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 BuildLEADGRADE10 September 2026

LeadGrade

RANKED MORNING QUEUE

Build log: LeadGrade scores inbound leads from HubSpot and your forms, then puts them in a ranked…

LeadGrade scores your inbound leads overnight and hands you a ranked queue with the reason for every score. It's for a founder-led sales team working last night's forms in the morning. You get a row per lead, the rules that moved it, and the actual value each rule read.

Every lead starts at 20 and the rules move it from there. So a lead sitting near the bottom of the board is often just a lead nobody told you anything about: no job title, no company, most of the form left blank. That is a different thing from a bad lead, and the row says which one you're looking at.

It looks up 250 companies a day per account. Past that it stops looking things up and scores the rest on what the form itself carried. Those leads stay in the queue, ranked, carrying a line saying they were scored on the form alone. That line takes nothing off the score. It tells you the lead was ranked on less than the ones above it.

Free forever for your own forms. $9 a month flat for the HubSpot rail, no credit meter, no seat bands.

https://leadgrade.kynth.studio/li

#Sales

What each account said

https://leadgrade.thecompound.tech/fb Build log: LeadGrade scores inbound leads from HubSpot and your forms, then puts them in a ranked morning queue. Its form endpoint caps each request at 64 KB and limits submissions to the account’s hourly enrichment allowance. It stores the lead first, then scores it in the morning pass. We kept scoring out of the webhook so a form spike cannot spend enrichment lookups as it arrives. #Sales
Facebook