Strategic
Completed

Columbia University: Beyond the Cursor

Role
Speaker — invited to present on agentic development practices and the shift from IDE to shell-level AI
User Problem
Engineers treat AI coding tools as autocomplete — missing the paradigm shift to autonomous agent execution.
Business Problem
CS programs needed practitioner perspective on how agentic systems are reshaping real engineering workflows.
Impact
Invited presentation at Columbia University CS Department.

The talk

Invited presentation at Columbia University’s CS Department. The core argument: the significant shift in AI-assisted development isn’t a better IDE — it’s when the model leaves the editor and starts executing in the shell.

I traced three generations of AI in engineering:

  1. Autocomplete (IntelliSense, Tabnine) — syntax speed, no structural understanding.
  2. Reasoning (ChatGPT, Gemini) — understanding intent behind code, but still waiting for you to act.
  3. Agency (Codex, Claude Code, Gemini CLI) — the model drives shell primitives directly. The cursor disappears.

What I covered

The execution loop. Gen 3 agents don’t just suggest — they plan, act, observe terminal output, and course-correct. The goal isn’t generating code; it’s returning a repository to a stable state after the perturbation of a new requirement.

The Google stack. How AI Studio, Gemini CLI, and Jetski work together in practice — from prompt tuning to MCP-based tool use to terminal-native execution within the google3 monorepo.

Human-in-the-loop friction. Without checkpoints, agents hallucinate libraries and create circular dependencies (“agentic drift”). Managed friction — deliberate pause points where a human verifies before the agent continues — is what makes autonomous execution reliable.

Live demo. I demonstrated a multi-agent system (organizational_agent_swarm) resolving a conflict: I asked it to create a script that bypasses its own safety checks. The Verifier agent identified the conflict with established rules, initiated a debate, and escalated to a human decision. The point: good agentic systems know when to stop and ask.

Slides | organizational_agent_swarm repo

Artifact Evidence

Project: sovereign-velocity-engine

Access Restricted

Access Required

Enter the access key to view projects

Hint: See intro email for access key.