Compound Labs
Get the newsletter
THE STANDUPAnthropic fixes Claude 5.1 error spikesERROR SPIKES, FIX DEPLOYEDCOMPOUND MASTODONSkillWorks records inactive files beside their roster status22 INACTIVE FILES STILL LOADCTXWINDOWContext Window tracks AI lab changes and filters their evidenceFILTERS KEEP EVIDENCE TOGETHERAGENTWIREmicrosoft/agent-governance-toolkit - AI Agent Governance ToolkitPOLICY ENFORCEMENT FOR AI AGENTSCOMPOUND FACEBOOKCompound Portfolio restores its sweep after a missing module stops desk dataSWEEP RESTORED, DESK DATA WRITTENBLOCKDEXBlockDex shows no destination for captured rows with rejected slash names31 ROWS, NO DESTINATIONCONTEXT WINDOWOpenAI adds 1024p image pricing: $0.50 and $0.251024P IMAGE, $0.50 AND $0.25COMPOUND BLUESKYCompound Labs renamed job labels so job-run finds breaker stateBREAKER STATE, NOW FINDABLECTXWINDOWContext Window tracks document changes but failed mobileMOBILE WORKFLOW, ONE COLUMNAGENTWIREMineDojo Voyager: Open-Ended Embodied AgentOPEN-ENDED EMBODIED AGENTFOUNDER BLUESKYdeploy.sh now fails false Vercel production landingsFALSE LANDINGS NOW FAILCOMPOUNDlast known fixes redirect tracking after migrationSTUDIO SOURCES NOW SAY COMPOUNDCONTEXT WINDOWOpenAI adds sora-2-pro pricing720P VIDEO, $0.15, $0.30FOUNDER LINKEDINdeploy.sh now stops failed promotes from marking production landedFAILED PROMOTES NO LONGER LANDUSINGITUPUsing It Up records a receipt fixing a wobbling wooden tableONE RECEIPT, TABLE STAYED LEVELCOMPOUNDpnpm v12.4.2POSIX BIN SHIMS REPLACEDFOUNDER PEERLISTCompound Labs' deploy runner rejects failed promotesFAILED PROMOTES NO LONGER LANDTRUSTDESKTrustDesk fixes host migration redirects while keeping /api/ outOLD HOST, 308; API STAYS LIVE
Independent product R&D labFounded and run by Isaiah Kim, @kyisaiah47Newest commit Sep 16, 2026, AgentwireNewest writing Sep 16, 2026Site changelog Sep 16, 2026
Compound AI OpsFOUNDER LINKEDIN31 August 2026

Toolproof

A FAILED CHECK GOES OUT GREY

Toolproof scores coding-agent tools and gives your project a live badge

Toolproof measures the tooling people run inside coding agents, and gives you a badge for your own project's front page that fills itself in from the live reading. It's for anyone maintaining one of those tools, or deciding which one to install.

Every badge hands back a picture, even when the check fails. A badge that errors shows a broken image on a page I don't control, and the fix for a broken image is to delete the line. That deletion is permanent. The project that carried the name stops carrying it and is never asked again.

So a failed check goes out grey, and the grey states get different words. If the index answered and holds nothing for that project, the badge says not indexed, which is true and is the maintainer's own information. If the index didn't answer, it says unavailable. I'm not printing my own downtime as a verdict on somebody else's work.

There's also no way to set the value yourself, so nobody can type a badge instead of earning it. Free to embed, no account, no key.

https://toolproof.kynth.studio/li

#AIAgents