Vibeleaderboard
← All Intel
Intel / video

Dashboards Are Dead — Sarah Simionescu, Composio

Source
youtube.com
Author
AI Engineer
Date

Context

An that works across apps needs a way to find the relevant tools and coordinate their use. The interface described in this Composio talk combines tool search with execution plans, addressing the problem that too many tools can drown the model.

Its cross-app analysis demo, run across PostHog and Metabase, is described as working without loading full query results into the model's . The design separates access to business data from loading all of that data into the conversation. It offers a concrete approach to cross-app work without establishing the talk's broader claim that dashboards are obsolete.

Key takeaways · AI-distilled
  • Simionescu names three reasons wiring up a dozen servers falls apart: agents don't learn, too many tools drown the model, and every app is isolated from the others.
  • She frames dashboards and query languages as translation layers: in 2022 teams juggled five tools with five query languages, then got AI 'sparkle buttons' in 2023 and MCP in 2024, when what users wanted was the answer rather than the dashboard.
  • Her own example: she used Datadog every day for six months without ever opening its dashboard.
Terms in this piece · Glossary
  • AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
  • context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
  • MCP — The Model Context Protocol — an open standard that lets any AI assistant plug into any tool or data source without custom integration code.
Read the source www.youtube.com
More from AI Engineer
Recommended reads
Comments

Checking sign-in…

Loading comments…