A SciOS Program
Amplify your capabilities.
Automate the tedious.
Make more room for discovery.
A 4-week intensive built around your research. Learn to build harnessed agent-chain workflows from your own data, processes, and problems.
You bring your real problems. Your grant writing, your data pipelines, your lab processes, your software needs — anything keeping you from your research. Over four weeks, you build harnessed agent-chain workflows that solve them.
Structure your lab and work into modules accessible by AI agents. Learn how and when to use these modules as context to optimize your work with agents. Turn your needs into comprehensive specs on which agents can execute again and again.
Encode your repeatable processes and preferences as one-command automations. Assign these automations personalities, directives, specialties, and constraints. Learn when to deploy them, and when your judgment must stay present.
Chain skills and agents into multi-step automations. Build orchestrators, checkpoints, and systems that enable multi-day progressive implementation.
Build real automations, test them against your actual work, and learn the techniques that make them excel. Every session ends with something you made.
Every session uses your real problems as the material. Your workflows become the lessons.
Best practices cross domains. Your cohort brings diverse fields and specialties together, surfacing techniques you’d never find working alone.
Every session ends with something you built and can use right away.
Your Knowledge Base
You'll Build
A knowledge base that gives AI agents full context on your lab, your research, and your work
You'll Learn
How LLMs work, how to structure conversations with them, and how to organize your work so agents can navigate it
Specs & Skills
You'll Build
A detailed spec of your workflow and your first working automations
You'll Learn
How to write specs precise enough for agents to execute, and how to encode your processes as reusable one-command skills
Agents
You'll Build
Agents that handle complex tasks independently and report back with results
You'll Learn
How to give agents their own workspace, how to delegate complex tasks to independent agents, and how to assess and improve your automations
Harnesses
You'll Build
A complete system blueprint for automating your workflow end to end
You'll Learn
How to chain skills and agents into orchestrated multi-step automations, how to utilize machine and human checkpoints, and how to design for continuous improvement
Community
After the intensive, you join a community maintained and facilitated by SciOS. Monthly calls, shared resources, and deep dives into verticals like Data, Writing, Knowledge Management, Literature Review, and Software. The 4 weeks end. The learning doesn't.
PIs, postdocs, PhD students — anyone doing the research and spending too much time on the work around it.
Research engineers, data scientists, librarians — the people building the software, pipelines, and systems research depends on.
Administrators, compliance officers, grants managers — the people who keep institutions running.
LLMs amplify and streamline every element of the scientific enterprise. If you want to learn how to use them effectively, this is for you.
Cohort 1 is free. Space is limited to 8–12 people.
