“An observability agent that hallucinates incidents is just an anxious colleague with API access.” We spent most of the effort keeping the AI grounded.
— on the FT-featured JRE workClosing the gap between it works and it ships.
viewing as
scroll down, or press Menu
01 — the gap
Most systems work on a laptop. Far fewer ship reliably, every day, to millions of real customers. The distance between those two things is where I've spent the last seven years. I rarely remember the clever fix. What I remember is the pattern that meant nobody ever had to fix it again.
← it works chaosorder it ships →
02 — Frankfurt · Lufthansa via IBM · 2018–2020
Keeping a global airline's digital experience in the air.
In plain EnglishI kept the Adobe platforms behind Lufthansa's website and customer campaigns running, and made sure only the right people could change them.
My first production job was DevOps Engineer at Lufthansa, running Adobe Experience Platform, which serves their customer-facing site, and Adobe Campaign, which runs their customer campaigns. Both were business-critical and used by teams on every continent.
- Instances, deployments, upgrades, certificates. All handled with minimal disruption to live operations.
- Access governance. Roles and permissions across globally distributed teams and agencies, with monitoring and audit checks.
- Under the hood: Adobe Experience Platform and Adobe Campaign instance management, deployment scheduling and upgrades across timezones, and certificate lifecycle management.
- Why it mattered: one wrong permission could expose customer data or push a campaign live in the wrong market.
Adobe Experience PlatformAdobe CampaignAccess governanceRelease mgmtGerman 🇩🇪
03 — London & New York (remote) · Burberry, Macy's via IBM
Turning deploy day from a gamble into a standard.
In plain EnglishI made releasing new software safe and routine for two global retail brands.
At Burberry, each client team was shipping in its own way. I built the CI/CD and infrastructure automation, then set the deployment standards every pipeline had to meet. At Macy's the stakes were retail uptime, so I automated operations in Python and Bash, with monitoring that caught anomalies before shoppers did.
- Deployment standards that made pipelines measurably more reliable across client teams.
- Automation first for high-availability retail systems, with alerting tuned to catch anomalies early.
- Under the hood: quality gates, image scanning, canary releases and automated rollback, rolled out across Jenkins and GitLab.
- Why it mattered: defects caught where they're cheap to fix, not in front of customers. Recognised with the Burberry Shining Star.
CI/CDJenkinsPython · BashMonitoring🏅 Shining Star
04 — Mumbai → New Zealand · Vodafone NZ via Infosys
Multi-cloud Kubernetes that survives a bad day.
In plain EnglishI kept a telco's systems online across two clouds, and broke things on purpose to prove they could recover.
This was a telco on AWS and Azure at once. I built CI/CD pipelines with Jenkins and Docker, ran multi-cloud Kubernetes with Terraform and Ansible, and did the root-cause analysis when things broke. Then I broke things deliberately, as a Gremlin-certified chaos engineer.
- Multi-cloud K8s on AWS and Azure, fully managed as infrastructure-as-code.
- Incident RCA with Nagios and Splunk to keep production reliable.
- Under the hood: EC2, S3, ELB and RDS provisioning, probes, autoscaling and failover, plus Python and Bash automation versioned in GitLab.
- Why it mattered: failures got found on a Tuesday afternoon, not at 3am. SLOs made reliability something you could negotiate.
KubernetesAWS · AzureTerraform · AnsibleSplunkGremlin ×3
05 — Auckland · One NZ via Infosys · 2023 → now
Teaching operations to think, and to wait for a human.
In plain EnglishI build AI assistants that spot outages early, find the cause, and suggest a fix. A human always approves it.
I'm a Site Reliability Engineer for generative and agentic AI. I build the AI-native observability layer and incident agents behind One NZ's Journey Reliability Engineering, which was featured in the Financial Times. The agents run grounded DQL on Dynatrace Grail, correlate journey health across OpenShift, MuleSoft and Kafka, and act on customer impact before it turns into an outage.
“An observability agent that hallucinates incidents is just an anxious colleague with API access.”
- Agentic AI: multi-agent workflows with tool use over MCP, connected to enterprise data platforms.
- RAG and LLMOps: hybrid search, reranking, golden-set evals, tracing, prompt versioning, guardrails, and cost and latency tuning.
- Legacy → cloud migration: −30% opex (~$150k/yr), −60% maintenance, provisioning cut from 2 days to 4 hours.
- Under the hood: Python/FastAPI, Claude and OpenAI, LangGraph, vector DBs, Ansible Tower, Terraform and Azure DevOps. I'm also the DevOps platform admin across Git, Jira, Splunk and Nagios.
- Why it mattered: 75% faster issue resolution, with responsible AI (personal data, access control, prompt-injection awareness) built in from day one. Named a One NZ Champion.
MCPClaude · OpenAILangGraphDynatrace GrailRAG · evals🏆 One NZ Champion
06 — the receipts
Reliability, converted into business value.
$0ksaved every year after the One NZ legacy → cloud migration
0%faster issue resolution with real-time dashboards and AI triage
0%maintenance overhead, and −30% operational cost
2d→4henvironment provisioning with Ansible Tower accelerators
FeaturedFinancial TimesJRE × One NZ × Infosys
AwardsOne NZ ChampionInfosys Star of the Quarter · Burberry Shining Star
CertifiedGremlin Chaos ×3Generative AI · AZ-900 · Cyber Security in SDLC · Adobe XP
Community2,500+ followerswriting about AI that actually matters
07 — how I think
Notes from the field.
keep scrolling, or use the arrows →
The model is rarely the bottleneck. The context around it is. Treat context as an engineering surface: snapshot it, version it, review it.
— context engineeringEvery benchmark the community optimises against eventually degrades. The pressure to show progress ends up corrupting the scoreboard.
— on the SWE-Bench Pro auditThe goal isn't fewer engineers. It's fewer 3am wake-ups for the same repeat failures.
— Kubernetes is learning to fix itselfThe talks are fine. The useful part is someone telling you quietly, over coffee, what they tried that didn't work.
— NZ Tech Expo ’26Sharing AI that actually matters, and helping PMs ship faster and break less.
linkedin.com/in/darshilkothari7 ↗08 — the lab
Don't take my word for it. Break something.
Pick one on the left and follow the numbered steps. Six pieces of production work, rebuilt as live simulations that run entirely in your browser. The data is representative, but the mechanics are the real ones.
Pretend something breaks, then watch an AI find the cause.
- 1Pick a problem
- 2Press Inject fault
- 3Watch the AI investigate
- 4Press Approve remediation
Problem. One customer journey crosses 6 systems. When it breaks, everything alerts and people argue about where the fault is.
Built. Agents on Dynatrace that run grounded DQL over MCP, cite evidence for every claim, and ask a human before acting.
Value. 75% faster resolution, with customer impact handled before it becomes an outage.
journey success99.4%
agent idle · waiting for signal…
time to root cause--manual ≈ 25–40 min (illustrative)
evidence-linked claims--no citation, no claim
Ask a question. The AI answers only from real documents, and shows its sources.
- 1Click a sample question
- 2Read the answer + sources
- 3Try the red "Ignore previous…" one
- 4Press Run golden-set eval
Problem. Hundreds of runbooks, and a chatbot that confidently gets things wrong.
Built. Chunking, hybrid BM25 + vector search, reranking, guardrails, and golden-set evals on every change.
Value. Answers are grounded and cited, and quality, cost and latency are measured together.
guardrailhybrid retrievererankground + citetrace
hit@k · MRR · $/1k queries · latency, compared with the previous run
Attack the servers and see whether the website stays up.
- 1Turn safety features off
- 2Press Blackhole AWS
- 3Watch availability drop
- 4Turn them back on and attack again
Problem. Multi-cloud K8s looks resilient on paper, until something actually dies.
Built. Probes, autoscaling, circuit breakers and failover, each proven with planned Gremlin attacks.
Value. Failures found on purpose, with SLOs and error budgets keeping the conversation honest.
attacks
resilience
availability100%
p95 latency--
error budget100%
See how automation turned a 2-day wait into 4 hours, and what that saves.
- 1Press Request an environment
- 2Watch the race
- 3Drag the sliders to your own numbers
Problem. Hand-built servers, two-day provisioning tickets and a growing maintenance bill.
Built. Cloud-native CI/CD, infrastructure as code and reusable Ansible Tower accelerators.
Value. −30% opex (~$150k/yr), −60% maintenance, provisioning cut from 2 days to 4 hours.
legacy · ticket queue0h
ansible tower · accelerator0h
opex saved / yr$150k
hours freed / yr--
lead time saved / yr--
Ship software with and without safety checks, then compare the failures.
- 1Turn deployment standards off
- 2Press Ship 25 releases
- 3Turn standards on, ship 25 again
- 4Compare the two summary lines
Problem. Every team deployed differently, so production became the test environment.
Built. Standard pipelines: tests, SAST, image scans, canaries and auto-rollback.
Value. Defects caught where they're cheap to fix. Compare the DORA metrics yourself.
change failure rate--
prod incidents0
caught pre-prod0
MTTR--
Choose a person and an action. The system decides whether it is allowed, and explains why.
- 1Choose who
- 2Choose what they want to do
- 3Read the decision and the reasons
Problem. Global teams and agencies on a customer-facing platform. One wrong permission is a breach.
Built. Role and attribute governance with monitoring, audit checks and certificate lifecycle management.
Value. A stable platform where every access decision can be explained and audited.
decision--
audit log · append-only
certificate radar
A command line for engineers. Type help and press Enter.
- 1Click inside the black box
- 2Type help and press Enter
For engineers. Type help. Tab completes, ↑ recalls history.
Try impact, experience, kubectl get pods…
…or sudo hire darshil.
09 — handshake
Let's ship something that stays up.
Auckland, New Zealand · open to APAC, remote and hybrid · English, German
Built with three.js, GSAP and plain JS. No trackers, and every simulation runs in your browser. ©