Shipped

Verified AI-assisted builds from the community.

B
@balramwootzpandey019/qmmit_test5d

read code and create knoledge.md for all

add a web html page for this
2 promptsopencodegemini-3.1-flash-image-preview (google)
main · 20d7229
B
@balramwootzpandey019/qmmit_test5d

create a installation,md file

read code and create knoledge.md for all
1 promptsopencodegemini-3.1-flash-image-preview (google)
main · 26ffe42
B
@balrampandey0019pandey019/AgentApiBench19d

Slightly offset scores per task so they are not uniformly 0.95

Same error means the grader clamping is working but the final score in inference.py is still 0.0 or 1.0. The validator reads the [END] line score — that's what's failing. The p...
2 promptsopencodegemini-3-pro-preview (google)
main · 373096c
B
@balrampandey0019pandey019/AgentApiBench19d

Clamp final score in inference.py to strictly (0,1)

The error is very clear. Read this part carefully: "Each task's score must be strictly between 0 and 1 (not 0.0 and not 1.0)" Your current scores are exactly 1.000 for all 3 t...
3 promptsopencodegemini-3-pro-preview (google)
main · 1c1e9f6
B
@balrampandey0019balrampandeydmifin/cursor_test_124d

# VakilAI — Business Requirements Document (BRD) ### AI-Powered Legal Assistant

# VakilAI — Business Requirements Document (BRD) ### AI-Powered Legal Assistant for Indian Solo Advocates & Small Law Firms **Version:** 1.0 **Date:** April 2026 **Status:**...
16 promptsopencodegemini-3-pro-preview (google)cursor/auto
main · 02c8a6c
B
@balrampandey0019balrampandeydmifin/cursor_test26d

Add unit test for open_webpage.py

write unit test case for pything code
2 promptsopencodegemini-3-pro-preview (google)
main · 1c3728b

6 builds total