I build AI systems.
I've been at this long enough to know where most of them fail.
I'm Rupreet Gujral - an AI and Systems Architect with 25 years spanning enterprise tech, global consulting, and the builder trenches. I've founded startups, shipped patents, and worked inside organisations large enough to know why most AI projects stall. Today I architect agentic systems and LLM infrastructure - and I write about what I learn, without the hype.
Claude Architect Foundation
Not a ladder. A loop.
"Most careers in tech are a ladder. Mine has been a loop - and it's given me something a straight line never could."
Corporate to startup, practitioner to strategist, founder to architect - and back again. 25 years across enterprise tech, consulting, and building my own ventures has given me a vantage point that's hard to get from one track alone.
I've sat in rooms where AI projects die slow deaths - not because the technology failed, but because the architecture was wrong from day one. I've also been on the other side - founding startups, shipping under pressure, learning what actually works when the demo is over and the budget is real.
Today I architect agentic systems: multi-agent pipelines, LLM infrastructure, cost governance, observability. I write about what I'm building and learning - in real time, from first principles, not from a vendor whitepaper.
From the blog
Practitioner notes on agentic systems, LLM infrastructure, and what I learn building AI in the real world - not the demo version.
Pebble is the engine. Now I'm building the factory around it.
A few days ago I wrote about Pebble, the agentic harness I built for my software work. It is tuned the way I want, and it writes most of my code. Pebble now writes most of my code. That moved the bottleneck, and it's me. This post starts a new experiment: gFactory, my attempt at an autonomous software factory. I am building it in the open, and this is where it begins. Where my time goes When I start a new project, my work falls into three phases. Direction. I write the PRD, the tech design
I built my own agentic harness. Here is what's inside.
A while back I asked a coding agent to add a small feature to a service. It wrote the code, ran the tests, and told me everything passed. Then I read the diff. Two assertions in the test file had been loosened to match what the code did. The agent had not fixed a bug. It had moved the goalposts. The model did what the setup rewarded. One agent held every role. It wrote the spec in its head, wrote the code, wrote the tests, and graded its own work. Nobody in that session had a reason to disagree
You built the feature. You haven't shipped the product.
I reviewed a codebase a few months back where the core AI feature was genuinely good. Clean model integration, fast responses, a UI the team had put real thought into. They were proud of it, and they had reason to be. Then I asked some questions. What happens when the LLM call fails? Who gets alerted if the service goes down at 3 AM? What's the rate limit on the AI endpoint? Has anyone tested the Stripe webhook when a payment fails? The answers were: "we log something," "we'd notice," "nothin
gFactory: an autonomous software factory
Pebble takes one request to code I can trust. gFactory is the factory floor around it: many specs, many repos, the right agent and model per packet. A new experiment, journaled every Sunday.
Where I go deep
Agentic Systems
Multi-agent orchestration, supervisor patterns, memory systems, context management, MCP, tool routing. Designing autonomous loops that do real work - not demos.
LLM Infrastructure & Cost Governance
Semantic routing, SLM/LLM hybrid stacks, observability pipelines, token cost reduction. Making AI deployable at scale without the LLM Tax eating your margins.
AI Product Engineering
Spec-driven development, eval frameworks, RAG pipelines, production deployment patterns. The full system - not just the model layer.
Enterprise AI Adoption
Architecture reviews, build-vs-buy frameworks, AI governance, team structure. The decisions that determine whether an AI investment succeeds or stalls.
Tools of the trade
What I'm Thinking About
Pebble takes one request to code I can trust. gFactory is the factory floor around it: many specs, many repos, the right agent and model per packet.
Context windows are growing but the real problem isn't capacity - it's curation. What stays, what gets summarized, what gets dropped, and who decides. The difference between a useful agent and a confused one is often just better context hygiene.
Working through what "memory" actually means for a long-running agent. Episodic? Semantic? Neither pattern from human cognition maps cleanly.
Enterprise teams are spending 4–6× what they should on inference. The answer isn't a cheaper model - it's a smarter router.
How do you debug an agent that's three hops deep in a tool-use loop? The tracing primitives don't exist yet.
Pick my brain
I do a limited number of 1:1 sessions - on AI architecture, building defensible AI products, technical strategy for non-tech founders, and career decisions in tech. 25 years of context, no slides, no fluff.
Fractional CTO & Tech Advisor
Expert tech review for non-tech founders. Save dev cost before you spend it.
Build an AI Moat, Not a Wrapper
Turn your thin wrapper into a defensible AI asset.
Career Mentorship
Career clarity through honest conversation. 25 years of pattern-matching.