Releases
v1.11.0
-
v1.11.0
Faster captures you can watch
- A page is captured at desktop, tablet and phone at once, so it takes about as long as its slowest size instead of all three added up
- Starting a review on the site shows each size as it lands, then where the review is. Close the tab and it still lands in Your reviews
- A wrong address or too few credits shows under the field, with what you typed and picked still there
- A review you start on the site walks you through it: mark what matters, ask for changes, then open it in Claude, ChatGPT or Cursor with the prompt filled in
- The review says which agent has it as soon as one opens the link, with no reload
- Bars fixed to the bottom of the screen show once at the end of a full-page capture instead of over the top of the page
-
v1.10.0
Start a review without an agent
- Start a review on the site: paste a page link, or add screenshots, a PDF or an email. No account, no agent needed to start
- Paste the review link to your agent and it picks the review up as its own, marks and all
- The review shows what to paste, and says so once your agent has it
- A review link pasted into Slack, iMessage or a post shows the review’s title, its open marks and the top of the page
- Guests looking at a review can start one of their own
-
v1.9.0
Long pages stay sharp
- A long page stays sharp at 2× much further down, and loads faster on the review — big shots are WebP now
- Your agent gets a picture of every mark, however far down the page it sits
- Chat bubbles stay out of the shot, like cookie banners, and fewer sites turn the capture away
- Slides from a PDF are sharper and show at their real size
-
v1.8.0
Your agent hears you the moment you decide
- When you approve or ask for changes in the inline review, it tells your agent in the chat, so it starts right away
- Your agent waits for you in one call instead of checking every 30 seconds, and knows the moment you mark, reply or decide
- Your agent can see each mark as you drew it, cropped from the screenshot, before it fixes it
- Mark in full screen inside the chat, and older copies of a review fold away so only the newest stays live
-
v1.7.0
Every mark has a timeline
- Every mark has a timeline: who marked it, what your agent did, what you said back, in order. “Talk only” folds it down to the conversation
- Your agent knows when you’ve spoken last on a mark and is asked to answer, and it can explain a fix in the same step it resolves it
- Reply to your agent from the inline review in your chat, not just on the web
- The Agent label is a round pill now, so it never reads as the In progress status
-
v1.6.0
Your agent answers on marks
- Your agent can answer in a mark’s thread: reply to a question, explain a fix, or ask before it guesses. A reply never changes the mark
- Everything your agent did carries an Agent tag: its notes, the statuses it set, its after images, its replies and its findings. Guests see it too
- The inline review shows each mark’s thread. Replying still happens on the web
- A new comment shows up on other open copies of the review straight away
-
v1.5.4
Your words for starting a review
- Assistants know when to reach for ReviseMy (check, proof, mark up, get feedback, "is this ready") and leave it out of code review
- Add your own words on Your reviews: phrases that should start a review, and phrases that never should. A new chat picks them up
- A check_page prompt reviews one live page from your assistant’s prompt menu
-
v1.5.3
See what a review is doing while it’s made
- While a review is made, the inline board says what it’s capturing and for how long, instead of a blank loading line
- Assistants that ask for progress hear each step as it happens: opening the page, then desktop, mobile and tablet
- If a review can’t be made, the inline board says why instead of loading forever
-
v1.5.2
Mobile captures work again
- Website captures stopped at the phone-sized shot and came back empty. Desktop, mobile and tablet shots all land again
-
v1.5.1
Assistants that sign in stay connected
- Claude, ChatGPT and Grok could sign in and then have every call turned away. They now stay connected after Connect
- A token refresh that gets lost on the way no longer asks you to connect again
- Claude Code can sign in from a different local port each time
- If a sign-in loses its way, Connect says to start again from your assistant instead of looping
- Connect has its own allowance for new try workspaces, so an office on one network isn’t stopped after a few tries
- The Connect page names the assistant by where it sends you, with its logo, and warns when an app only calls itself Claude
- A sign-in link that can’t be used shows how to fix it, not an error code
- An assistant you connected more than once is one row in your connections, and one Disconnect
-
v1.5.0
Captures that match the finished page
- Website captures wait until the page stops moving — fade-ins land, scroll reveals stay open, fonts and images load
- The mobile capture renders as a phone, with touch styles and a phone browser, at 2×; a tablet capture joins desktop and mobile
- Cookie banners are kept out of the shot
- PDF slides keep their colours, and you’re told when a deck runs past five pages
-
v1.4.0
Connect in one click, a calmer review, and dark mode
- Claude and ChatGPT connect by pasting one address and clicking Connect — no account and no token to copy; Cursor and VS Code install in one click, and Grok, Muse and Codex take a try token
- The connect page shows the moment your assistant makes its first call, and lists what’s connected so you can disconnect it
- A new look shared with Koati, our studio’s other product, with dark mode that follows your system
- The review sidebar is three panels — your marks, hints, and the decision — and removing a mark or accepting hints can be undone
- Approve and Changes wait a few seconds so you can call them off; A, C, J and K work from the keyboard
- Decision webhooks refuse private addresses, don’t follow redirects, and pause after five failed deliveries
-
v1.3.0
Plus is back, plus credit packs — billing now runs on Polar
- Plus returns at $9/mo for 100 credits each billing month, sold through Polar as merchant of record
- New one-time credit pack: 50 credits for $5 that never expire, on Try or Plus — spent only after your monthly credits
- create_checkout takes a product (plus or credits_50); get_billing reports monthly and purchased credits separately and offers both when you run out
- Credits are granted by Polar’s payment webhook, once per order — reloading a checkout page can no longer refill credits
- Canceling Plus keeps it through the paid period; purchased pack credits stay after you downgrade
-
v1.2.0
Hardened ingestion and a leaner agent payload
- Screenshot and PDF URLs are fetched under a strict guard: public https only, redirects re-checked at every hop, and loopback, private, and cloud-metadata addresses refused
- get_review responses are ~60% smaller — mark crops ship as geometry the review app composes, so a signed URL no longer rides on every copy of every mark
- resolve_marks now returns a skipped list, so a batch where only some marks landed can no longer read as a complete one
- While paid Plus is paused, the checkout tools are no longer advertised — agents load 11 tool schemas instead of 14
- PDF ingestion tells you when the host’s ImageMagick policy blocks the PDF coder (the Debian/Ubuntu default) instead of failing opaquely
-
v1.1.2
Agent-native feedback loop
- Work packets now include mark comments, suggested copy, question answers, and finding provenance
- Pass ledger on multi-pass reviews plus an “Awaiting your verify” focus with verify-all
- Faster second-opinion and guest triage: accept as severity, accept/dismiss all
- Enriched list_reviews summaries and a token-scoped /reviews page (no account)
-
v1.1.1
Capture scroll and second-opinion marks
- Tall captures scroll on the web review page and in the MCP inline app
- Vision region marks accept width/height aliases and 0–100% units so S# overlays show reliably
- MCP second-opinion list under the capture with stable S# indexing
- Axis-aware wheel routing so zoomed captures do not block page scroll
-
v1.1.0
Yellow mark and framed marketing
- New yellow app mark across logo wordmark, favicons, and Open Graph card
- Framed rails chrome shared by homepage and guide / use-case / legal pages
- Shared site footer with Testament Made copyright
- MCP inline review closer to web: legend, previous pass, agent notes, before/after, decision callouts
- O’Saasy license for the open-source product
-
v1.0.0
Human-in-the-loop design checkup
- MCP design checkup loop with create_review, get_review, and next_action
- Owner marks, guest suggestions, and board lifecycle open → verified
- Second opinion checklist plus optional BYOK vision hints
- Connectors for ChatGPT, Claude, Copilot, Cursor, and Grok
- Discovery pages for review types, audiences, and alternatives