Skip to content
View AasthaSanghi91's full-sized avatar

Block or report AasthaSanghi91

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
aasthasanghi91/README.md

Hi, I am Aastha👋

I think in systems, write in specs, and ship in prototypes.

I am building at the intersection of AI product management and developer tooling — focused on the gap between what LLMs can do and what engineers actually need from them.

What I am Working On

🔬 Provenance — An AI GitHub-to-Portfolio Engine


What I Think About

  • AI trust design — 46% of developers distrust AI output (Stack Overflow 2025). How do you build products where the AI generates and the human verifies, without making verification feel like correction?

  • LLM context tradeoffs — README-only parsing vs. RAG over embeddings vs. agentic file traversal: when does the cost/quality curve justify complexity? I wrote the full comparison in the PRD.

  • Prompt engineering as product spec — Prompts aren't engineering implementation details. They are versioned product artifacts with their own regression risk.


About Me

  • Studying AI PM craft by building real products.
  • Currently experimenting with AI workflows and evaluation systemm. Building ProvenanceAI as a working demonstration of AI product thinking — market research through to shipped prototype
  • Targeting AI PM roles where the job is to make powerful models actually useful to real people
  • I write about AI product decisions, LLM architecture tradeoffs, and the design of trustworthy AI systems
  • Always interested in talking to engineers building with LLMs and PMs navigating the "what should the AI actually do?" question

Building in public. All artifacts are real working documents,not post-hoc writeups.

Popular repositories Loading

  1. aasthasanghi91 aasthasanghi91 Public

    landing page

    1

  2. ai-investment-analyst ai-investment-analyst Public

    an AI financial Analyst

    Python

  3. competitor-intelligence-agent competitor-intelligence-agent Public

    Python

  4. rag-trust-layer rag-trust-layer Public

    Enterprise RAG tool with citation-based trust scoring for compliance and SaaS document Q&A

    Python

  5. compliance-copilot compliance-copilot Public

    AI tool that explains contract clauses, flags ambiguous terms, and generates review checklists for compliance and procurement teams

    Python

  6. saas-adoption-analyzer saas-adoption-analyzer Public

    AI-powered SaaS feature adoption dashboard that combines usage analytics with natural language PM prioritization recommendations

    Python