# Praneeth Ravuri

> AI engineer at Tuskira, building memory and tools for security investigation agents. Previously worked on network-flow processing at Lumen and internal web tools at ADP.

Personal portfolio of Praneeth Ravuri, an AI Engineer based in Chicago, USA. Updated 2026-10-04. The Markdown portfolio contains current experience, project descriptions, technologies, education, and contact details, generated from the same content as the website.

Read-only personal portfolio; there is no hosted API or MCP endpoint. Employer names describe work experience, not the publisher of this site.

## When to use this

- [Agent instructions](https://praneethravuri.com/agent-instructions/index.md): Use this site to understand Praneeth Ravuri’s experience with security investigation agents, agent memory, MCP integrations, and Go backend systems; compare project implementations; and find professional contact details. Read with GET and Accept: text/markdown, or follow the explicit Markdown links. Project execution instructions live in the repositories.

## Portfolio

- [Full portfolio in Markdown](https://praneethravuri.com/index.md): Experience at Tuskira, Lumen, and ADP; projects; education; skills; and contact information.
- [Portfolio website](https://praneethravuri.com): The human-readable version.
- [About Praneeth Ravuri](https://praneethravuri.com/about/index.md): Engineering background, education, and the scope of this personal portfolio.
- [Contact Praneeth Ravuri](https://praneethravuri.com/contact/index.md): Professional inquiries and project questions.
- [Privacy notice](https://praneethravuri.com/privacy/index.md): Hosting, analytics, performance measurement, email, and external links.

## Projects

- [Developer project resources](https://praneethravuri.com/projects/index.md): Source code and README setup links for Tether, Gary, Pitstop, Smart Traffic, and Notstuck.
- [Tether](https://github.com/praneethravuri/tether): Coding agents in separate terminals need a way to talk and coordinate edits. Tether gives them a shared inbox through a local CLI. Agents can send questions, wait for replies, leave handoffs, and claim files they plan to work on. A Go daemon stores messages in SQLite and connects sessions across Git worktrees.
- [Gary](https://github.com/praneethravuri/gary): Gary takes a master resume and a job description and produces a tailored Word document. Three agent passes analyze the role, draft the resume, and check the result against the source material. A document template keeps the formatting consistent, and Google Sheets records the application details.
- [Pitstop](https://github.com/praneethravuri/pitstop): Pitstop brings Formula 1 data into an AI chat through MCP. Its tools cover race results, standings, schedules, telemetry, and news. For questions about a race, it can compare lap pace, summarize stints, and calculate how lap times change over a tire stint. It combines FastF1, Jolpica, and OpenF1 with a queryable SQLite database.
- [Smart Traffic](https://github.com/praneethravuri/traffic-congestion-reduction-with-SARSA): A university team project exploring how reinforcement learning can control a four-way intersection. A SARSA agent chooses which direction gets a green light, using accumulated vehicle delays to represent traffic conditions. Pygame shows the traffic simulation, while learning curves track the agent’s behavior during training.
- [Notstuck](https://github.com/praneethravuri/notstuck): Upload a PDF, Word document, or text file, then ask questions about it. Notstuck splits the document into chunks, embeds them, and retrieves relevant passages from Pinecone. A chat interface shows the answer alongside document references. The assistant also has a web-search tool for questions beyond the uploaded files.

## Optional

- [GitHub](https://www.github.com/praneethravuri): Praneeth Ravuri's GitHub profile.
- [LinkedIn](https://www.linkedin.com/in/prav10): Praneeth Ravuri's LinkedIn profile.
- [X](https://x.com/praneeth2510): Praneeth Ravuri's X profile.