Latest release:
Latest release:
Latest release:
🗂️ Agent activity classifications ⚡ Fast chart edits in Generative Apps
Explore and share insights from Generative Apps Continue your analysis in an agent thread without leaving the app, and automatically deliver CSV exports to stakeholders on a schedule. 💬 Chat with Generative Apps📎 Schedule CSV exports for Generative Apps🤖 New models to pick from
Latest release:
💬 Chat with Generative Apps 📎 Schedule CSV exports for Generative Apps 🤖 New models to pick from
Explore and share insights from Generative Apps Continue your analysis in an agent thread without leaving the app, and automatically deliver CSV exports to stakeholders on a schedule. 💬 Chat with Generative Apps📎 Schedule CSV exports for Generative Apps🤖 New models to pick from
Latest release:
💬 Chat with Generative Apps 📎 Schedule CSV exports for Generative Apps 🤖 New models to pick from
⚖️ Publish and version eval suites Did last week’s guide change actually make the agent better? Now you can answer that question without rerunning every test by hand. Publish an eval suite from the CLI, schedule it to run automatically, and track its performance over time in Context Studio. Turn the questions you test repeatedly into a versioned suite, then compare results as your guides or semant…
Publish eval suites, skip approvals, and build Hex projects from your chat agent Publish and schedule eval suites, let the agent work without stopping for approvals, and build Hex projects straight from your chat agent. ⚖️ Publish and version eval suites✅ Skip agent approvals🛠️ Your chat agent can build in Hex
Latest release:
⚖️ Publish and version eval suites ✅ Skip agent approvals 🛠️ Your chat agent can build in Hex
🎮 More control over Generative app iteration 📎 Analyze CSVs directly in Slack 🔑 Clearer OAuth errors in published apps 🔐 Bring your own AI provider 🔎 More visibility and model choice for BYOK
🎨 Generative chart controls Previously, even small edits to your charts in generative apps required new prompts to the agent. Now, you can build custom, code-generated apps with the Hex Agent, and then use the Style panel to make point-and-click chart polishes. Some edits you can now make this way:
🎨 Generative chart controls Previously, even small edits to your charts in generative apps required new prompts to the agent. Now, you can build custom, code-generated apps with the Hex Agent, and then use the Style panel to make point-and-click chart polishes. Some edits you can now make this way: Update the chart title, style and height Restyle series and change the colors Rename axes Control le…
Chart controls and easier collaboration Fine-tune generative charts directly with point-and-click controls, and collaborate more safely with shareable results for OAuth-backed connections. 🎨 Generative chart controls🔐 Shareable results for OAuth connections
Latest release:
🎨 Generative chart controls 🔐 Shareable results for OAuth connections
August 18, 2026Semantic projects via CLIYour semantic projects from Hex can now live where the rest of your code does.⌨️ Semantic projects via CLI Semantic projects via CLIAugust 18, 2026⌨️ Semantic projects via CLI Pull your semantic spec out of Hex and into your repo, for local development and source control. This makes it easier to audit context or track what's changed. Read and export semantic…
⌨️ Semantic projects via CLI
🤖 Quickly toggle from chat to notebook 💬 The Hex Agent reads the whole Slack thread
⚡ Fast mode Need an answer now? Flip on fast mode in the model picker to push Opus models to 2.5x faster token output, at increased usage. The boost is most dramatic on long blocks of pure token output: big explanations, large blocks of code, or heavy reasoning. Questions that require a lot of query
⚡ Fast mode Need an answer now? Flip on fast mode in the model picker to push Opus models to 2.5x faster token output, at increased usage. The boost is most dramatic on long blocks of pure token output: big explanations, large blocks of code, or heavy reasoning. Questions that require a lot of querying and tool calls will still feel faster, just less dramatically, since a chunk of that time is cal…
Tune how the agent runs Get answers faster, pick the right model for the job, and ensure all Explorers are using endorsed data. ⚡ Fast mode🧠 GPT-5.6 Sol, Terra, and Luna✅ Default new Threads to Endorsed mode🏷️ See which model Auto picked
Latest release:
⚡ Fast mode 🧠 GPT-5.6 Sol, Terra, and Luna ✅ Default new Threads to Endorsed mode 🏷️ See which model Auto picked
🧪 Introducing EvalsMeasure how the Hex Agent performs and test context changes safely before they ship, all from the CLI.🧪 Introducing Evals🧪 Introducing Evals 🧪 Introducing Evals Measure Hex Agent performance and test context changes safely before they ship, all from the CLI. If you've added a guid
August 4, 2026🧪 Introducing EvalsMeasure how the Hex Agent performs and test context changes safely before they ship, all from the CLI.🧪 Introducing Evals 🧪 Introducing EvalsAugust 4, 2026🧪 Introducing Evals Measure Hex Agent performance and test context changes safely before they ship, all from the CLI. If you've added a guide or tweaked a semantic model, Evals helps you measure whether it actual…
🧪 Introducing Evals Measure Hex Agent performance and test context changes safely before they ship, all from the CLI. If you've added a guide or tweaked a semantic model, Evals helps you measure whether it actually helped — before you publish. To do that, define a suite of test questions with expect
🧪 Introducing Evals Measure Hex Agent performance and test context changes safely before they ship, all from the CLI. If you've added a guide or tweaked a semantic model, Evals helps you measure whether it actually helped — before you publish. To do that, define a suite of test questions with expected outcomes and run them against the Hex Agent. Evals turn agent quality and cost into something tha…