mulch
Back to the app →

Changelog

What's changed

A running log of updates to Mulch during the private beta, newest first. Since this is a proof of concept moving quickly, expect this list to grow often. Check back if you're curious what's new.

  • While you wait for a reply, leaves now drift down under the breathing reminders and pile up, so a long wait has something to show for it. Turn it off in App Settings; it never shows if your device is set to reduce motion.
  • When you start a new note or click Clear during a learning edge reflection, Mulch now shows "Saving your learning edge reflection…" while it saves, so you know the click worked. Extra clicks while it saves are ignored.
  • Copy note now stops at the note's "Next session:" line, so a comment from Mulch after the note never ends up in your EHR. Mulch also puts any such comment before the note instead.
  • The Assessment can now speak in the present tense about where the client is now: current severity, prognosis, and why another session is needed. What happened in the session stays in the past tense.
  • When a dictated word doesn't seem to fit (like "careful" where you may have said "tearful"), Mulch asks you before writing it into the note, instead of guessing.
  • Mulch keeps your own words for how the client described their experience, instead of swapping in a word that means something a little different.
  • Fixed: a learning edge reflection could quietly fail to save when Mulch repeated the "Learning Edge Reflection" heading partway through, for example while helping you shift an edge. Save and end disappeared, and starting a new note deleted the reflection. A repeated heading now continues the same reflection.
  • Starting a new note or clicking Clear now checks that your reflection saved first. If it didn't, Mulch asks before deleting the conversation, so you can stay and try Save and end again.
  • Starting a Learning Edge Reflection now lets a handful of small leaves fall from the button. They swing side to side as they drift down over the conversation, then fade. In dark mode some are cream. It replaces the seeds. The App Settings switch is now called "Leaf fall when you start a reflection," and its description and the Help page say leaves too. It's still off if you turn it off in App Settings or your device is set to reduce motion.
  • On a phone in light mode, the reminder dot beside Menu is a slightly deeper coral so it's easier to see against the white bar.
  • The Weekly Learning reminder dot is a little bigger, a lighter coral, and sits right after the words "Weekly Learning" instead of off to the left. On a phone, the dot beside Menu matches it.
  • A greener green: the sidebar, links, outlined buttons and the Mulch mark are now a forest green that no longer reads as black, and the word "mulch" in the logo matches the mark. In dark mode the sidebar is a deep forest green too.
  • Starting a Learning Edge Reflection now drops four small seeds onto the conversation, and each one sprouts a little green seedling before they fade. It replaces the red line. It's still off if you turn it off in App Settings or your device is set to reduce motion.
  • On a phone, the bar at the top of a note is shorter: Note Options and Clear sit beside the note's name, and the actions fit on fewer lines, so more of the conversation shows.
  • On a phone, the sidebar is now behind a Menu button at the top right, so the conversation gets the screen. Menu opens it over the page, and picking anything, tapping outside it or pressing Escape closes it. Menu shows the Weekly Learning dot too, and is outlined when your next step is in the menu.
  • One outlined button now marks your next step, and it moves as the session goes: Send while you're talking it through, then Copy note once the note is written, then Learning Edge Reflection, then Send again during the reflection, and finally the note type under Write new for the next session. In Reflect First, Write Progress Note is outlined once the reflection is saved. Everything else is a plain link.
  • Copy note is now also in the bar at the top, under Draft, so you don't have to scroll to the bottom of a long note. It copies the newest note you haven't copied yet. The Copy note at the foot of the note still works.
  • The sidebar now shows on Learning Edges, Weekly Learning, Reflection History and the Field Guide too, with the page you're on highlighted. Back to Notes is still at the top.
  • Held edges show Edit, Make active and More (Settle, Delete) on each card, without clicking the card first. Every card now says "No reflections yet" when it has none.
  • On a phone, the sidebar strip wraps onto labeled rows, so the Learn pages are on screen without scrolling sideways.
  • New in App Settings: Note types to show. Turn off Therapy, Coaching or Supervision to leave them out of Write new and the start screen. At least one stays on, and Reflect First always shows.
  • Reflect First on the start screen now looks like the note types, and Clear is in red so it reads as the delete it is.
  • The sidebar's "Write" is now "Write new". Picking any note type there, including the one you have open, starts a fresh conversation, so the New Note link is gone from the top of the note.
  • Mulch now asks before deleting a conversation that hasn't produced a note yet, if you've written anything in it (including text you haven't sent). This covers starting a new note and Clear, and Reflect First conversations too.
  • Fixed: some learning edge reflections had no Save and end button and weren't saved to your practice history. If one of yours was missed, open that conversation and then leave it, and it saves.
  • Starting a Learning Edge Reflection now draws a red-ink line under the button, and one seedling grows up from it before it fades. It replaces the sprouts. It's still off if you turn it off in App Settings or your device is set to reduce motion.
  • Dictation that stops on its own now tells you. If the browser stops turning your speech into words while the mic still looks on, Mulch quietly restarts it. If that doesn't work, the mic turns off with a low two-note sound, and a red note under the box says dictation stopped.
  • When you put a learning edge into your own words as a when-then rule, Mulch saves it as you said it. It no longer rewrites it or asks whether it's complete. This works the same in learning edge reflections and Growth Conversation.
  • Copy note is now a button inside the note's white box, at the bottom, so it's clear which note it copies. Learning Edge Reflection is a button too, and New Note is back to a plain link.
  • Mulch has its real logo: a hand-drawn sprout, in the header of every page and on the browser tab.
  • Your deliberate edge is now called your active edge. Nothing else about it changes.
  • The start screen shows your deliberate edge as a card above the note types, so it's in mind before you start. Click it to open Learning Edges.
  • Therapy, Coaching and Supervision notes show a small "deliberate" tag with your deliberate edge at the top of the conversation. It scrolls away with the messages, and clicking it opens Learning Edges.
  • Each learning edge now has a short headline above the red line, with the full edge written out below it. Mulch wrote headlines for the edges you already have; you can change any of them with Edit.
  • When you add an edge, Mulch suggests a headline before saving it. Use it, try another, or write your own. When you change an edge's wording, Mulch offers a new headline and keeps the one you have unless you pick the new one.
  • Reflection History opens on a new All tab: everything you've saved, reflections and self-reports together, grouped by day and marked with what kind each one is. The other tabs are still there.
  • A new look across the app and these pages, in light and dark: serif type for headings and for your own words, a dark green sidebar, square paper-like boxes, and a new placeholder logo.
  • Learning Edges shows your edges as index cards. Your deliberate edge sits on its own card; held edges are cards in a grid, and clicking one shows its actions.
  • Reflection History groups each page by day.
  • The reminder to keep things de-identified now also sits under the Growth Conversation message box.
  • On a phone, the sidebar becomes a strip across the top, so the conversation gets the whole width.
  • Mulch now loads its fonts from its own server, and Google Analytics runs only on the public sign-up page, never inside the app. The Privacy Policy says so.
  • Learning Edges has its own place in the sidebar, first under Learn. Your deliberate edge has its own card, held edges are listed below it, and you add an edge from the top of the page.
  • Mulch now asks before deleting a note you haven't copied yet, when you start a new note or clear the conversation.
  • Process notes keep their Copy button after a reload, and a typed request for a process note gets one too.
  • Growth Reflections is now called Growth Conversation, and the Process Note button reads Write Process Note.
  • Clear asks before it deletes the conversation.
  • Growth conversations have a length limit: Mulch starts winding down after about 15 of your messages and closes the conversation after 20. Start a new one anytime.
  • The hidden message that starts a conversation no longer shows when you reopen it.
  • Weekly Learning reminder: turn the reminder dot on or off, and choose which days it shows, in Settings, App Settings.
  • When Mulch offers labels for your interventions, it lists each moment with lettered label options to choose from, instead of folding them into one list of questions.
  • New Field Guide, under Learn: twelve areas that research and clinical experience point to in helping relationships that work, with notes on how strong the evidence is for each. It also opens in a panel beside a growth conversation.
  • The sidebar's Reflect heading is now Learn.
  • Growth Reflections follows what you bring: something you want to work on, the big picture of your practice, or something heavy from the work. While you shape an edge, Mulch may name an area from the Field Guide as a possible fit, for you to decide, and may ask what you already know or do well first.
  • Dark mode: choose Auto, Light, or Dark in Settings, App Settings. Your choice follows you between devices.
  • Settings is one window with categories: Clinician Profile, Note Settings, App Settings, and Help & Legal.
  • Notes: Mulch asks about the session in plain language and checks the Assessment with you before writing it, so the clinical meaning stays yours. It translates your words into clinical language rather than adding meaning of its own.
  • A small burst of sprouts rises from the Learning Edge Reflection button when a reflection starts. Turn it off in App Settings.
  • A lighter color palette and logo.
  • Mulch no longer assumes your pronouns.
  • The opening screen shows the ways to start in the middle of the page: a note type, or Reflect First.
  • Once your note is written, New Note is outlined so it's easy to find.
  • Mulch stays reflective and supportive without cheerleading or grading your work.
  • The actions for the open conversation sit in a bar above the chat, grouped under Draft and Reflect. Full Review & Rewrite is now Review & Revise. SOAP and supervision notes are recognized too.
  • A new message box: your text, Dictate, and Send in one place. Alt+M starts and stops dictation, and Enter always sends, even while you're dictating.
  • Notes always ask about homework, and name the areas of functioning when you describe severity.
  • Asking for a process note ends and saves an open learning edge reflection, as asking for a progress note does.
  • The sidebar is for getting around: Write and Reflect, with Settings, Support and Log Out at the bottom. The actions for the open conversation moved above the chat.
  • Reflection History is in tabs and loads one page at a time, so it opens faster.
  • A small dot on Weekly Learning reminds you from Friday through Sunday until that week's entry is written.
  • Growth Reflections uses the same sidebar as your notes and waits for you to click Start Conversation.
  • Asking for a note ends and saves an open learning edge reflection. A note asked for after Reflect First keeps all its usual steps, including lettered label options and the blank "Next session:" line.
  • A learning edge you agree on in a reflection is saved for you, and reflections are filed under the edge they were about, with no card to answer.
  • Save and end appears only after you've answered the reflection's first question.
  • Learning edges no longer ask for a domain.
  • Mulch no longer asks you to confirm an extended session you've already described.
  • Growth Reflections never asks you to name specific clients. If you bring up a case yourself, it follows your lead.
  • Learning edge reflections are as short as you need. When your edge went well, Mulch reflects briefly and offers "Ask more about what went well" instead of asking questions. A Save and end button lets you stop anytime.
  • Mulch works as a reflective partner: it asks rather than grades, praises, or prescribes. When you ask for feedback on your work, it points you to the people who support you. Name them in Clinician Profile, under Supports for your clinical work.
  • Behind-the-scenes markers no longer show up in Mulch's replies.
  • Saved reflections now go through the same check that removes anything that could identify a client, as self-reports do.
  • Reflection History says why a note has no self-report.
  • Notes no longer ask for or include the next session date. Each note ends with a blank "Next session:" line for you to fill in after you paste it into your EHR. This keeps appointment dates out of what Mulch receives.
  • Deliberate Practice Reflection is now called Learning Edge Reflection.
  • Growth Reflections saves itself, with no save button to remember, and comes back after a refresh or a trip to your notes.
  • The reminder to keep things de-identified now lists exactly what to leave out.
  • Clear now saves your self-report from the conversation before deleting it, so clearing the slate at the end of the day doesn't lose it.
  • Dictation no longer beeps mid-sentence or drops words when Chrome restarts listening.
  • Growth Reflections reads dates as "today" or "3 days ago" instead of doing its own calendar math.
  • Learning edges: one deliberate edge you carry into every session, plus any number of held edges that are alive but not your current focus, and settled ones kept as history. Manage them in Learning Edges, from Clinician Profile or the Growth Reflections sidebar. Your current learning objective became your deliberate edge.
  • Deliberate Practice reflections now ask how your deliberate edge showed up and whether the session touched a held edge, and can stay with a held edge instead of steering back. After a reflection saves, you can attach it to the edge it was about.
  • When Mulch suggests a new learning objective, it now asks before saving it.
  • Session self-reports: when you start a new note, Mulch turns the previous note conversation into a short record of what you said about yourself (your state, reactions, what you tried and why), with anything that could identify the client removed. Read, edit, or delete them in Reflection History; Growth Reflections reads your latest 60.
  • Saved reflections can now be deleted from Reflection History.
  • Corrected the help page, beta page, and privacy policy on how long note conversations are kept.
  • Added Terms of Service and Privacy Policy pages, linked from the signup and login screens and from Settings.
  • Deliberate Practice and Growth Reflections now save automatically as soon as you navigate elsewhere in the app, close the tab, or log out (not only when the closing message says so), fixing cases where a reflection could go unsaved without any indication.
  • Added a "Save Reflection" button right in the chat box for both reflection types, so you don't have to look for it in the sidebar.
  • Behind-the-scenes cleanup to how note-format instructions are organized. No visible changes.
  • Fixed a login bug where an account created with different capitalization or extra spaces in the email wouldn't log in, even with the correct password.
  • Note intake now asks about extended sessions and anything else to add in the same message as confirming intervention labels, instead of as a separate step later.
  • Deliberate Practice reflections now open by asking how your focus area showed up, rather than guessing at a specific moment from the note.
  • Deliberate Practice reflections are shorter and more focused: one question per turn.
  • Ending a Deliberate Practice reflection (e.g. "that's enough," "I'm good") now saves it in that same reply.
  • Added Weekly Learning: once a week, jot down one case that stood out and one thing worth remembering. No AI involved.
  • Fixed a bug where opening Clinician Profile or Note Settings and saving too quickly, before your existing values had loaded, could overwrite them with blanks.
  • Added an "include diagnosis" checkbox to Note Settings, off by default, so notes don't name a diagnosis unless you opt in.
  • Added basic, privacy-respecting analytics so we can see which parts of the app are actually getting used during the beta.
  • Feedback sent through the Support button is now saved on our end in addition to being emailed, so nothing gets lost.
  • Added a Support button and this Help & FAQ page.
  • Added "Reflect on This Session": a way to start straight into a Deliberate Practice reflection without writing a note first.
  • Reorganized the sidebar into clearer sections and cleaned up the color scheme.
  • Notes and reflections now use your saved timezone instead of the server's.
  • Added Reflection History, so you can browse, reread, and edit past Deliberate Practice reflections.
  • Rebranded to "Mulch."
  • Smoothed out account creation and beta signup emails.
  • Fixed a bug where dictating quickly could duplicate a message.
  • Added invite-based self-service signup.
  • Note and Growth Reflections conversations are now ephemeral by design. Nothing lingers beyond what you choose to save.
  • Added a clinical decision-making guardrail and a disclosure modal about what the AI is and isn't for.