Suryanand/ Portfolio
Let's talk

Suryanand, solutions architect and founding engineer who solves messy problems with software, in Pune and Dubai

# Home — Desktop 1440 × 900
◇ Solutions architect · founding engineer
Taking on new problems
SuryanandSuryanand
1156 × 210

Bring me the messy problem. I design the system, build it and stay until it works in production.

LayersAssetsHome
  • #Home — Desktop
  • ✎Suryanand
  • TStatement
  • ▭Buttons
  • ▶intro.mp4
  • ◇Now: Araxis AI
▶ intro.mp4 · 2:00 VSL
◇ Now: Araxis AI
Voice runtime · prod● Healthy
218 ms
p99 voice round-trip · last 24 h
DesignPrototypeInspect
Name / vector
X142Y146W1156H210
Text
GeistSemibold
Aa208|A|-5%
Fill
RGB(12, 12, 14)100%
100%
A
Ava · PM
Kai · Eng
Taking on new problems

Bring me the messy problem. I design the system, build it and stay until it works in production.

▶ intro.mp4 · 2:00 VSL
◇ Shipped with13 clients · 10 skills
AlphabetLogisticsGranules IndiaPharmaSyntegonProcess equipmentHosokawa MicronPowder processingSun PharmaPharmaAzbilAutomationPegasusFreightSyngentaAgritechHoagHealthRelic CareHealthPlugzeeEVPloySoftwareAestloCommerce
TSystem designTCore platformsTTypeScriptTPythonTNext.jsTFastAPITPostgresTTemporalTLLM toolingTVoice AI
▣ blue-linen.jpgCrop · 514 × 642
Portrait of Suryanand
Ava · dragging
[03] About

I've spent eight years untangling the messy first version of products, from ◇ Google logistics to an AI runtime built from a blank repo.

I care less about novelty and more about shipping the right thing: clear architecture, honest observability and code the next engineer can actually live with.

These days I build Agent Serve and Agent Live with the team at Valnora & Elric, and I've led plant-floor systems for Granules India, Syntegon, Sun Pharma and Azbil. I also share four Apache-2.0 tools at Valthrax and teach system design at bootcamp.suryanand.com.

Based inPune, IN · Dubai, UAE
Working asFull-time or contract
Studiovalthrax.com
System designCore platformsAI runtimesVoiceObservabilityTeaching
[▶] Videos

Short videos on how I think about problems, and walkthroughs of things I've built.

Next video in production

Case study walkthroughs

Screen-by-screen tours of the systems on this page.

Next video in production

How I'd architect it

Real problems, solved on a whiteboard.

[04] Selected work
Valnora & Elric · Platform architecture

Agent Serve

An AI workspace where teams build, deploy and manage AI agents. I architected the platform and lead its engineering, from multi-tenant data to the agent runtime.

0modules: Chat, Workflows, Knowledge, Tables, Files, Logs
0ways to build agents: visually, in chat or in code
0workspace for agents, data and BI dashboards
AI agentsMulti-tenantPlatform
Read the case study
01 Background02 Layout grid03 Hero image04 UI cards05 Type06 Redlines
# Agent Serve — Hero · 1920 × 1200
01 Background
02 Layout grid
03 Hero image
04 UI cards
Relays on watch
Relay · revenue ops
Note ready
Weekly pipeline summary drafted
Approve
05 Type
Agent ServeProductPricingStoriesGet started
The AI workspace for teams.
Build, deploy and manage AI agents.
06 Redlines
24361224
Valnora & Elric · Platform architecture

Agent Serve

An AI workspace where teams build, deploy and manage AI agents. I architected the platform and lead its engineering, from multi-tenant data to the agent runtime.

Relays on watch
Relay · revenue ops
Note ready
Weekly pipeline summary drafted
Approve
Agent ServeProductPricingStoriesGet started
The AI workspace for teams.
Build, deploy and manage AI agents.
24361224
Read the case study
6modules: Chat, Workflows, Knowledge, Tables, Files, Logs
3ways to build agents: visually, in chat or in code
1workspace for agents, data and BI dashboards
Valnora & Elric · Real-time AI

Agent Live

A real-time AI copilot for sales calls: live guidance while the call is happening, playbooks and compliance checks, and an admin portal for managers.

Compliance check passed
Live call · discovery
Ask about budget
Playbook step 3 of 6
Next prompt
Agent LiveProductPricingStoriesGet started
A copilot on every sales call.
Live guidance, playbooks and compliance.
24361224
Read the case study
3surfaces: desktop app, live service, admin portal
Liveguidance during the call, not after it
1playbook library shared by the whole team
EV mobility · Product build

Plugzee

An EV super app: find and reserve chargers, plan road trips with charging stops, book service and insurance, and pay from one wallet.

Charging complete · 80%
Plugzee Fast Charging · Kharadi
4 of 6 free
120 kW DC · ₹18.5 / kWh
Reserve charger
PlugzeeProductPricingStoriesGet started
One app. Every mile.
Charging, trips, service and insurance.
24361224
Read the case study
5journeys in one app: charge, service, buy, insure, travel
Livecharger availability and pricing on the map
1wallet and rewards across every journey
Pharma · Forward deployed delivery

Granules India

Lyophilization process intelligence: every freeze-dryer, cycle phase, alarm and batch record on one live screen, with the audit trail on.

Audit trail on
LYO-01 · primary drying
−38.2 °C
Product temperature, on recipe
Open batch record
GranulesProductPricingStoriesGet started
Every freeze-dryer, on one live screen.
Cycles, alarms, SOPs and batch records.
24361224
Read the case study
7cycle phases tracked, from loading to complete
7live readouts per lyophilizer
1screen for every freeze-dryer on the block
Process equipment · Forward deployed delivery

Syntegon

A fluid bed dryer digital twin: live sensor readings on a 3D model, drying curves, and an AI copilot that flags drift before it becomes a deviation.

Inlet 62 °C · outlet 38 °C
Copilot · drying curve
Drift +1.4 °C
Outlet temperature above expected
Review
SyntegonProductPricingStoriesGet started
The dryer, live in 3D.
With an AI copilot on the curve.
24361224
Read the case study
3Dlive twin of the dryer
AIcopilot watching the drying curve
ARview for engineers on the floor
Powder processing · Forward deployed delivery

Hosokawa Micron

Process and equipment intelligence across milling and drying: 3D equipment, live parameters, health scores, CIP/SIP monitoring and reports.

CIP cycle complete
Mill 02 · health
92 / 100
Bearing vibration in range
Open work order
HosokawaProductPricingStoriesGet started
From the plant down to the bearing.
Milling and drying, on one model.
24361224
Read the case study
3Dequipment viewer, plant down to the bearing
Liveparameters and equipment health scores
CIPand SIP cleaning cycles monitored
Pharma field maintenance · Forward deployed delivery

Sun Pharma

Field AI for on-site maintenance: smart glasses show the next step on the equipment, capture evidence and write the inspection report as technicians work.

Glasses paired
Inspection · step 4 of 9
Check seal
Photo and voice note captured
Next step
Sun PharmaProductPricingStoriesGet started
The next step, on the equipment.
Hands-free guidance and reports.
24361224
Read the case study
ARstep guidance on the equipment itself
Autoinspection reports when the job ends
Liveremote session view for maintenance leads
Industrial automation · Forward deployed delivery

Azbil

On-site operations with AR: sign-in, pre-work compliance, guided execution, live data and evidence capture, ending in an audit-ready record, hands-free.

E-signature captured
Valve positioner · calibrate
Step 3 of 5
Pre-work checks complete
Sign off
AzbilProductPricingStoriesGet started
From sign-in to signed off.
Hands-free, with an audit-ready record.
24361224
Read the case study
ARhands-free field workflow on smart glasses
VoiceAI assistant for field engineers
2languages in one interface
Freight · Product build

Pegasus

A freight operating system: shipments, bookings, containers and exceptions in one command centre, with live tracking and AI insights on delay risk.

Customs hold cleared
MSKU 492 · Jebel Ali
Delay risk high
Port congestion, +2 days
Notify customer
PegasusProductPricingStoriesGet started
Every shipment, one command centre.
Live tracking and delay-risk insights.
24361224
Read the case study
3modes tracked live: ocean, air and road
AIinsights on port congestion and delay risk
1command centre for every exception
[05] In numbers

Updated Oct 2026
W years01
0

shipping software that runs in production

H companies02
0

built for, from Alphabet to Sun Pharma

X industries03
0

from pharma lines and freight to fashion

Y systems04
0

AR, 3D and digital-twin systems on the plant floor

[06] Services


Most engagements start with a 30-minute call and move right. Each frame is a separate engagement, so you can start anywhere.

Book a call
thenonce it's liveat scale
# Frame 01
(01)→

Founding engineering

Your first technical partner. I own the platform end to end: architecture, the build and the first engineering hires.

  • Core platform
  • Architecture
  • Observability
  • Hiring loop
OngoingFull-time or contract
# Frame 02
(02)→

Solutions architecture

I map the business problem to a system: integrations, data flows, security and the build plan, written down before anyone writes code.

  • Discovery workshops
  • Reference architecture
  • Integration design
  • Security review
1–2 weeksFixed scope
# Frame 03
(03)→

Forward deployed engineering

Embedded with the process owners, inside your IT and security rules, putting AI and data into production against a business target.

  • On-site discovery
  • Systems integration
  • AI in production
  • Team handover
30-day sprintOutcome-based
# Frame 04
(04)→

0→1 product builds

From a back-of-napkin idea to something people use in production, in about two weeks, without a rewrite later.

  • Product scoping
  • MVP build
  • Deploy and monitoring
  • Handoff docs
~14-day sprintFixed scope
[07] Process

Auto layoutHorizontalGap 24Padding 24
Step 1 / 4
01Days 1–2

Discover

I sit with the people who'll use it and write down the one outcome that matters, with a number next to it.

02Days 3–4

Architect

03Days 5–12

Build

04Days 13–14

Ship

[08] Testimonials

Four founders, four threads. Resolve them if you've read enough.

Start a project
AS
Ananya SharmaSaaS founder, Pune
◇ SaaS

“Two weeks from Figma to a working app. We shipped to users on the call right after handoff.”

1 reply · Suryanand
IK
Ishan KapoorCTO, PaymentFlow
◇ PaymentFlow

“Our junior devs picked up the code without one question. That alone was worth it.”

1 reply · Suryanand
PD
Priya DesaiHealthtech founder
◇ Healthtech

“Three other devs gave up on this build. Suryanand had it live in two weeks.”

1 reply · Suryanand
RM
Ravi MehtaFounder
◇ Seed-stage

“We launched on day 12. Closed our seed round on day 19.”

1 reply · Suryanand
[09] Lab


Open-source tools, weekend projects and experiments. Drag anything around.

Browse on GitHub
threads-clone.png
Every tool on this board is free. Apache-2.0, all of it.Suryanand · note

$ pip install pressmark

✓ pressmark 0.1 installed

$ pressmark eval --min-pass-rate 0.9

✓ 47/50 prompts passed

4B3BFFFF5B24C8F25A
◇ Cue, 3 modes
kpop-urban-drop.png
r2r-care.png
Sunday project: a CSV fixer with no login. 500+ people a week now.
#weekend-builds
Murmur: sub-second voice, every stage swappable.Suryanand · note
switchboard · 200+ models

› anthropic/claude

openai/gpt

google/gemini

$0.0021 · 412 tok
Drag anything · board resets on reload
[11] Questions

The questions I get on almost every first call. If yours isn't here, email me; I answer every one.

Ask something else
LayersFAQ6 items

The messy ones where software, data and operations meet: AI platforms, real-time voice, plant-floor and field systems, and products that need to go from zero to production. I've solved these for pharma, process-equipment, freight and EV companies.

[12] Next step

Building somethingfrom zero?Text · 104Let's ship it.

Tell me what's slow, broken or stuck. I reply within one working day with a first idea of how I'd solve it.

Local time● online
--:--:--

Pune. I reply within one working day, usually faster.

Version history v26.10
v26.10Portfolio rebuilt as a design file
v26.10Case studies: Agent Serve, Agent Live and six plant-floor builds
v26.04Added Cue to the open-source shelf
v26.04New Teaching section with the bootcamp
v26.03Founding-engineer redesign