# Sub Agent or Super Agent, MCP UI Over Lunch, Bitter Lesson Learnings, Locking in on Prompts and Trying to Live in the Future

Page: https://stenobird.com/podcast/you-ve-been-a-bad-agent-7334728/sub-agent-or-super-agent-mcp-ui-over-lunch-bitter-lesson-learnings-locking-in-on-prompts-and-trying-to-live-in-the-future
Text version: https://stenobird.com/podcast/you-ve-been-a-bad-agent-7334728/sub-agent-or-super-agent-mcp-ui-over-lunch-bitter-lesson-learnings-locking-in-on-prompts-and-trying-to-live-in-the-future.md
Podcast: [You've Been a Bad Agent](https://stenobird.com/podcast/you-ve-been-a-bad-agent-7334728)
Published: 2025-08-06T11:40:18+00:00
Episode link: https://www.youtube.com/watch?v=8moSHUSSwKI
Audio file: https://media.transistor.fm/7753e1ba/7a100409.mp3
Processing state: processed
JSON: https://stenobird.com/v1/public/podcasts/you-ve-been-a-bad-agent-7334728/episodes/sub-agent-or-super-agent-mcp-ui-over-lunch-bitter-lesson-learnings-locking-in-on-prompts-and-trying-to-live-in-the-future
Duration seconds: 3466

## Resource

The future of AI development lies in managing context through sub-agents and standardized protocols like MCP. The discussion explores the tension between powerful models and the practical difficulties of prompt engineering and tool integration.

## Highlights
- Main idea: Sub-agents are essential for managing context windows and preventing main agent pollution
- Practical takeaway: Developing better UI for prompt engineering is more valuable than creating new SaaS-based prompt management tools
- Failure mode: Relying on custom prompting as a competitive moat is risky in an era of rapidly advancing foundational models
- Technical insight: MCP (Model Context Protocol) servers provide a standardized way to extend agent capabilities via specialized tools
- Practical takeaway: Effective AI-assisted coding requires robust feedback loops and live evaluations to overcome the volatility of model performance

## Topics

AI Agents, Model Context Protocol, Prompt Engineering, Software Engineering, Sub-agents, MCP Servers, AI Tooling, Context Windows

## Chapters
- 1:00 — Outdoor Adventures: A brief look at recent fishing and water sports experiences in Dorset.
- 10:00 — Context Management and Sub-Agents: Analyzing how sub-agents can be used to manage context windows and specialized rules without overwhelming the primary model.
- 14:00 — The Role of MCP in Agent Architecture: Discussing the use of MCP to provide sub-agents and the potential limitations of centralized agent control.
- 18:00 — Tooling and Permissions: Examining the complexities of managing actions, permissions, and disallowed tools within agentic workflows.
- 23:00 — The Volatility of AI Coding: Reflecting on the inconsistent performance of AI coding tools and the difficulty of maintaining control over prompts.
- 27:00 — Prompt Engineering and UI: Critiquing current prompt writing workflows and the need for better structured, visual interfaces for prompt development.
- 31:00 — Future-Proofing AI Skills: Discussing the importance of mastering tools and form factors that will remain relevant in the next five years.
- 40:00 — The Future of Agentic Workflows: Speculating on the shift toward highly automated, agent-driven development and the potential for new technological frontiers.

## Actions

- request_transcript: `POST https://stenobird.com/v1/public/podcasts/you-ve-been-a-bad-agent-7334728/episodes/sub-agent-or-super-agent-mcp-ui-over-lunch-bitter-lesson-learnings-locking-in-on-prompts-and-trying-to-live-in-the-future/transcription-requests` — Idempotently request low-priority transcript generation for this episode.
- read_markdown: `GET https://stenobird.com/podcast/you-ve-been-a-bad-agent-7334728/sub-agent-or-super-agent-mcp-ui-over-lunch-bitter-lesson-learnings-locking-in-on-prompts-and-trying-to-live-in-the-future.md` — Read the agent-friendly Markdown representation of this episode resource.

A page view does not enqueue transcription. Agents should invoke `request_transcript` explicitly when they need this episode processed.

## Transcript

Full transcripts are not published on public pages unless there is a clear rights basis.