Arcturus Labs
Building the future
of AI products
and workflows
Strategy, training, and hands-on engineering
for teams building with AI agents.
From possibility to product
Arcturus Labs can help
Product direction. AI behavior. Agentic engineering.
“The strategic assessment from Arcturus Labs was a turning point for our product. By implementing their 'participatory experience' model, we are empowering our users to guide the AI, leading to higher confidence and much better data outcomes.”
“Building a multi-agent therapist training simulator from scratch is a massive undertaking. Arcturus Labs provided the foundational architecture, a sophisticated strategy, and hands-on work that gave us the ability to train and refine our Patient, Coach, and Evaluator agents into a reliable, evidence-based training platform.”
“Arcturus Labs took a complex, email-driven process and turned it into a systematic, AI automated workflow. And the research agent cut through the noise of hospital shortages, and was able to identify substitutes in a fraction of the time it would take staff.”
“If you have the chance to bring him in for a training with your team then I would definitely recommend it and I know my colleagues would too.”
Just looking around?See what Arcturus Labs is building
- AI Can Read Neural Network Weights. I Wasn’t Ready for That.Frontier models can apparently interpret neural networks from their weights written out as text.
- My Software FactoryMy software factory is an agent skill – harness-agnostic, modular, and evolving independently across repos.
- Will OpenAI Eat Jev's Lunch?TypeSafe's Jev is a genuine breakthrough – snap judgments with calibrated probabilities instead of generated text.
- TypeSafe's Jev Trades Text Generation for Instant, Calibrated DecisionsTypeSafe's Jev skips text generation entirely, answering structured questions with calibrated probabilities in milliseconds.
- My AI Skill Edited This Video That Explains My AI SkillI had my Cursor agent watch a YouTube tutorial on AI video editing and replicate the process – packaged as an agent skill – in…
Talks, workshops, and conversations with John Berryman.
Prompt Engineering for LLMs course at AgilityFeat
AgilityFeat
Lexical Love: Rediscovering the Power of Text in RAG [John Berryman]
Jason Liu
Prompt Engineering Workshop
Hamel Husain
A Builder’s Guide to Agentic Search & Retrieval with Doug Turnbull & John Berryman
Vanishing Gradients
Patterns and Anti-Patterns For Building with AI (with John Berryman)Vanishing Gradients
He Built AI for GitHub Copilot. Now He Says We're All Doomed | John Berryman, Github Engineer
TwoSetAI
Code search, Copilot, LLM prompting with empathy and Artifacts - John Berryman, ex-GitHub Copilot
Vector Podcast
The Evals That Made GitHub CopilotHamel Husain
Prompt Engineering for LLMs: Best Practices With John Berryman of Arcturus Labs
Scaling Tech Podcast
The Dark Factory: How Twin Sun Automated Their Entire Dev Pipeline
Arcturus Labs
This Week in AI: Rethinking the Agent Harness with Eric Freeman and John Berryman
O'Reilly
You Built It With AI. How Do You Deploy It? Operate ItArcturus Labs
B.Y.O.A. – Bring Your Own AgentArcturus Labs
RAG is two things. Prompt Engineering and Search. Keep it Separate | S2 E28
How AI Is Built
Show Us Your (Agent) Skills Episode 5 - w/ John Berryman, Isaac Flath, & Matt PalmerVanishing Gradients
Zero to Agent in 30 Minutes: Build a Workflow Agent Without Code with John BerrymanO'Reilly