing code manually,
The goal is to evolve i80agent into a generic platform for building domain-specific AI agents that can retrieve knowledge, apply expert workflows, and coordinate real tasks.
It started with a simple realization: LLMs are powerful, but they do not know your personal or business knowledge.
What began with cooking stories and personal memory evolved into a broader vision: AI agents grounded in domain knowledge, reusable workflows, and real-world expertise.
How It All BeganA living journal of experiments, notes, and lessons learned while exploring domain-specific AI.
A practical framework for deciding when a knowledge agent should look up facts, apply expert workflows, or combine both.
How surface, essence, and philosophy can improve LLM use and help design better knowledge agents.
A practical reflection on why the concept behind RAG still matters, even as naive RAG becomes insufficient for domain-specific AI agents.
Why fast AI coding breaks as systems grow, and how spec-driven development helps AI-generated software scale.
A personal reflection on writing less code, designing more intent, and moving toward structured natural language.
A comparison of chunk-based and query-focused embedding strategies for private-domain agents.
Research notes on how embedding construction affects semantic search precision.
A comparison of query-focused embeddings vs. traditional embedding strategies for domain-specific AI agents.
A setup note from the first phase of the i80agent journey, when I was getting the Python foundation in place.
i80agent is still evolving.
Many of the ideas behind i80agent are being explored through real-world projects and guided implementations. The goal is not just to solve individual problems, but to discover reusable patterns that can eventually evolve into a broader agent platform.
If you have real-world use cases or are exploring domain-specific AI, I’d love to connect and exchange ideas.
Get in Touch