
To everyone who joined from SF, London, and beyond: your curiosity and engagement made the day 🙏 We look forward to continuing these conversations and building on the connections we made 🩵 Join EvalEval: evalevalai.com/
✓We are a researcher community developing scientifically grounded research outputs and robust deployment infrastructure for broader impact evaluations.

To everyone who joined from SF, London, and beyond: your curiosity and engagement made the day 🙏 We look forward to continuing these conversations and building on the connections we made 🩵 Join EvalEval: evalevalai.com/

Huge thanks to our panelists for sharing their experiences and perspectives 🎤: Alan Aqrawi, Mick Yang, @CFGeek, @RayanKrishnan, @rtorney, John G, @struthious, Samira Nedungadi, @irenetrampoline, Rumman Chowdhury, @LamaSaouma, and @kevinlwei

Thanks also to everyone who worked on programming, outreach, logistics, and community-building 🛠️: @aspenkhopkins, @UsmanGohar, Matthew Kennedy, @evijit, @batznerjan, @IreneSolaiman, @BlancheMinerva, @AnkaReuel, and @prpaskov

Thank you to @SachinPendse for hosting us at @UCSF 🏛️, and to @kevinlwei and Michelle Lin for making the London satellite possible. Special thanks to @Poindexter_Labs for collaborating with us on the satellite event 🤝

Special thanks and kudos to @3rdcultureme and Jennifer Mickel 🙌 who led this effort impeccably! @3rdcultureme conceived the idea and led the vision, agenda, panels, and speaker engagement. Jenn shaped the program and ran planning and logistics ✨

About 60–65 people joined in person at UCSF 🌉, and another 40 joined virtually from around the world 💻, including a London satellite gathering at the GovAI office 🇬🇧 Even at the end of a full Saturday, the conversations were still going strong 🔥

💡This started as an idea just 6 weeks ago. On Saturday it became a day of discussion on the future of embedded AI evaluations, the challenges of running rigorous, independent evals, and how that work can inform accountability and governance ⚖️

🎆 This past Saturday we held our first microconference on Embedded Evaluators in Practice, with attendees across at least three continents. A huge thank you to everyone who made the 2026 Embedded Evals Microconference possible!! Read what happened🧵👇

To everyone who joined from SF, London, and beyond: your curiosity and engagement made the day 🙏 We look forward to continuing these conversations and building on the connections we made 🩵 Join EvalEval: evalevalai.com/

Huge thanks to our panelists for sharing their experiences and perspectives 🎤: Alan Aqrawi, Mick Yang, @CFGeek , @RayanKrishnan, @rtorney, John G, @struthious, Samira Nedungadi, @irenetrampoline , Rumman Chowdhury, @LamaSaouma, and @kevinlwei .

Thanks also to everyone who worked on programming, outreach, logistics, and community-building 🛠️: @aspenkhopkins, @UsmanGohar, Matthew Kennedy, @evijit, @batznerjan, @IreneSolaiman, @BlancheMinerva, @AnkaReuel, and @prpaskov .

Thank you to @SachinPendse for hosting us at @UCSF 🏛️, and to @kevinlwei and Michelle Lin for making the London satellite possible. Special thanks to @Poindexter_Labs for collaborating with us on the satellite event 🤝

Special thanks and kudos to @3rdcultureme and Jennifer Mickel 🙌 who led this effort impeccably! @3rdcultureme conceived the idea and led the vision, agenda, panels, and speaker engagement. Jenn shaped the program and ran planning and logistics ✨

About 60–65 people joined in person at UCSF 🌉, and another 40 joined virtually from around the world 💻, including a London satellite gathering at the GovAI office 🇬🇧 Even at the end of a full Saturday, the conversations were still going strong 🔥

Super special thanks to @SachinPendse for making this all possible and hosting us at @UCSF 🤩

Organizing team and friends: @3rdcultureme, Jennifer Mickel, @evijit, @IreneSolaiman, @BlancheMinerva, @UsmanGohar, @batznerjan, Matthew Kennedy, Aspen Hopkins, @prpaskov, @AnkaReuel, @kevin_klyman