Changelog

Follow up on the latest improvements and updates.

RSS

New
  • Let AI execute Python code against your spreadsheets. Code execution will automatically be enabled for newly uploaded spreadsheets. You can ask the AI to do math, sum data, count rows, etc. Note: workflows pre-plans tool calls and prompts need to be refined for best results.
code execution
Example prompts:
"Analyze my sales data spreadsheet and give me a summary of key statistics for each column"
"What's the data quality like in my inventory.xlsx file? Check for missing values, duplicates, and any data inconsistencies"
"Calculate monthly growth rates from my revenue spreadsheet and identify the best and worst performing months"
"Find correlations between different variables in my marketing campaign data and tell me which factors most impact conversions"
"Compare this month's sales performance against the same month last year - show me percentage changes by product category"
  • Grok 4 available in the model selector. Note: for day zero access Grok 4 is heavily rate limited by xAI and users may see delays in requests.
image
image
  • Generate reports on the training completion status in the Admin Dashboard for individual tenants. Reports generate in a few seconds and download as CSVs.
talent lms report
Improved
  • 90% speed improvement for page loads. Workshop cards and most pages load in under 1 second. This global improvement increases loading speed across the entire platform. Note: these updates have been taken incrementally in the background over the past week.
customer dashboard speed
admin dashboard speed 2
Screen Recording 2025-07-10 at 6
  • Deprecated the "App Builder" role and replaced it with "Workshop User." Workshop Users can no longer Create or Edit apps. Workshop Users now have access to Chat functionality. All former App Builders have been automatically converted to Workshop Users. For more detailed information about roles and permissions, you can visit our knowledge base article linked here .
Fixed
  • Fixed a bug causing some users to see an unusable url input in automations and extended the url character limit.
  • Fixed a bug that sometimes caused empty workshop drafts to save after publishing.
  • Various security updates.
New
  • Support for math formulas and equation rendering.
latex markdown
  • Better table rendering.
ezgif-644e4f77f82b01
  • New thinking token rendering UI.
thinking
  • Added support for emojis 😃
image
Improved
  • Better handling of MFA factors, ability to regenerate codes and manual code entry in authenticator app as alternative.
  • Overall chat experience update including user messages sending off screen, general formatting, and look/feel.
Fixed
  • Added better support for MFA QR codes in dark mode.
New
  • New setup wizard and UI with several improvements to make getting started easy.
set wizard v1
  • Choose response profiles for your AI Agents: Verbose, Concise, Creative
response profiles
  • View call transcripts within the dashboard.
call transcript
  • Load AI Phone Agent Template optimized for specific use cases.
agent templates
  • Limit individual AI Phone Agents to specific users.
assign to users
  • Filter voices by different characteristics in the new interface.
voice selection and filtering
Improved
  • Improved AI model selection interface.
better model selection
  • All voices upgraded with both sound quality and realism.
  • Various security and speed updates in different parts of the platform.
  • Error responses for users attempting to use a model disabled for their organization.
New
  • Inline tool calling. Your tool requests from AI no longer happen behind the scenes. See exactly what the AI is doing including search and scrape queries as well as responses from the tools.
Start with a query that includes tools.
inline tool calling request
The AI will tell you exactly what it is searching, what tools it is using and the responses from the tools.
continued tools
The AI will continue to use up to four tools for each request. It can reference output from one tool into the next tool call.
final tool call
Finally, when the AI completes their tool calling it will write you summarize the information.
  • Integrations tab. Connect 3rd party integrations to your Hatz AI Account. Navigate to [subdomain]/workspace/integrations to view available integrations.
Screenshot 2025-06-18 at 9
  • Microsoft Outlook integration added. Connect your account by navigating to the integrations tab and completing oAuth. Note: your O365 administrator may need to approve the app. connect microsoft
  • Use the outlook integration from inside the secure chat by selecting the "Outlook" button, which will appear after connecting your account. Search emails, list emails, list calendar invites, create email drafts (saved to your drafts folder), send calendar invites, and decline calendar invites.
Note: We have found the best performance with Claude 4 Sonnet.
calendar example
  • Enable organization wide MFA mandate as a General Admin or through the admin dashboard tenant organization settings.
MFA Settings
  • Enable global MFA mandate for all tenants.
Screenshot 2025-06-18 at 9
New
  • Edit the name and description of drafts for apps and workflows.
output
  • Use images as an input in workflows for steps using LLMs that support vision.
inageworkflow
New
set global default 2
  • Set the default LLM for a specific tenant from the admin dashboard.
set default LLM for tenant
  • Set the default LLM as a General Admin.
set default as general admin
  • Disable LLMs Globally.
Screen Recording 2025-06-12 at 10
  • Disable LLMs for specific tenants.
tenant disable llm
  • Disable LLM as General Admin
disable as general admin2
Fixed
  • Fixed a bug causing some users to not be able to save edits to apps and workflows created by another user.
New
New LLMs including Open AI's o3 and o4-mini, Google Gemini 2.5 Pro and Flash, and Llama 4 Maverick and Scout.
image
  • Description from OpenAI:
    OpenAI o3 is our most powerful reasoning model that pushes the frontier across coding, math, science, visual perception, and more. It sets a new SOTA on benchmarks including Codeforces, SWE-bench (without building a custom model-specific scaffold), and MMMU. It’s ideal for complex queries requiring multi-faceted analysis and whose answers may not be immediately obvious. It performs especially strongly at visual tasks like analyzing images, charts, and graphics. In evaluations by external experts, o3 makes 20 percent fewer major errors than OpenAI o1 on difficult, real-world tasks—especially excelling in areas like programming, business/consulting, and creative ideation. Early testers highlighted its analytical rigor as a thought partner and emphasized its ability to generate and critically evaluate novel hypotheses—particularly within biology, math, and engineering contexts.
image
  • Description from OpenAI:
    OpenAI o4-mini is a smaller model optimized for fast, cost-efficient reasoning—it achieves remarkable performance for its size and cost, particularly in math, coding, and visual tasks. It is the best-performing benchmarked model on AIME 2024 and 2025. In expert evaluations, it also outperforms its predecessor, o3‑mini, on non-STEM tasks as well as domains like data science. Thanks to its efficiency, o4-mini supports significantly higher usage limits than o3, making it a strong high-volume, high-throughput option for questions that benefit from reasoning.
image
  • Description from Google:
    Gemini 2.5 Pro is our state-of-the-art thinking model, capable of reasoning over complex problems in code, math, and STEM, as well as analyzing large datasets, codebases, and documents using long context. Gemini 2.5 Pro rate limits are more restricted since it is a preview model.
image
  • Description from Google:
    Our best model in terms of price-performance, offering well-rounded capabilities. Gemini 2.5 Flash rate limits are more restricted since it is an experimental / preview model.
image
  • Description from Meta:
    Llama 4 Scout, a 17 billion active parameter model with 16 experts, is the best multimodal model in the world in its class and is more powerful than all previous generation Llama models, while fitting in a single NVIDIA H100 GPU. Additionally, Llama 4 Scout offers an industry-leading context window of 10M and delivers better results than Gemma 3, Gemini 2.0 Flash-Lite, and Mistral 3.1 across a broad range of widely reported benchmarks.
image
  • Description from Meta:
    Llama 4 Maverick, a 17 billion active parameter model with 128 experts, is the best multimodal model in its class, beating GPT-4o and Gemini 2.0 Flash across a broad range of widely reported benchmarks, while achieving comparable results to the new DeepSeek v3 on reasoning and coding—at less than half the active parameters. Llama 4 Maverick offers a best-in-class performance to cost ratio with an experimental chat version scoring ELO of 1417 on LMArena.
  • Display of thinking tokens fro reasoning models. Current supported models include DeepSeek, o3, and o4-mini.
thinking tokens click
Improved
  • Improved performance and speed for DeepSeek.
New
  • New LLM Selector with featured LLMs, model attributes, credit bands, searching, and other improvements.
View Featured LLMs
featured models2
Sidebar for Viewing All Models
view all models
Filter by Developer
filter by developer
Model Attributes
  • Model Descriptions
  • Capabilities (Low, Medium, High)
  • Speed (Slow, Medium, Fast)
  • Credit Usage (Lowest, Low, Medium Low, Medium High, High, Premium)
  • Vision capabilities (Images)
  • Tool usage (AI-Powered Search + Other Tools)
image
  • New model selector and sidebars in workflows and apps
image
image
  • Scrape websites as a step in workflows. Use inputs, outputs, or text.
image
website step 5
Screenshot 2025-05-29 at 9
Screenshot 2025-05-29 at 9
Screenshot 2025-05-29 at 9
Improved
  • Autoscroll in chat adjusted to make it easier for users to read outputs as they stream.
autoscroll2
  • Better responsiveness with the chat sidebar and other chat improvements.
Fixed
  • Fixed a bug causing some users to experience stream errors with long outputs lasting longer than two minutes.
New
  • New LLMs: Claude 4 Sonnet and Claude 4 Opus. Claude Opus 4 is the world’s best coding model, with sustained performance on complex, long-running tasks and agent workflows. Claude Sonnet 4 is a significant upgrade to Claude Sonnet 3.7, delivering superior coding and reasoning while responding more precisely to your instructions.
image
Improved
  • Various chat improvements including styling updates to code blocks, text-input auto resizing, and pasting user experience.
Fixed
  • Fixed bug causing legacy word files to sometimes fail file upload.
New
  • View
    your
    run history of AI Workflows. You can open the workflow run history for a specific workflow from the run view or view all run history from the "Run History" tab in Workshop. Review credits used for each step, time to run each step, and compare inputs with outputs.
run history3
Screenshot 2025-05-16 at 8
Run History Management Part 1
Run History Management3
  • Generate, view, and manage API keys outside of the customer dashboard. End customers can now generate their own API Keys.
Screenshot 2025-05-16 at 8
  • End customer MFA settings can now be accessed by navigating to Workspace > Account
Improved
  • Various improvements to AI-Powered search including the swapping of Brave Search for Google Search. The AI-Powered search button will also now stay clicked throughout a chat.
Fixed
  • Various fixes for File Upload. Some users experienced errors when uploading relatively larger files that were still under the file size limit. Improvements made to the copying and pasting of files and Office Document Contents sometimes pasting as images.
Load More