My OpenClaw was spending $80 a day to read my email. One config line brought it down to a few dollars. Wrote up where the money went and how observability made the fix obvious: briandouglas.me/posts/2026/0...
My OpenClaw Was Spending $80 a Day to Read My Email
My OpenClaw chief-of-staff agent was burning $80 a day in Anthropic API costs. The fix was one config line, and the only reason I found it was observability.
briandouglas.me
Claude code shared Fable is storing for sessions for 30 days because it’s useful for understand the safety of the model. My suggestion is you should save your sessions too. If you are not today, put it on paper. Here’s my AI Devcon talk on the subject lnkd.in/efQRKGTx
This link will take you to a page that’s not on LinkedIn
lnkd.in
@andrewnez.bsky.social want to join us on a podcast to talk ecosystems?
I tried training a model instead of writing a skill and have some honest results. briandouglas.me/posts/2026/0...
I Trained a Model Instead of Writing a Skill
Skills are a great way to teach an agent a pattern. I got curious whether the agent could just learn the pattern, so I tried training a model while also figuring out what RL actually is.
briandouglas.me
🎤 New episode of Open Source Ready with @bizza.pizza - we talked to @stormypeters.bsky.social about open source at Amazon, how the relationship between AI and open source is actively evolving, and the growing challenges that come with that. Check it out! www.heavybit.com/library/podc...
Open Source Ready | Ep. #37, Is AI Killing Open Source Software? with Stormy Peters | Heavybit
On episode 37 of Open Source Ready, Brian and John speak with Stormy Peters about the evolving relationship between AI and open source software.
heavybit.com
New company launched. papercompute.com/blog/introdu...
Introducing Paper Compute Co: Infrastructure for Running AI Agents in Production - Paper Compute Blog
We built Paper Compute to close the Agent Gap — the inability to prove what an agent did, audit its actions, or replay its decisions. Here's what we built and why.
papercompute.com
Raising kids in the bay is fun. Basically like a dog that speaks English eventually
Hacking on an agent orchestrator that is essentially a bunch of open source tools I like (Git, tmux, opencode and stereOS), duct taped together using Bun. The result provides an isolated workspace in a tmux session you can attach to do work, and a VM where the agent can access the workspace
I had 1,992 ESLint errors. Dispatched a sweeper agent to produce 5 parallel Claude Code sessions. Three rounds, 100% fix rate, 54 minutes. briandouglas.me/posts/2026/0...
842 Lint Errors, 5 Parallel Agents, 54 Minutes
I built a tool that fans out parallel Claude Code agents to fix lint errors across a codebase. It taught me that the hard problems aren't prompts or models. They're isolation, observability, and memor...
briandouglas.me
I used observational memory to train my Pokémon agent. briandouglas.me/posts/2026/0...
What I Learned Running 10 Pokemon Bots in 36 Seconds
How a DeepMind paper turned my Pokemon agent from 'watch and tweak' into 'run and measure.'
briandouglas.me
Claude Code crashed an hour into a session. No recovery, no history. But I had tapes running. It stores every LLM interaction in a local SQLite db. Pointed Claude at it, recovered everything, and shipped the feature. briandouglas.me/posts/2026/03/04/claude-failed-mid-session-tapes-brought-it-back/
📼 Introducing tapes: transparent AI agentic telemetry. In every single AI session or workflow, there's an incredible amount of lost information on the "what", "why", and "how". www.youtube.com/watch?v=ATeU...
I started a company.
YouTube video by John McBride
youtube.com
What does long term care for agents look like? Wrote about tapes, an open source project @johncodes.com and I have been working on these past 2 weeks. briandouglas.me/posts/2026/0...
Is product management making a comeback? 🤔 We checked in with development experts Amit Eyal Govrin, @bizza.pizza, and Alex Kurilin to dig into why and what it means to be a good product manager or product engineer in the age of AI. www.heavybit.com/library/arti...
What Makes a “Good” AI Product Manager? | Heavybit
What does product management mean in the age of AI codegen, and what does a good AI PM do? Veteran dev leaders weigh in.
heavybit.com
"There is no secure ai enclave, Neo" I continue to bang the gong on how crazy it is we're shipping and integrating all these agentic systems with critical services with nearly zero guardrails. johncodes.com/archive/2026...
there is no secure ai enclave
there is no secure ai enclave
johncodes.com
I made the joke that every Ralph needs a Super Nintendo and no one laughed, so I wrote post on it. briandouglas.me/posts/2026/0...
Wrote about the sheer amount of software that is going to be created: the software Cambrian explosion is upon us. Prepare accordingly. johncodes.com/archive/2026...
The software Cambrian explosion.
The software Cambrian explosion.
johncodes.com
Back at 98 in performance thanks to this one trick. briandouglas.me/posts/2025/1...
I Tried Edge SSR in My React Vite App
How moving to edge functions improved performance without a full rewrite.
briandouglas.me
This was a lot of fun interviewing @bizza.pizza! Thanks for letting me guest co-host @whiskey.fm! whiskey.fm/are-develope...
Are Developers Overthinking Everything? w/ Bdougie - Whiskey Web and Whatnot: Web Development, Neat - Episode 221
Recorded live at All Things Open, Robbie and guest co-host Nick Taylor talk with Bdougie (Brian Douglas) about open source’s impact on their careers, the legacy of OpenSauced, and why developer tools ...
whiskey.fm
I think I made a code rabbit clone. youtu.be/vEoABlyfwq0?...
I built my own AI code review tool called Codebunny
YouTube video by bdougie
youtu.be
Now streaming for everyone: build a web-based hotline. Watch @bizza.pizza, Pedro, @jherr.dev, Sherm, Avi, and Dibs code up custom call-in services using Twilio's ConversationRelay. Full episode: codetv.link/wdc/s2e11
Created a follow up pr for review logging github.com/bdougie/code...
feat: implement review history tracking with artifacts by bdougie · Pull Request #2 · bdougie/codebunny
Overview Implements persistent review history tracking using GitHub Actions artifacts as proposed in #1. What's New Review History Tracking Each review is saved as a GitHub Actions artifact fo...
github.com
bdougie@bizza.pizza · 10mo agoI wrote a post on how I use @continue.dev config to own my AI code review data. Looking forward to improving AI with code reviews I can fine tune. briandouglas.me/posts/2025/1...
I wrote a post on how I use @continue.dev config to own my AI code review data. Looking forward to improving AI with code reviews I can fine tune. briandouglas.me/posts/2025/1...
CodeBunny: Privacy-First AI Code Reviews with Continue
AI code reviews that run in your GitHub Actions environment, keeping your code in your repository. Built on Continue for flexible, privacy-focused code analysis.
briandouglas.me
New for @codetv.dev supporters! Build a custom hotline using Twilio ConversationRelay, featuring @bizza.pizza, Pedro, @jherr.dev, Sherm, Avi, and Dibs codetv.link/wdc/s2e11
Operators Are Standing By | Web Dev Challenge Season 2
Build a software powered phone hotline.
codetv.link
