About Quest & Crossfire
Practical AI, connected knowledge, and clearer systems.
Quest & Crossfire is where I document the work, thinking, and learning behind practical AI systems. It connects my focus on AI Engineering with Personal Knowledge Management—the discipline of turning scattered information into knowledge that can be retrieved, tested, and used.
The idea behind the name
From complexity to clarity.
Quest represents curiosity with direction: asking better questions, following evidence, and learning through building.
Crossfire represents the point where ideas, tools, constraints, and human needs meet. Useful systems emerge from working through that complexity—not avoiding it.
That is the purpose of Quest & Crossfire: to explore difficult problems, connect knowledge across domains, and turn what is learned into practical systems and resources.
Follow better questions.
Build context across ideas.
Turn learning into useful work.
Two connected focus areas
What I focus on.
AI Engineering
I design and build applications using large language models, retrieval-augmented generation, AI agents, and automation. My interest is not AI for its own sake; it is creating systems that are useful, testable, understandable, and grounded in real user needs.
Personal Knowledge Management
PKM is the practice of capturing, connecting, retrieving, and applying knowledge. I explore workflows and tools that help people think more clearly, learn continuously, and avoid losing useful context.
AI systems depend on knowledge quality. PKM provides structure, context, and traceability; AI makes that knowledge easier to search, synthesize, and use. Quest & Crossfire explores this intersection through projects, notes, experiments, and reusable resources.
About the founder
I’m Asheesh Ranjan Srivastava.
I am an AI Engineer based in Lucknow, India. I focus on building practical systems with LLMs, RAG, agents, and automation.
My foundation in systems thinking came through education and social impact, including my work as a Gandhi Fellow in Surat. That experience taught me to look beyond isolated problems, understand the surrounding system, and begin with the people the work is meant to serve.
Today, I bring that perspective to AI Engineering through architecture design, experimentation, debugging, product thinking, and continuous learning.
Earlier nonprofit education experience
These metrics describe nonprofit education work, not AI Engineering experience. They inform a people-first approach to technology and systems.
Working principles
How I approach the work.
Useful before impressive
A focused system that solves a real problem is more valuable than a complicated demonstration without a clear user.
Evidence before inflated claims
Results should be measured, limitations should be visible, and placeholders should remain placeholders until evidence is available.
Systems over isolated tools
Models matter, but so do data, retrieval, evaluation, interfaces, workflows, and human judgment.
Learning should compound
Projects, notes, and experiments should create reusable knowledge—not disappear when the immediate task ends.
Explore Quest & Crossfire
Projects, learning, and useful resources.
Portfolio
AI Engineering projects, architecture decisions, technical challenges, and documented outcomes.
View Portfolio →Learning Hub
Practical notes on AI Engineering, PKM, systems thinking, and lessons learned while building.
Explore the Learning Hub →Resources
Selected tools, frameworks, templates, and references that support better building and learning.
Browse Resources →Build with clarity
Let’s turn complex problems into useful systems.
I’m open to AI Engineer opportunities, thoughtful collaborations, and conversations about practical AI and knowledge systems.