Feiyi Workshop

An AI built for projects.

Feiyi Workshop is not a chatbot. It is an AI system built around real projects: it remembers, asks back and analyzes, working with you through nine stages to turn a question into a work.

feiyi.ai/workshop
Feiyi WorkshopPROJECTS面向课堂的 AI-IPBL 研究阶段 5 · 原型创作者的 AI 工作流实验阶段 2 · 提问MEMORYProject Memory面向课堂的 AI-IPBL 模式研究LIVE研究提问构思实验原型评审成品展示沉淀进行中访谈提纲 v3课堂观察记录评审中原型可用性测试已完成项目章程研究笔记 01概念草图AI Project Agent学生的提问总是停留在表面,怎么引导他们继续深挖?回到阶段 2 的三次讨论记录:他们其实提到过「器材为什么这样」,建议从这里追问,而不是给出答案。memory: discussion#12 · decision#3建议动作推进到评审生成评审清单plan: stage#6 · board#2 · review#1
Interface in development · placeholder visual, shipping with the first projects.

Features

One workspace for the whole project.

01

Nine-stage workflow

A clear track from inquiry to reflection. The AI knows where you are and what comes next.

workflow · 9 stages
Inquiry
Research
Concept
Experiment
Prototype
Critique
Outcome
Showcase
Reflection

02

Multi-agent collaboration

Specialized agents for analysis, suggestion and reflection relay work on the same project memory — a small team around your project.

agents · relay

agent-1

Analyze

Reads project context

agent-2

Suggest

Proposes next steps

agent-3

Reflect

Traces decisions

03

Project Memory

Every discussion, decision and revision is remembered. The agent cites your project history, not guesses.

project-memory

How do I push them to dig deeper?

Revisit the three stage-2 discussions and ask from there.

memory

discussion#12

decision#3

revision#7

04

Artifact archive

Outlines, prototypes, reports and presentations grow into an archive as the project moves.

artifacts

Research outline v3

Usability test report

Presentation deck

Project Memory

The project's lasting memory

Discussions, decisions, reflections and every revision are recorded — the project moves forward, the context never resets.

AI Project Agent

Six capabilities, one goal

Understand · Remember · Analyze · Suggest · Ask · Reflect — all in service of one thing: deepening your inquiry.

Workflow

A nine-stage project path

From research to portfolio, each stage gets support matched to its context — not one universal prompt.

Artifact & Decision

Outcomes with evidence

Behind every artifact: traceable decisions and the evidence of process.

A project path you can see

You lead the question, research and concept. Through experiment, prototype and critique, the Agent offers analysis, suggestions and pushback. The outcome and portfolio are made together.

QuestionResearchConceptExperimentPrototypeCritiqueOutcome

See how it works.

The product is being refined along the nine-stage workflow. Its first public release ships with the first projects.