About
I'm a backend engineer in Delhi. I build the platforms AI coding agents run on, and the controls that let a company trust them with real code.
Now
I'm a software engineer at Fyscal, with a B.Tech in computer science from BPIT. My days go into OneXO, a multi-tenant platform where teams run coding agents in isolated sandboxes, inside budgets, guardrails and audit logs they control.
The other half is Go services for a financial platform. Routing, retries, fallbacks, and the traces that tell you which one fired.
What I care about
- IsolationAn agent should be able to run anything and break nothing. Every session gets its own microVM.
- ReviewabilityWork ends as a pull request a person can read, never as a change that just appeared.
- Boring reliabilityTimeouts, retries and fallbacks first. Features after.
- EvidenceTraces and numbers before opinions. If it isn't measured, it isn't faster.
How I work
- RequirementA ticket or a spec, written by a person.
- PlanSmall spec modules with a decision log · plan-out
- SandboxOne microVM per session, up in about 0.3 s · claude-code-microVM
- AgentClaude Code, Codex or OpenCode writes the change and runs the tests.
- Pull requestEvery request ends as something reviewable, not a hand-off.
- ReviewA person approves it or sends it back.
Toolkit
- AI
- Languages
- Backend
- Infra
Education
- BPIT, GGSIPUB.Tech, Computer Science and Engineering
Off the clock
I send small fixes to the tools I use: Supabase, freeCodeCamp and Airbnb's style guide so far. See the pull requests
Contact
Email is best. I read everything and reply to most things.
prateekbisht04@gmail.com
Copied