30초 요약
Matthew Berman presents Journey, a project he says he built to make complete agent workflows easier to discover and replicate. He describes kits as installable packages combining skills, tools, context, tests and examples. This short introduction reflects the creator's description, not an independent assessment of the project's effectiveness.
- 1A creator's projectBerman introduces Journey as a project he has been building and asks for feedback.
- 2The sharing problemHe says complete agent workflows are difficult to discover and reproduce across agents.
- 3Installable kitsHe describes kits that combine the tools, context and tests needed for an end-to-end workflow.
핵심 정리
- Berman created Journey to help people share and reproduce agent workflows.
- He describes a kit as a packaged workflow containing skills, tools, context, tests and failure examples.
- The project is presented as a registry where people can discover use cases created by others.
- The video is an introduction by the project's creator and asks for feedback, not a comparative evaluation.
챕터별로 다듬은 전문 읽기
The workflow-sharing problem
Berman explains why people want concrete agent use cases and why reproducing them can be difficult.
I built a project called Journey and would like feedback. The problem I want to solve is that, once you have built a workflow for one agent, it can be difficult to hand the entire workflow to another agent.
When I made videos about OpenClaw, viewers frequently asked what I actually used it for. Discovering practical examples is valuable, but reproducing another person's agent setup can be harder still.
Journey's kits
He describes a registry of installable workflow packages and the components he says they contain.
I describe Journey as a registry for end-to-end workflows called kits. A kit packages an installable workflow for an agent, including skills, tools, learnings, memories, services, tests and failure examples. The aim is to avoid rebuilding the same workflow from scratch; this is the creator's description of the project rather than an independent test.
같은 채널의 다른 글
34:21EN
Matthew Berman· 2026년 10월 27일Matthew Berman Examines Anthropic’s IPO Filing, AI Growth and GovernanceMatthew Berman, Sam Altman · Forward FutureThe presenter reviews the S-1’s financial metrics, compute strategy and voting structure while questioning the tension between rapid AI development and safety.
0:26ENMatthew Berman· 2026년 10월 25일Sam Altman on Human Values and Problem-Solving in an AI WorldSam Altman · OpenAIIn a short interview excerpt, Altman considers the enjoyment of solving hard problems and the human role in interpreting results.
0:36ENMatthew Berman· 2026년 10월 25일Kimi K3.1 and a Rubik’s Cube Solver DemonstrationMatthew Berman · Forward FutureMatthew Berman shows a scrambled virtual cube being solved and gives the Kimi K3.1 test a favorable assessment.
0:21ENMatthew Berman· 2026년 10월 24일An AI-Generated Kimi Benchmark Chart Used Invented ScoresMatthew Berman · Forward FutureMatthew Berman asks for a graph of Kimi K3.1 Pro benchmarks, then discovers that the displayed figures are illustrative placeholders.
25:50ENMatthew Berman· 2026년 10월 24일Kimi K3.1 Pro Tested: Strong 3D Demos, Uneven Results and Competitive PricingMatthew Berman · Forward FutureMatthew Berman tests the open-weight model on coding, 3D rendering and visual explanations, then compares benchmark results and prices.
32:20ENMatthew Berman· 2026년 10월 23일Who Is Local AI For? The Costs, Trade-offs and a Hybrid FutureMatthew Berman · Forward FutureMatthew Berman weighs data control and independence against hardware cost, setup complexity and inference speed.