BlogsHexConnected Apps for Agent Context

Connected Apps for Agent Context

Connected Apps for Agent Context

5
posts
2026

Hex has evolved its customer data presentation from a static dashboard (Account 360) to a more dynamic, conversational interface (Threads). This shift allows customer-facing teams to ask direct questions of their data, receive real-time answers, and gain deeper narrative insights into customer behavior and history. The underlying data sources (support tickets, product usage, revenue) remain, but the access and interaction model has been significantly improved for speed and depth of understanding. Agent Tasks further enhances this by enabling scheduled, automated execution of agent queries, delivering results directly to users via Slack or email, and allowing for follow-up questions and learning from previous runs to track changes over time.

2026

Fed for a day

6/25/2026

This post discusses the evolution of data tools, contrasting 'fed for a day' (constrained, UI-driven) with 'fed for a lifetime' (primitive-based, code-centric). It positions Hex as a 'fed for a lifetime' tool, emphasizing its cell-based architecture (code, charts, markdown) as primitives that enable users to build and organize information freely. It highlights how this code-centric approach allows agents to reason about code more effectively and enables faster setup for data exploration compared to traditional, months-long implementations. The post also touches on the role of AI in enabling learning and the importance of teaching users how to prompt effectively and critically evaluate AI-generated answers.

Introducing Agent Tasks

6/16/2026

Introduced Agent Tasks, a feature that allows scheduling of Hex Agent prompts to run automatically. This enables recurring automated data analysis and delivery of results to Slack or email. The feature supports referencing previous runs for trend analysis and follow-up questions within the delivery channel.

Bring the web to your data

6/11/2026

Introduced web search capabilities for the Hex Agent, enabling it to query external web sources. This includes two primary functions: open-ended search for information retrieval and URL extraction for data enrichment. The integration allows the agent to automatically leverage these tools when external context is required, seamlessly bringing web data into existing analysis threads.

Connect Hex to the rest of your stack

5/28/2026

This post introduces the capability for the Hex agent to integrate with external applications (Notion, Linear, MCP servers) to enrich its context. It details how this integration allows the agent to reason across data warehouse information and external documents/tickets, providing more informed answers. The technical implementation leverages individual authentication for each connected tool to maintain existing permission structures.

Tactics for credit efficiency in Hex

5/20/2026

This post details tactics for optimizing AI credit efficiency within Hex. It explains the effort-based AI pricing model and provides three key tactics: 1. Building out context through table metadata, endorsements, and guides, including programmatic syncing from GitHub and leveraging existing Hex projects as context. It also emphasizes keeping guides concise and using Context Studio to monitor usage and identify areas for improvement. 2. Educating users on smarter prompting, including referencing existing assets like Collections and Data Apps, and reserving high-cost models for complex tasks. 3. Utilizing admin controls for managing and planning spend, such as setting thoughtful add-on caps and per-user credit allocations.