In 30 seconds
Asked about common agent-building mistakes, Jared Zoneraich advises teams to account for model progress and avoid scaffolding that fights the model's capabilities.
- 1Account for model progressZoneraich says teams should consider the direction of model development.
- 2Avoid fighting the modelHe recommends allowing the model to use its capabilities instead of forcing every step.
- 3Revisit scaffoldingHe predicts that stronger models will need less surrounding scaffolding for some tasks.
Takeaways
- Consider how model capabilities may change when designing an agent.
- Let the model handle tasks it can perform rather than adding unnecessary direction.
- Zoneraich expects improving models to reduce some scaffolding needs over time.
Read the edited text by chapter
Designing as models improve
Zoneraich discusses model progress and agent scaffolding.
Asked about mistakes in building AI agents, Cognition builder-in-residence Jared Zoneraich says teams should account for progress in model capabilities. He recommends designing with the direction of model development in mind and avoiding unnecessary scaffolding that forces the model into a particular path. In his view, improving models will reduce the amount of surrounding machinery needed for some tasks; this is his expectation rather than a universal rule for every agent.
More from this channel
46:40EN
17:50EN
15:03EN
33:09EN
13:05EN
1:06EN