Help Center
Changelog

Have something to say?

Tell BoltAI how they could make the product more useful to you.

orkflow Palette Unresponsive Across Multiple Devices; Duplicate "Instant Workflow" Entries Cannot Be Removed

Environment: App: BoltAI OS: macOS (tested on multiple devices) Issue persists after: reinstallation, shortcut reassignment Description: The workflow palette no longer opens when triggered via keyboard shortcut or UI. This issue is reproducible across multiple macOS devices and persists after the following troubleshooting steps: Reassigned the workflow palette shortcut to a different key combination. Completely uninstalled and reinstalled BoltAI. Restarted the devices. None of the above resolved the issue. Additional Issue — Duplicate "Instant Workflow" Entries (attached below): The workflow list displays multiple duplicate entries labeled "Instant Workflow." Attempting to delete these duplicates has no effect — the entries remain after deletion attempts, and no error or confirmation is shown. Steps to Reproduce: Open BoltAI. Trigger the workflow palette via the assigned shortcut or UI button. Expected: Workflow palette opens. Actual: Nothing happens. No palette, no error. Navigate to the workflow list. Observe duplicate "Instant Workflow" entries. Attempt to delete any duplicate. Expected: Entry is removed. Actual: Entry persists with no feedback. Impact: Workflows are completely inaccessible, making a core feature of the app unusable. Troubleshooting Already Performed: Shortcut reassignment (multiple combinations tested) Full uninstall and reinstall Tested on multiple macOS devices/different lics — same behavior on all

IbrahimMan 3 days ago

7

Issues with Instant Workflow, {{user_prompt}}, and Keyboard Shortcuts in BoltAI 2

Dear BoltAI Team, I am having trouble using an Instant Workflow in BoltAI 2 as intended and I am not sure whether I misconfigured something or if this is a bug. Setup macOS: latest version App: BoltAI 2 (direct license) Workflow type: Instant Workflow Settings: Input Source: Selection Agent: None (use defaults) Prompt Template: INSTRUCTION: {{user_prompt}} TEXT: {{input}} Only Text, no explanation or comments Preview Mode: No Preview (run immediately) Output Action: Paste at Cursor Issue 1 – Instant Workflow does not receive the selection In Outlook I select a German sentence in the email body. I open the Instant Chat Bar with Option+Space and type e.g. “bitte auf englisch übersetzen”. The model’s response is something like: “Please send the text you want me to translate into English.” So it seems that the selected text is not passed as {{input}} into the Instant Workflow, although Input Source is set to Selection. Question: How do I need to configure the Instant Chat Bar and/or the Instant Workflow so that the current selection is used as {{input}} and the result is directly inserted via “Paste at Cursor”? Issue 2 – {{user_prompt}} in regular workflows According to the UI hint, {{user_prompt}} is “only set for Instant”. In a regular workflow (type “Workflow”) that I trigger via the Workflow Palette, {{user_prompt}} indeed remains empty – only {{input}} is populated. My questions: Is it correct that {{user_prompt}} is only populated for Instant Workflows and will always be empty in regular workflows? Is there a way to trigger a specific Instant Workflow directly via a keyboard shortcut (without going through the normal chat UI), using the current selection as input and setting {{user_prompt}}? Is it intentional that the special “Instant Workflow” does not appear in the Workflow Palette? I would appreciate any guidance on the correct configuration or information on whether this is a known issue. Kind regards, Martin

Martin Schmid 4 days ago

Feature Request - Per-Model Parameters

Hi BoltAI Team, I'm a beta tester and I've discovered that different AI models have different parameter requirements: Issue: Moonshot Kimi requires Temperature = 1.0 (fixed) I prefer Temperature = 0.4 for Claude/GPT-4 Currently need to manually change global settings every time I switch models Feature Request: Per-model parameter override in AI Services settings: Each model can have custom Temperature, Top-P, etc. Falls back to global default if not set Auto-applies when switching models Shows "locked" icon for restricted parameters This would greatly improve UX for power users who use multiple models with different needs. Thank you for this amazing app! Regards, Greg

Greg 8 days ago

1

Responses truncated from Opus 4.5

Hi, over the past few days, and still with the 2.6.2 release (which I just installed, hoping it might fixed the issue, but alas no), responses are now truncated very quickly. Example: Analysis: Quarterly Review Template (FY26 Q1) Lens used: Template Quality Assessment + Messaging-A/B + Inherent Simplicity Executive Summary This is a template deck, not a completed review. Approximately 90% of the content consists of placeholder text ("x", "Example", "Comment", "Project name"). The deck provides structure …and then it gets truncated. This has just started happening in the last day or two. I can say, “continue” and it will go a little bit farther but then truncate again.

Eric Bowman 13 days ago

Optional local python script execution support in workflows

A lot of us code scripts (hobby or otherwise) which leverage APIs of various subsystems we want to gather information from. Once the information is gathered, there is a need to make use of AI to analyze/convert/format/summarize before presentation. Since the foundation of workflows, like custom commands to be executed at will are already there, i would like to have an optional local python script execution section with in workflows so that the input for AI is generated by the script (one of many other input areas like selection, clipboard etc). The interface need not be to embed a code editor of sort, because python scripts can span modules and multiple code files. Just an input field which takes in the python command would do. This can open up any code written by AI tools to be readily invoked using the BoltAI workflows. examples: ~/venv/bin/python service_health.py --service | AI (to explain) ~/venv/bin/python get_pipeline_failures.py —pipeline-id | AI (to investigate) I can understand if this is not feasible (like literally embed in workflow section), but would love to have the feature implemented in any other way too, so that all of us can automate many things in our day to day lives.

prasadvelidi 16 days ago

1

Bug: 'Record Shortcut' fields don't capture keystrokes

See title; I’m unable to record any shortcuts via the settings. If I try to change a preset shortcut, I end up having to reset my settings to get it back. I’ve already given BoltAI all the system permissions it needs. This could totally be a “my machine only” issue caused by one of my apps - has anyone else run into this?

harrisonfloam 17 days ago

Add / @ # commands

I would love to have in-line commands and references with autocomplete like GitHub Copilot in VS Code. / = force or strongly suggest a tool/action (ex: /search, /add_memory /code, /summarize) @ = target a tool provider # = reference artifacts, files, etc. A clean autocomplete mechanism really makes this feature useful, but would probably require tagging each option with identifiers (e.g., ‘openai:web_search’, ‘boltai:web_fetch’).

harrisonfloam 17 days ago

Problems with images

I had this issue with gpt-5.2-pro, but I am guessing it can be a problem for other models. When I drag a photo from Apple Photos into the chat window and ask a question about it the prompt is rejected with an error saying the image needs to be jpg, png, or webm. I am wondering if it gets pasted as HEIC. The image itself is visible normally in chat window after dragging in, but prompt fails. Would be great if it got converted upon dragging in. Many thanks

C Yucel 25 days ago