# Agent Frameworks Considered Harmful — Rémi Louf, .txt

## Executive summary

The talk details the creation of a robust, event-driven agent runtime system designed to overcome limitations in existing AI frameworks and chat interfaces. The core innovation is moving from string-based prompts and complex graphs to an auditable, content-addressed store where every component (system message, skill description, user question) is hashed and stored separately. This architecture ensures full traceability, allowing for precise diffing between runs and reliable replaying of requests against different models, making the system highly debuggable and scalable.

## Key takeaways

- Event-Driven Architecture (EDA): The system relies on agents subscribing to typed events rather than maintaining complex graphs with edges. This simplifies orchestration significantly, allowing for 'funneling' and 'fan out' without requiring code knowledge; users only need to know what events exist in the system.
- Content-Addressed Prompt Store: Prompts are no longer rendered strings. Instead, every part (system message, skill description, tool definition, user question) is hashed and stored as an identifier. A prompt is represented as a list of these hashes, enabling precise auditing.
- Enhanced Observability: The system implements two key boundaries: typed tool calls and typed events. This rigorous typing prevents malformed or non-existent inputs from breaking the pipeline, which was necessary because early failures included rejected/malformed events.

## Technical details

- Agent Orchestration: The system uses a declarative approach where agents are defined as markdown files, allowing non-coders to contribute. The runtime handles the execution flow based on event emissions (e.g., a voice note agent emits 'voice_note_processed', which triggers a daily brief agent).
- Prompt Versioning and Diffing: By treating prompts as graphs of hashes rather than rendered strings, the system allows users to perform accurate diffs between runs (e.g., identifying if only the user message changed) and reliably replay old requests using different models.
- System Logging: A central, append-only events table serves as the system's memory. All events are causally linked, which is crucial for debugging complex multi-agent workflows and preventing data loss (e.g., lost notes or uncounted attempts).

## Practical implications

- Implementing background agents (like the robot mower analogy) can automate complex daily workflows and process random thoughts into structured outputs.
- The speaker advises that small companies should 'build before they buy' when evaluating AI solutions to understand their exact needs and limitations.
- For developers building frameworks, adopting a typed event/tool call boundary is critical for making bad actions impossible, improving reliability over existing unstructured methods.

## Topics

AI Agents, Event-Driven Architecture (EDA), Prompt Engineering, System Observability, Software Orchestration, The Typical Set, Blog Post on Typed Events

Source: https://www.youtube.com/watch?v=KHudyx5wW3U