Uses

What's actually on my machine. Verified, not aspirational.

Every tool here left a real trace: a commit, a log, a build. Installed-but-unused tools are left off on purpose.

Rig

HP Victus 15 — Intel Core i7-12650H, RTX 4050 (6 GB), 32 GB RAM

Languages in running code

  • GDScriptEXIT LIQUIDITY
  • TypeScriptAccountWard, Redl, Warrant, JobApp
  • PythonBEMA, scripts, tooling
  • RustTauri shells (AccountWard, Redl)
  • JavaScriptearlier web projects
  • KotlinFitFindr (Android)
  • C++Warrant native tooling

Toolchains

  • Godot 4.6EXIT LIQUIDITY
  • Tauri 2AccountWard, Redl desktop shells
  • Expo / React NativeFitFindr, NEXUS mobile
  • Android SDKFitFindr, Warrant Portal
  • AWS Lambda (Serverless)AeroBites
  • Dockerlocal service dev

AI coding agents

  • Claude Codeprimary agent for shipped projects — AccountWard, EXIT LIQUIDITY, this site
  • Codexused on ADDE and other explorations
  • Google Antigravityused on lab prototypes
  • GitHub Copilotinline completion

A cost-aware routing policy across these (default / escalation / never) is on the list for this page; not written up yet.

m.mittal
Home
Work
Research
Lab
About
Experience
Now
Résumé
Uses
Colophon
Contact
AccountWardin-build
Redlbuilt
The Councilresearch
BEMAresearch
EXIT LIQUIDITYin-build
NEXUSarchived
Warrant + Forgebuilt
Concordarchived
BlueCollarPalin-build
Chispenbuilt
Warrant Portalbuilt
JobAppin-build
Night/Dayexplored
BLACKSITE: NULLin-build
SlugBitesbuilt
Riptidebuilt
AeroBitesarchived
Internbuilt
CAD & 3D printingexplored
ForgeCouncilexplored
ADDE: adversarial due-diligence engineexplored
Model routing in practiceexplored
AI due-diligence market mapexplored
Quorumarchived
Colossus Wakeexplored
FitFindrbuilt
Project Omniexplored
Oblivionexplored
MeetWisebuilt
EyeOSexplored
LinkLeap AIexplored
Up-Toexplored
Offline speech-to-notes (Java)explored
AI-assisted game production pipelineexplored
COLLAPSEarchived
THE TRIALSarchived
EcoNodearchived
ESP32-S3 / LoRa benchexplored
CleanPlaybuilt
Rezonyrbuilt
Habit Tracker Telegram Botbuilt
Job Board Aggregatorin-build
Visual Hand Trackbuilt
CLI Task Trackerbuilt
All work44 entries
Can’t Hallucinate, Can Still Be Wrong: Calibration of a Typed-Decision Model Under Input Noisepaper
Disagreement as Signal: A Hybrid Multi-Agent and Council Architecture for Error Detection in LLM Systemspaper
Killing Good Ideasessay
Uncorrelated Failure Modesessay
ADDE: adversarial due-diligence engineexplored
AI due-diligence market mapexplored
AI-assisted game production pipelineexplored
Aura Chatexplored
Colossus Wakeexplored
EcoNodearchived
ESP32-S3 / LoRa benchexplored
EyeOSexplored
FitFindrbuilt
ForgeCouncilexplored
LinkLeap AIexplored
MeetWisebuilt
Model routing in practiceexplored
Offline speech-to-notes (Java)explored
Oblivionexplored
Print benchexplored
Project Omniexplored
Provably-fair outcome enginebuilt
Quorumarchived
Up-Toexplored
Copy hello@mitanshm.com
Switch theme
Play motion
RésuméPDF
Open GitHub ↗mit37
Open LinkedIn ↗
Toggle layout gridh
Toggle single-key shortcuts/ h