Composio Engineer Sarah Simionescu: Dashboards Are Dead, MCP Alone Fails Agents
In a talk at AI Engineer World's Fair, Sarah Simionescu, a member of technical staff at Composio, argues that traditional dashboards and query languages are obsolete as translation layers between humans and data. She identifies three critical failures in using MCP protocols alone for agents: lack of learning from errors, context window drowning due to excessive tool definitions, and application isolation. Simionescu demonstrates mechanisms such as returning execution plans with tool searches and passing saved user cohorts between PostHog and Metabase without loading full results into context, arguing for interfaces specifically designed for agents.
ImportanceMaterialEvidenceE3 inspectableWrite-upQuick
Sarah Simionescu, a member of technical staff at Composio responsible for the company's dashboard product, presented a seemingly contradictory argument at the 2026 AI Engineer World's Fair: dashboards are dead. This claim stems from her personal experience—despite using Datadog daily for six months, she froze when asked to navigate its dashboard to view an alert. This disconnect between daily usage and interface familiarity reveals the rise of agents as a new interaction layer.
Simionescu contextualizes this shift historically. In 2022, resolving a Slack error report required traversing five tools and five query languages, each serving as a translation device between user intent and data. The 2023 'sparkle button' attempted to use LLMs to generate queries but offered limited reliability and still required dashboard access. Anthropic's release of the MCP protocol in 2024 allowed agents to connect directly to services and execute queries, yet this did not solve the fundamental problem.
The core thesis is that MCP itself is insufficient for effective agent workflows. Simionescu identifies three specific failure modes: first, agents do not learn, starting every conversation from zero and repeating yesterday's formatting mistakes today; second, connecting multiple MCP servers dumps thousands of tool definitions (such as Composio's GitHub toolkit with over 200 tools) into the context window, causing models to select wrong tools or struggle with call ordering; third, each MCP server describes only its own app, leaving cross-app tasks requiring manual stitching of steps.