The Operator · Issue 01
May 2026 · Bengaluru
Cover story

One human.
Eleven agents.

Krish Mehta runs a one-person studio where AI agents do the engineering. He writes the brief, sets the bar, and decides what stays.

Open to
Founding-engineer, founding-PM, or 0→1 advisory roles. Full time or 4-day weeks. Bengaluru / remote.
Engineers on payroll
0
Products shipped
2
pg. 01TripOS shipped without engineers
pg. 02What the agents actually do
pg. 03Receipts from PayPal — $5M, $60K/mo, 40%
pg. 04How to reach the operator
Feature01 / 02
Studio dispatch · Live in production

TripOS.

The AI concierge that takes over once your trip starts. I'm the only human in the loop — eleven agents ship the product.

Read the feature
Commits
176
API routes
126
Components
104
Prisma models
55
Unit tests
689
E2E specs
148
Feature02 / 02
Pull quote

“Built solo over weekends. Real card-counter depth — Hi-Lo, KO, Illustrious 18, Wonging.”

Side project · Live

Blackjack
Trainer.

A complete product, shipped solo, with the depth a serious player needs.

Read the feature
Track record · from my last rolePayPal · 2024 — 25
$5M+
Audit savings surfaced (ML)
$60K
/mo GCP saved (Artifactory cleanup)
40%
Downtime cut (bare-metal → k8s)
20k
Developers served
Letter from the operatorBy Krish Mehta

I think like a founder. The taste, the brief, the call on what ships — that's the work I do. The agents handle the code.

By day I'm at Harness, leading enterprise implementations. By night I run a one-person studio. TripOS proves an operator with strong taste and the right tools can ship a real product without an engineering team.

PayPal taught me to keep score. I surfaced $5M in audit savings with an ML model, saved $60K/month on Artifactory storage, and cut Artifactory downtime 40% by moving it to Kubernetes.

Roles · 2023 — now
  • Harness2025 —
  • PayPal · SWE2024 — 25
  • PayPal · Intern2023
Education · Trinity College Dublin — Engineering
Contact the operatorDirect line
krishmehta77@gmail.com →
System online
Build: v2026.05
/ ai-engineer

I build agents that ship to production.

Eleven named agents ship TripOS, coordinated by a control plane, each pinned to a model tier — Opus, Sonnet, Haiku — chosen on cost and workload. I work on the application side of AI: MCP servers, agent orchestration, LLM-augmented tooling. Not training; integration.

Open to
AI engineer / forward-deployed engineer / agentic-tools roles. Senior or staff level. Bengaluru / remote.
// primary stack
  • claudeopus-4.7
  • claudesonnet-4.6
  • claudehaiku-4.5
  • openaigpt-runtime
  • mcpcustom-nlp
/ fleet
12 processes · all green
/ shipped
2 live
/ production-ai
PayPal + Harness
// systemPayPal · 20k devs
NLP MCP server

Custom MCP server unifying search and command across Artifactory, GitHub, and Jira — material SDLC velocity gain.

// systemPayPal
GenAI PR review bot

Enforces enterprise governance and coding standards across PRs. 100% compliance with internal rules.

// systemPayPal · Finance
ML cost prediction

Jira task analysis model surfaced $5M+ in cost savings for the Finance audit team.

// systemHarness
AI onboarding accelerators

Three accelerators with Claude + GitHub + Harness — incl. a one-shot repo → CI/CD framework with STO.

/ operator-profile
krishmehta77

I build agentic systems for real production. TripOS has 11 specialized agents (ATLAS, FORGE, PILOT, CONCIERGE…) coordinated by a control plane, each pinned to a specific model tier and budget.

At PayPal: custom NLP MCP server bridging Artifactory + GitHub + Jira, an ML model predicting Jira task costs (surfaced $5M+ in audit savings), a GenAI PR-review bot enforcing internal coding standards across 20,000 developers.

At Harness I'm building AI-powered onboarding accelerators with Claude + GitHub + Harness — including a one-shot repo → CI/CD framework with integrated STO, and the IDD onboarding chatbot used internally and by customers.

// uname -a
host krishmehta.space
role impl-engineer @ harness
prior swe @ paypal
edu tcd · engineering
tz IST · UTC+5:30
stat available
/ contact
async friendly
krishmehta77@gmail.com
Available · Bengaluru · 2026

Krish Mehta.
I ship complete products.

TripOS is a 126-route Next.js 15 app with 689 unit tests and 148 e2e specs. Blackjack Trainer is a pure-function game engine with invariant tests. I take things from blank repo to live URL.

Open to
Software engineer roles. Backend or platform preferred. Bengaluru / remote / hybrid.
Featured work
Toolkit
TypeScriptNext.js 15React 19Node.jsPythonPostgresPrismaRedisTailwindStripeAuth.jsMapboxPlaywrightVitestVercelAWS S3KubernetesTerraformn8nDatadogSentryOpenAIClaudeMCP
Recent shipping
May 26
TripOS · Live Mode v2 — 30-panel mobile screen, geofence-aware
tripos.dev
May 26
TripOS · /how-its-made — 11-agent build narrative with model costs
tripos.dev
Apr 26
TripOS · b2b /agencies page + lead capture
tripos.dev
Mar 26
TripOS · prod launch · auto-deploy on main
tripos.dev
Feb 26
Harness · AI onboarding accelerator — one-shot repo → CI/CD + STO
harness
Jan 26
Harness · IDD onboarding chatbot for internal + customer enablement
harness
Dec 25
Blackjack Trainer · Vercel analytics + credit line
vercel
Nov 25
Blackjack Trainer · v1 release · 17 modes
vercel
Oct 25
PayPal · Artifactory cleanup automation — $60K/mo GCP saved
paypal
Aug 25
PayPal · @codeppllm — internal LLM tool for 50+ devs · 40% fewer errors
paypal
Jul 25
PayPal · custom NLP MCP server bridging Artifactory + GitHub + Jira
paypal
Jun 25
PayPal · ML prediction model for Jira tasks — $5M+ audit savings surfaced
paypal
Apr 25
PayPal · GenAI PR review bot · 100% internal-standards compliance
paypal
Mar 25
PayPal · Artifactory bare-metal + VMs → Kubernetes — 40% downtime cut
paypal
Jan 25
PayPal · Terraform + Python repo automation · 100+ monthly requests
paypal
Nov 24
PayPal · 15,000+ GitHub repos migrated to EMU
paypal
About

I ship. TripOS — Next.js 15 + Postgres + Prisma + Stripe + Auth.js v5 + S3 + OpenAI, 126 API routes, 689 unit tests, 148 e2e specs. Blackjack Trainer — React 19, pure-function game engine with invariant tests.

At PayPal I was Software Engineer for Artifactory / GitHub / Jira across 20,000 developers and 2M daily ops — wrote and shipped code, owned tooling, drove rollouts.

Trinity College Dublin, engineering. Bengaluru since.

Quick facts
  • RoleSoftware Engineer · @ Harness (Impl.)
  • PriorSoftware Engineer @ PayPal
  • EduTrinity College Dublin · Engineering
  • BasedBengaluru · IST
  • StatusAvailable 2026
Contact
krishmehta77@gmail.com
╔══════════════════════════════════════════════════════════════════╗
║  KRISH MEHTA · PLATFORM ENGINEER · BENGALURU · 2026             ║
╚══════════════════════════════════════════════════════════════════╝
$ whoami
↳ Krish Mehta — Platform Engineer
$ cat /etc/role.conf
ROLE="Implementation Engineer"
EMPLOYER="Harness"
FOCUS="CI/CD · STO · IaCM · IDP · SCS"
PRIOR="Software Engineer @ PayPal — 20k devs, 2M daily ops"
$ status
AVAILABLE [✓]
# ./summary

Platform engineer.

Moved PayPal's Artifactory from bare-metal + 5 VMs to a Kubernetes cluster — 40% less downtime. Built Terraform automation cutting 40% of manual repo work. Now owning enterprise CI/CD, STO, IaCM, IDP and SCS rollouts at Harness.

$ open-to
> platform / DevOps / SRE roles · senior or staff
> Bengaluru / remote / hybrid · IST
# ─── system.metrics ──────────────────────────────
downtime
-40%
// k8s migration
gcp_cost
-$60K/mo
// cleanup automation
repos
15k+
// migrated to EMU
artifacts
250M+
// JFrog Xray E2E
# ─── kubectl get deployments --all-namespaces ────
namestatusscopeimpact
artifactory-k8sRunning2 bare-metal + 5 VMs → k8s cluster-40% downtime
repo-automationRunningTerraform + Python · 100+ req/mo-40% manual
emu-migrationComplete15,000+ GitHub repos → EMU-30% mgmt time
xray-e2eRunningJFrog Xray · 250M+ artifacts5k+ CVEs mitigated
datadog-metricsRunning30+ custom metrics · 10+ teams-20% detect time
artifactory-cleanupCronAutomated retention + GC-$60K / mo GCP
// side projects (not platform — for completeness)
# ─── tail -f /var/log/war-stories ────────────────
[STORY 01] · Artifactory migration

Inherited 2 bare-metal hosts + 5 VMs running production Artifactory for 20,000 developers. Sized a k8s cluster, designed a zero-downtime cutover with a read-only window, shadowed traffic for 48h, flipped DNS. Result: -40% downtime, same hardware budget.

[STORY 02] · The $60K/mo storage leak

Artifactory storage growing unbounded. Wrote a retention policy + GC cron that respected legal/compliance holds. Dry-ran against prod for a week before cutover. Result: -$60K/month GCP, zero accidental deletions.

[STORY 03] · 15K repos to EMU

Migrating 15,000 GitHub repos to Enterprise Managed Users — every dependent CI/CD reference would break. Wrote a Python + Terraform pipeline that rewrote refs, validated, and rolled back per-repo on failure. Result: -30% ongoing repo-management time.

# ─── platform.pipeline ───────────────────────────
[BUILD]
Bare-metal + 5 VMs → Kubernetes cluster
PASS
PayPal · -40% downtime
[DEPLOY]
Terraform + Python repo automation
PASS
100+ monthly requests · -40% manual
[MIGRATE]
15,000+ GitHub repos → EMU
PASS
-30% repo management
[OBSERVE]
30+ custom Datadog metrics
PASS
-20% detection time
[SECURE]
JFrog Xray E2E · 250M+ artifacts
PASS
5,000+ vulnerabilities mitigated
[OPTIMIZE]
Artifactory cleanup automation
PASS
-$60K/month GCP
# ─── apt list --installed ────────────────────────
kubernetes
terraform
docker
ci-cd
jenkins
github-actions
harness
artifactory
jfrog-xray
datadog
sentry
vercel
aws-s3
postgres
redis
n8n
python
bash
node
linux
# ─── cat README.md ───────────────────────────────

I do platform work. PayPal Artifactory: bare-metal + 5 VMs → Kubernetes cluster, 40% downtime cut. Terraform + Python automation for repo sunsetting and user provisioning — 100+ monthly requests, 40% manual work eliminated.

15,000+ GitHub repos migrated to EMU. 30+ custom Datadog metrics with 20% detection-time improvement. JFrog Xray covering 250M+ artifacts; 5,000+ vulnerabilities mitigated. Artifactory cleanup automation: $60K/month in GCP savings.

Now at Harness, owning enterprise CI/CD, STO, IaCM, IDP and SCS rollouts — integrating with customer code repos and artifact registries.

# uname -a
role impl-engineer
org harness
prior paypal
edu tcd
tz utc+5:30
# ─── send.message ────────────────────────────────
$ mail krishmehta77@gmail.com
krishmehta77@gmail.com
Volume I · No. 1
The Implementation Quarterly
Cover story · By Krish Mehta

Making enterprise adoption stick.

I work as a trusted technical advisor across five-plus enterprise rollouts spanning CI/CD, security testing, infrastructure as code, internal developer portals, and software supply chain. The job is to take Harness from contract to actually-adopted — architecture conversations, integration design, onboarding strategy, and the kind of AI-powered accelerators that compress the timeline.

I built three onboarding accelerators with Claude, GitHub and Harness — including a one-shot framework that takes a repository all the way to a production-ready CI/CD pipeline with integrated STO. I also built the IDD onboarding chatbot used internally and by customers.

Before this, a year and a half as Software Engineer at PayPal for Artifactory, GitHub and Jira — 20,000 developers and roughly two million daily operations. Strong measurable outcomes (see By the Numbers below).

Open to
Implementation engineering, technical advisory, and customer engineering roles. Senior or staff level.
Engagement
Full-time preferred. Open to consulting engagements for the right scope. Bengaluru / remote / hybrid.
On the practice
“Quietly turns a contract into adoption.”
— Krish Mehta · personal note
Features · Practice deliverables
I.
Accelerator

One-shot repo → CI/CD framework.

AI-powered onboarding accelerator built with Claude + GitHub + Harness. Takes a customer repository and produces a production-ready CI/CD pipeline with integrated security testing (STO). Compresses what was a two-week kickoff into a single working session.

Used on: Global financial services SCS rollout · Global marketplace CI/CD
Built · 2025
In production
Harness · internal
II.
Chatbot

IDD onboarding chatbot.

AI assistant for the Implementation Delivery Development process — used by Harness internal teams and customer-side engineers during enablement. Reduces the “where do I find…” tax that bogs every multi-module rollout.

Audience: Implementation teams + customer engineers
Built · 2025
In production
Harness · internal
III.
Framework

Reusable expert-skill workflows.

Modular Claude/Copilot-style assistant skills that Implementation Engineers can compose for specific customer guidance — accelerating platform adoption and onboarding across multiple engagement types.

Built · 2025 — 26
Active
Harness · internal
Selected engagements
Software Supply Chain (SCS)

Global Financial Services

Multi-module rollout with custom integration to enterprise artifact registries.

Continuous Deployment (CD)

Global HR-Tech Platform

Production CD pipelines integrated with their existing repo strategy and release cadence.

CI/CD · STO · IaCM · IDP

Global Marketplace Platform

Four-module transformation. End-to-end from contract to adoption across distributed teams.

By the numbers — PayPal · 2024–25
$5M+
Audit savings surfaced via ML
$60K
/mo GCP saved · Artifactory cleanup
40%
Downtime cut · bare-metal → k8s
20k
Developers under tooling
Correspondence

Write to the editor.

krishmehta77@gmail.com
Office hours

India Standard Time. Async friendly. Direct line preferred for substantive inquiries — I read everything and reply to most within a day.