Jim Bennett @jimbobbennett.dev · 07/08/2026How do you trust agents before they hit production? At @arize.bsky.social's Observe 2026, Salesforce's Manjit Singh walked through evaluating agents across the lifecycle — single agents to orchestrators & handoffs. Sketchnoted 👇 🔗 Video link in the comments. 100
Jim Bennett @jimbobbennett.dev · 05/08/2026"Everyone is an AI agent builder — if you let them." At @arize.bsky.social's Observe 2026, CrewAI shared enterprise lessons on where agent ROI shows up and how to scale building across an org. Sketchnoted 👇 🔗 Video link in the comments. 110
Jim Bennett @jimbobbennett.dev · 03/08/2026As agents become digital coworkers, access control built for humans starts to break. At @arize.bsky.social's Observe 2026, WorkOS's Michael Grinich explored the identity & security model for autonomous agents. Sketchnoted 👇 🔗 Video link in the comments. 100
Jim Bennett @jimbobbennett.dev · 31/07/2026What does agent adoption actually look like in production? At @arize.bsky.social's Observe 2026, Mastra shared patterns from thousands of teams — what separates shipped agents from stuck prototypes. Sketchnoted 👇 🔗 Video link in the comments. 100
Jim Bennett @jimbobbennett.dev · 29/07/2026From experimentation to production, agents need whole-lifecycle platforms. At @arize.bsky.social's Observe 2026, Microsoft's Sebastian demoed building, deploying, evaluating & governing agents with Microsoft Foundry. Sketchnoted 👇 🔗 Video link in the comments. 100
Jim Bennett @jimbobbennett.dev · 27/07/2026Scaling agents from prototype to production is an infrastructure problem. At @arize.bsky.social's Observe 2026, Anyscale's Robert Nishihara explained how Ray scales RL, inference & multimodal AI — and why RL is having a moment. Sketchnoted 👇 🔗 Video link in the comments. 220
Jim Bennett @jimbobbennett.dev · 24/07/2026The hardest problems in AI aren't model problems anymore — they're evaluation problems. At @arize.bsky.social's Observe 2026, Hamel Husain argued agents are bringing the data scientist back to AI engineering. Sketchnoted 👇 🔗 Video link in the comments. 100
Jim Bennett @jimbobbennett.dev · 22/07/2026What are the smartest AI investors seeing before everyone else? At @arize.bsky.social's Observe 2026, Jaya Gupta of Foundation Capital shared where VC is flowing across the AI stack. Sketchnoted the fireside 👇 🔗 Video link in the comments. 100
Jim Bennett @jimbobbennett.dev · 20/07/2026When a hallucination is a regulatory + financial risk, responsible AI gets real. At @arize.bsky.social's Observe 2026, BlackRock shared how it deploys AI to support pros managing trillions — with real guardrails & evaluation. Sketchnoted 👇 🔗 Video link in the comments. 110
Jim Bennett @jimbobbennett.dev · 17/07/2026With autonomous agents, observability shifts from "what happened" to "why did the agent do that." At @arize.bsky.social's Observe 2026, AWS's Nate Slater explored how agentic AI changes observability. Sketchnoted 👇 🔗 Video link in the comments. 110
Jim Bennett @jimbobbennett.dev · 15/07/2026Two of the fastest-growing open-source agent projects, one conversation. At @arize.bsky.social's Observe 2026, OpenClaw & Nous Research debated where agent frameworks go next — memory, skill creation, long-term learning. Sketchnoted 👇 🔗 Video link in the comments. 120
Jim Bennett @jimbobbennett.dev · 13/07/2026"AI agents need specs, not prompts." At @arize.bsky.social's Observe 2026, George Zhang argued the engineer's real job is specifying the hill agents climb — tests, evals, rubrics, constraints. Sketchnoted 👇 🔗 Video link in the comments. 100
Jim Bennett @jimbobbennett.dev · 10/07/2026What happens when a leading AI coding company turns its product inward? At @arize.bsky.social's Observe 2026, Cursor shared how it uses agents, evals & agent-powered workflows to build Cursor itself. Sketchnoted 👇 🔗 Video link in the comments. 130
Jim Bennett @jimbobbennett.dev · 08/07/2026"Kubernetes is not your sandbox." At @arize.bsky.social's Observe 2026, the Daytona team argued K8s wasn't built for agent workloads, and walked through what agent-native infrastructure actually needs. Sketchnoted 👇 🔗 Video link in the comments. 100
Jim Bennett @jimbobbennett.dev · 06/07/2026Building agents is harder than the demos make it look. At @arize.bsky.social's Observe 2026, Anthropic's Marius Buleandra shared why agent failures compound in production, how to design evals that catch them, and why human review still matters. Sketchnoted 👇 🔗 Video link in the comments. 110
Jim Bennett @jimbobbennett.dev · 03/07/2026How do you improve a product with hundreds of millions of users? At @arize.bsky.social's Observe 2026, OpenAI's Stuart Sy showed how ChatGPT turns fragmented 'vibes' into evidence + action. I sketchnoted the talk 👇 🔗 Video link in the comments. 100
Jim Bennett @jimbobbennett.dev · 01/07/2026Agents stopped being demos this year — they're shipping code, fixing bugs, and running real workflows. In @arize.bsky.social's Observe 2026 keynote, the founders lay out what's next. I sketchnoted the whole keynote 👇 🔗 Video link in the comments. 100
Jim Bennett @jimbobbennett.dev · 19/05/2026Every AI agent deployed inside an enterprise sometimes quietly disagrees with the humans running the same process. The written policy says one thing. The institutional knowledge sitting in Slack threads, hallway conversations, and the heads of long-tenure employees says another. 🧵 1/3 100
Jim Bennett @jimbobbennett.dev · 24/04/2026Why do I run? Currently I’m running for Sage House, a dementia support charity helping my dad and other folks live with dementia. Sponsor me for the @londonmarathon.bsky.social! 2026tcslondonmarathon.enthuse.com/pf/james-ben... 000
Jim Bennett @jimbobbennett.dev · 18/01/2026In 99 days I’m running the 2026 TCS London Marathon to raise money for Sage House, a charity that helps folks with dementia like my Dad. Please sponsor me as I try to raise $10,000 for this charity! 2026tcslondonmarathon.enthuse.com/pf/james-ben... 090
Jim Bennett @jimbobbennett.dev · 15/10/2025Same! Undecided to build it now or wait till closer to Christmas 100
Jim Bennett @jimbobbennett.dev · 30/08/2025Private repos were turned public, secrets were stolen, repos were renamed. How is this not a fucking security or privacy incident? 100
Jim Bennett @jimbobbennett.dev · 15/08/2025TFW you go to a @kcdc.bsky.social session in RenPy and decide your plane ride home will be playing with then, then @abt.bsky.social gives you a copy of her book and you also want to read that. 040
Jim Bennett @jimbobbennett.dev · 13/08/2025Not saying my @kcdc.bsky.social Star Wars themed workshop was the best, but here’s one of the attendees warming up the audience playing Star Wars on the accordion. 020
Jim Bennett @jimbobbennett.dev · 13/08/2025Checking my fit before teaching a workshop on creating a copilot at @kcdc.bsky.social. Clippy FTW! 150
Jim Bennett @jimbobbennett.dev · 12/08/2025A WH Smith’s at MCI airport! But not a beano in sight. 110
Jim Bennett @jimbobbennett.dev · 06/08/2025Well I don’t think I’ll be coming to eat at this restaurant at any point 040
Jim Bennett @jimbobbennett.dev · 18/07/2025TFW you get a random shoutout during a @devrelcon.bsky.social talk! 031
Jim Bennett @jimbobbennett.dev · 24/06/202540 plus appreciation post! Reskeet with a pic if you’re on the right side of 40. 47! 020
Jim Bennett @jimbobbennett.dev · 08/06/2025Quick but very hot 10k at the big backyard run in Marymoor park. 4th in my age group which is nice. 010
Jim Bennett @jimbobbennett.dev · 08/06/2025Just had a fun vodka tasting with a friend at the Duvall Distillery. Highly knowledgeable patron sharing how he makes his vodka, lots of interesting flavors, and some random woman trying desperately to chat me and my friend up. 010
Jim Bennett @jimbobbennett.dev · 07/06/2025Great to see the 501st legion at Snohomish Pride today. 010
Jim Bennett @jimbobbennett.dev · 05/06/2025Quick stretch before talking about evaluation driven development of genetic apps at the AI engineer worlds fair. 181
Jim Bennett @jimbobbennett.dev · 03/06/2025On my way to SF. If you’re attending the AI Engineering worlds fair and want ti learn why your AI needs reliability and evaluations come say hi at the @rungalileo.bsky.social booth. 011
Jim Bennett @jimbobbennett.dev · 02/06/2025The new Lego Jango Fett ship is a very fun build! Probably the most fun one in a long time. Solidly built, interesting construction techniques, and some fun details. 020
Jim Bennett @jimbobbennett.dev · 24/05/2025It’s Saturday, I’m sitting outside a brewery with a beer and working on a deck to teach 4th graders some tips to pitching a product as they are doing a shark tank project to round out their year! Almost perfect except my leg hurts after decking it on a trail run earlier. 140
Jim Bennett @jimbobbennett.dev · 20/05/2025You at #msbuild? Here’s all the @rungalileo.bsky.social fun you can expect today. 132