Companies
Long-term ambitions, with room to grow into something real.
The long viewSoftware × AI × Products
Another option
isn’t the goal.
A better standard is.
I’m Prathmesh Adsod, a software engineer and product builder. I work across AI, software, and creative technology to make useful ideas work better.
Products
Ideas in exploration. Useful things earn their public release.
What comes nextPublic work
Original projects and experiments. The code tells the story.
Explore GitHubWriting
A home for the decisions, questions, and lessons along the way.
Notes & newsletterIn progress
Curiosity, put to work.
I’m exploring where AI capability meets real engineering constraints—and where a thoughtful product can make the difference.
01
Make agents more dependable
Memory, tools, evaluation, and clear boundaries. What helps an AI system do useful work you can actually inspect?
02
Connect intelligence to systems
From an answer on a screen to a workflow that handles data, permissions, failures, and the next step.
03
Keep the human experience clear
Useful interfaces, honest states, and fewer unnecessary decisions. Complexity belongs in the engineering.
Selected public work
Ideas are easy.
The details
are the work.
Projects exploring memory, evidence, and the space between a promising idea and a useful system.
All public repositories01
HARK
Execution memory for Agent Skills: scoped recall, run evidence, recovery paths, and invalidation for a query-regression workflow.
02
Latch
A dataset release-review workflow combining source context, measured checks, human approval, and hash-verifiable release evidence.
03
GridForge
Off-grid solar design that normalizes web component inventory and checks panel, inverter, and battery combinations against electrical constraints.
How I contribute
Across the stack.
Close to the problem.
AI & agentic systems
LLM applications, retrieval, tool use, and memory—with explicit boundaries around what a model may decide.
Backend & data
APIs, structured data, durable workflows, and the architecture that turns an experiment into a dependable system.
Product engineering
The full path from a useful problem to a clear interface, with attention to usability, failure states, and evidence.
Applied experimentation
Exploring models and data through notebooks, evaluation, and small projects that make assumptions testable.
A principle I build by
The same script.
A different standard.
“The same script can become a good film or a masterclass. The difference is execution. I build for the masterclass.”
The idea is a starting point. Architecture, judgment, simplicity, and thousands of small decisions determine what it becomes.
More about my approachThinking in public
There’s a story
behind the shipped work.
Trade-offs, experiments, and the questions that change a project’s direction. A place to share them, when they’re worth sharing.
Writing & newsletterA little about me
Engineer by practice.
Builder by instinct.
I enjoy taking an ambiguous problem, finding what’s useful, and following it through to a working system. My interests span AI, backend engineering, applied machine learning, and thoughtful product design.
The longer introductionLet’s connect