Build
I’m building Signalpost at Builderr: a test for whether a company-research agent can produce a result you can actually audit. Give it a Norwegian organisation number. The agent returns public company…
Live Demobuilderr.aiSoham Sinha
@soham-sinha
Building source-backed evaluation harnesses for company-research agents at Builderr.
Ships 1 creation recently · mostly build posts · into Research, Agents, Tools & Frameworks
Currently building
Building Signalpost: a starter-kit challenge for testing crawler evidence and shared blind spots.
expires in 2d
builder
- Posts
- 1
- Streak
- 1d
Creations
1 creationShip calendar
· last 12 weeks1d streakJulAugSep
1 ship · 1 day · best 1dLessMore
Ship graph
· last 12 months1 in 1 day1 ship across 1 active day in the last year.
More about @soham-sinhaShowHide
ai-mltesting
Featured Build Clips
Fast walkthroughs, demos, and shipping proof from @soham-sinha.
I’m building Signalpost at Builderr: a test for whether a company-research agent can produce a result you can actually audit. Give it a Norwegian organisation number. The agent returns public company facts with the source URL and retrieval date for each claim, and marks uncertainty instead of filling gaps. The starter runs one saved company first, so you can inspect a wrong match or weak citation before you scale a crawler. The question I’m working on: if several crawlers agree, how do you tell whether they all missed the same source? I’m treating agreement as a clue, not recall, and looking for a practical test-harness pattern that makes the shared blind spot visible. Challenge and starter: https://builderr.ai/challenges/signalpost?utm_source=slop&utm_medium=community&utm_campaign=builder_acquisition_20260926&utm_content=shared_blind_spots_build_v1 Disclosure: I run Builderr.
Open clip post →Posts