Talk to Nishant about
How Nishant thinks
Prompt chaining
Uses prompt chaining to decompose complex tasks into manageable sub‑problems.
For you: You can break down challenges into steps and let each LLM focus on one.
Agentic design patterns
Frames AI agents as autonomous, goal‑oriented entities that perceive, decide, and act.
For you: You can treat an LLM as a goal‑driven agent that plans and learns.
Modular pipeline design
Designs modular pipelines that separate reasoning from deterministic actions, improving clarity and control.
For you: You can build a clear pipeline that isolates planning from execution.
Ask this first
- How do you apply prompt chaining in real projects?
- What challenges did you face building agentic systems?
- Can you share insights from your internship at Technocolabs?
Nishant's brain
Recently updated
GitHub Codespaces gives me a cloud‑hosted development environment that I can spin up instantly from any repository, pull‑request, commit…
All users have access to the free tier of GitHub Issues and Projects.
The GitHub Copilot app is the only desktop‑only, agent‑driven development environment that runs on macOS, Windows, and Linux. It works with…
GitHub Actions is GitHub’s integrated CI/CD and automation platform. It offers a variety of hosted runners—including Linux, macOS, Windows…
I captured a snapshot of the MCP marketplace UI, which lists all available MCP server integrations. The UI shows a total of 394 servers…
I manage GitHub Copilot code‑review permissions for unlicensed members in my organization. By default the feature is disabled, and enabling…
If you do elect to enable this feature, the copyright responsibility is ours, not our customers.
GitHub Copilot handles user data according to the access mode (IDE chat vs. other code completions). The service acts as a data controller…
I designed NuroFlow with a clear separation of responsibilities: reasoning, planning, execution, validation, and response. I use LangGraph…
I built the voice assistant workflow in NuroFlow by extending the existing text pipeline. Audio recorded in the browser is sent to the…
I use multiple specialized agents (true).
I designed NuroFlow with a clear, modular pipeline that separates reasoning from deterministic actions. The flow goes from the User through…
I adopted GitHub’s Code Review and Pull Request workflow to keep code moving and the main branch green.
GitHub’s marketing page highlights the combined power of GitHub, Copilot, and AI tools, emphasizing collaboration, security, and rapid…
I encountered a GitHub login page on Windows that reported session conflicts caused by actions in other tabs or windows. The page displays…
I use prompt chaining, also called the Pipeline pattern, to break complex tasks into a series of manageable sub‑problems, letting each LLM…
Hypothesis 5: The Goal‑Driven, Metamorphic Multi‑Agent System
I describe Level 3 as “The Rise of Collaborative Multi‑Agent Systems”, where a central “Project Manager” agent coordinates specialist…
I define an AI agent as an LLM that perceives its environment, plans, uses tools, and learns, and I capture its operation in a repeatable…
I wrote *Agentic Design Patterns: A Hands‑On Guide to Building Intelligent Systems* to give developers a practical, accessible resource…
I introduce *Agentic Design Patterns: A Hands‑On Guide to Building Intelligent Systems* by framing intelligent agents as autonomous…
I reflected on four decades of technology cycles and noted that the current AI cycle differs from previous “AI summers” and “winters.” The…
I write the foreword for *Agentic Design Patterns: A Hands‑On Guide to Building Intelligent Systems* to signal the importance of moving…
I open this book with a heartfelt dedication to my family and a gratitude list for the many colleagues, teams, and external pioneers who…
I am Nishant Kumar, currently an intern at Technocolabs Softwares Inc. in Ropar, Punjab, India, while pursuing a B.Tech in Engineering…