# The New Primitives: Building AI Native Software — Kwindla Kramer, Daily

## Executive summary

The talk traces the 80-year history of digital computing—from Vannevar Bush's predictions in 1945 to modern AI agents—to argue that current 'agents' are merely a primitive. The speaker posits that just as web pages were superseded by full web and mobile applications, agents will eventually give way to a new fully AI native software layer. This next generation requires advanced primitives like asynchronous non-blocking context compression and dynamic interface generation.

## Key takeaways

- The Evolution of Primitives: History shows that every major computing leap (e.g., web pages to mobile apps) renders the previous primitive insufficient for the next era. Agents are viewed as the 'web page' of the current AI age.
- The Next Frontier: AI Native Software: Building beyond agents requires mastering primitives such as asynchronous non-blocking context compression, long running subagents that share context, progressive skills loading, dynamic interface generation, and conversational voice.
- The Role of Abstraction: Historical examples like VisiCalc demonstrate how new abstractions (e.g., the spreadsheet) make vastly more complex work possible, creating entirely new categories of work rather than eliminating jobs.

## Technical details

- AI Agent Infrastructure: The speaker works at Daily and highlights Pipecat, an open-source, vendor-neutral framework used for building voice agents. The industry trend involves 'multimodal harnesses' that integrate models, data, and tools (e.g., GitHub Copilot).
- Historical Computing Milestones: The progression includes: Abacus $ ightarrow$ Stored Program Computer (1940s) $ ightarrow$ Personal Computer (1980s) $ ightarrow$ Global Cloud/AI Agents Era. The 1950s focused on transmitting human intent via programming languages, while the 1960s introduced interactivity and graphical programming.
- Multimodality in Computing: The web was fundamentally multimodal from its start, anticipating that text, audio, video, and data were integrated. Modern AI native software must similarly integrate these modalities.

## Practical implications

- Developers should focus on building full coherent software stacks for AI agents and anticipate the need to move beyond current agent primitives.
- The concept of 'multimodal harnesses' is critical for modern enterprise AI tools, ensuring tool access and rich context feeding.
- Understanding historical abstractions (like VisiCalc) helps counter fears of mass unemployment by focusing on new categories of work enabled by technology.

## Topics

AI Agents, Digital History, Multimodality, Software Architecture, LLMs, As We May Think, Pipecat

Source: https://www.youtube.com/watch?v=LZuWZRze3MU