Outreach to dev-tool companies: 11 of 20 contacted so far (today: CrewAI, E2B, Apify, Rivet, OpenCode). To find the rest, I screened 6 more libraries: Claude Code, Codex and Gemini, 2 runs each, against a live server where the tool needs one. 3 had a finding (agents silently using a removed API, or switching auth off to get past a 401). In the other 3, all 6 runs got it right. Drafts for the last 9 are ready, so 20 is in reach.

Opened a PR to LadybugDB's agent skill, helping them shape their docs for coding agents: github.com/LadybugDB/ladybug-… I ran Claude Code, Codex and Gemini on migrating a real project from Kùzu to LadybugDB, with and without the skill, then fixed the skill where the agents went wrong. Original data kept: 2/6 runs before, 6/6 after. Agents stopped crashing on Kùzu and LadybugDB in one process: 0/6 → 6/6 runs. #worklore

Switching Rosetta translation over to gemini-2.5-flash #jot

started an experiment for worklore: take a dev-tool that just shipped a major version, run its quickstart through claude code, codex and gemini (6 runs, a hidden script checks the result, not the agent's word), and turn whatever breaks into docs patches. if it works, this is how i'll offer agent-ready docs to saas companies #worklore

Closed a stale upload-500 incident and stopped a cosmetic spinner label from filing production exceptions when Gemini is busy #donequote

Registered dev account, paid $5, submitted Carrd Auto-Save extension to Chrome Web Store! Wow thank god for Gemini - generated all the text needed to submit - made it too easy! Now the painful part - waiting 🤞🤞🤞 #pluginsforcarrd

I had a review step using Anthropic instead of Gemini. Put everything back to Gemini. One model to rule them all! #offertecc

✅ Skip a dozen AI subscriptions! 🤑 One Subscription - Save 90%! ✨ Sign-up here fajarsiddiq.com/aymo 🤖 All the Top AI Models: ChatGPT, Claude, Gemini, Perplexity, Grok. Mistral, DeepSeek, Llama, Qwen, Kimi, GLM, MiniMax #fajarsiddiq

Added a spend watchdog for our AI bill. It pings Slack hourly when Gemini costs cross a threshold, but never caps. I'd rather overpay than have the app stop. #offertecc

Claude Opus 4.8 is as wordy as Gemini 3.1 Pro. That's not a good thing. #llm

Same prompt given to Fable and GPT5.5 to produce content. Output judged by Gemini. Fable won. #llm

Put more default rule prompts in Gemini's "system" slot #donequote

Optimize gemini caching #donequote

Improved Gemini 3 configuration #donequote

working on Gemini best practices as I feel it's dumber in my app than it should be

update #calmcompanies i18n pipeline to use gemini 3.1 flash lite model instead of Grok 4.20 because it's much cheaper and recommended by the guys who built translatepress.com/

Got Gemini to write my Carrd plugin tutorials for me - paste snippet, write prompt, copy in markdown... such a timer saver! - calendarplugin.carrd.co/#tuto… #pluginsforcarrd

Auto-drafted quotes now use the smart Gemini model and email the vendor when the concept is ready. #donequote

reading about the french revolution with gemini #nnjlife

My #openclaw is much less interesting with a Gemini model that Opus was.