What’s new

The API reaches your clients. Alongside decks, an API key can now read and update the people in your firm's client book. In Settings → Developer, two new permissions decide how far a key goes: read the client book, or add and update people. Clients are shared with the whole firm, so a key created by a guest is refused, the same as that person is in the app.

Keep your client list in step with the CRM you already use. A new bulk endpoint takes a batch of people from any outside system — through Zapier, Make, or a script of your own — and files them into the book. Each person carries the id your system uses, so someone who changes jobs and changes email keeps their Foveate record, their meeting notes and their profile. Send the same list twice and nothing happens the second time; only real changes are written.

It will not quietly merge two people, and it will not delete anyone. When an incoming person matches someone already in your book beyond doubt, the two join up. When the evidence is weaker — two contacts sharing one address, or just the same name — you get both records and a note that they might be the same person, for you to decide. Removing someone in your own system marks the connection and leaves their Foveate record, notes and profile untouched.

Corrections you make by hand stay corrected. If you fix a phone number or a job title in Foveate, a later sync from an outside system leaves your version alone instead of overwriting it on the next run.

Adding the same person twice no longer creates a duplicate. Whether a person arrives from the API, a form, a share link or a CSV, Foveate recognises someone already in the book and fills in only what was missing.

Foveate now has an API, starting with decks. From Settings → Developer you can create an API key, name it, and choose what it may do: read your decks, create and edit them, or generate them with AI. The key acts as you — the decks it makes land in your workspace, and AI generation spends your credits, exactly as if you had done it in the app.

Build a deck from an outline, or from a prompt. Send a list of slides — a cover, a few content slides, some metrics, a closing — and Foveate lays them out with the same templates the deck wizard uses, so the result opens in the editor as a real, editable deck. Or send a brief and let the AI write the outline first. Every response includes links to open and share the new deck.

Copy a key any time, revoke it any time. Every key on the Developer page has a Copy button, so you never have to create a new one just because you lost the old one. Each key shows when it was created and last used, and revoking one stops it immediately without affecting your other keys.

Videos you generate can now be downloaded. Saving a clip used to do nothing useful — the option was missing on most videos, and where it appeared the file either opened in a tab instead of saving or landed under a meaningless name. It now prepares the file and saves it properly, under the name of the asset itself. Images and videos selected on a slide get the same option.

Two more video models. Hailuo 3 Max and Grok Imagine Video 1.5 join the model picker. The picker also now shows every kind of input a model accepts — text, image or video — instead of guessing one, so a model that can take your image no longer looks like it only takes words.

Generated clips stay with the deck you made them in. A video or image generated inside a deck that isn't filed under a project now shows up on that deck's own tab in the Library, rather than being hard to find again.

A result no longer plays over the top of another. Starting a new generation, or opening your history, used to leave the previous clip playing underneath. Whatever you are looking at is the only thing making sound.

A model that can't take your input says so. Picking a combination a model doesn't support used to come back as a content-policy warning with a "Rewrite" button that couldn't help. It now tells you what the model actually accepts.

Anyone who can edit a deck can rename it. Renaming from the header was limited to whoever created the deck; teammates with edit access can do it too.

Pickers open fast, however much you have. Add to Project, Add to Shared, the Library and template pickers, and the page grids in PDF and drawing imports used to build every thumbnail at once before showing you anything. They now fill in as you look, and their previews load as you scroll rather than all at once.

Generate Media opens larger, and now goes fullscreen. Both the deck and workspace versions open about a tenth bigger, and a new control in the panel's header expands it to fill the window — worth it when you are comparing several results side by side. It opens at the normal size next time.

Generated files are named after what you asked for. A clip or image you generate now arrives named after your prompt instead of the model and a timestamp, so it is recognisable in your Library and stays recognisable after you download it.

Prompts can run as long as each model actually allows. Prompt fields now hold as much as the model you picked accepts — several times more than before on the models that permit it — and a counter appears as you approach that model's limit, so a prompt that is too long is something you find out while writing it rather than after submitting it.

Video generated with audio waits for you to press play. A result that has its own soundtrack no longer starts by itself — browsers block audio that starts unprompted, so it now lands paused and plays when you click. Silent clips still preview on their own as before.

Every trait score shows its evidence. Hover any of the eight traits on a client's chart and you'll see the quote behind that score, where the quote came from, and the reasoning. The same receipts are gathered in a summary under the chart, open by default, so you can read the whole basis at once instead of hovering each one.

The confidence number explains itself. What the percentage measures, what would raise it, and the point where a read is as grounded as it is going to get now sit behind an info dot beside the number, rather than as three paragraphs above a chart you haven't seen yet.

Profiles explain every trait, not just the strong ones. A trait that lands near the middle used to pass without comment; it now gets the same explanation as a pronounced one. Longer profiles also keep all their evidence — the list used to be trimmed before the last few traits could cite anything.

Client research finds people behind a login wall. Looking someone up now locates their professional profile first, so their title, company and profile link fill in even when the page itself can't be read.

A profile tells you when it has fallen behind. When notes or engagement have arrived since a profile was generated, it says how much is new and offers to update. Seeing the count costs nothing; only the update itself uses credits.

Decks you generate use your firm's positioning again. Decks built from a brief had quietly stopped picking up your Studio firm profile, and nothing reported it. They use it again.

A spoken take tidies your firm profile instead of piling onto it. Recording a new take now folds what you said into the answers already there — clearing filler, dropping repetition, and preferring your newer statement where the two disagree — rather than appending another block of text. The questions also stay on screen while you talk.

The competitor finder says where it looked. It now names the market it searched, and separates a competitor you described from one you named outright.

Incumbent research cites its sources. Firms found in an RFP carry numbered citations with a matching, clickable source list.

A pursuit stops forgetting what it knew. Adding a drawing or a screenshot to a pursuit used to blank out the client name, due date or location it had already established, because the new file mentioned none of them. Those details stay put.

The document viewer settles down. Switching tabs while a document is open no longer leaves it showing a cancelled state or re-rendering pages you were already looking at.

Send someone in your workspace the link, and they can read the chat. Chats now work the way the rest of Foveate already does — the people you work with can open one without being added to it one at a time. Use the share button at the top of a chat to copy its link, then send that link however you normally would. Whoever opens it sees the whole conversation and everything it produced — findings, go/no-go, plan, proposal — along with the sources it cites.

Your workspace only, and only with the link. A chat stays private to the people you share a workspace with; guests and anyone outside it can't open one at all. Nothing appears in a colleague's list until they open the link you sent them, so a chat is never on show to the whole company by accident.

Read-only, always. Someone reading your chat can't send messages or run steps in it. Your pursuit stays exactly as you left it.

Chats you open collect on your Chats page. Anything you've opened that belongs to a colleague gathers in an "Opened by you" section at the top, showing whose chat each one is.

Filing under a project still works the way it did. A chat filed under a project stays visible to that project's members on the project's own Chats tab, as before.

Your deck's picture updates when the deck does. After a deck's picture is re-made, its card shows the new one right away instead of the old one until you reloaded the page. Recent decks on your home page follow the same rule.

A deck that opens on a video gets a real picture. A deck whose first slide is a video used to come out as a black rectangle. It now shows the video's opening frame.

Re-make a deck's picture whether or not it's shared. The refresh on the Share window's thumbnail now works on private decks too — the picture it makes is your dashboard card, not only the preview a link shows.

If you can open it, you can share it. You can now create a share link for a deck, form, previs, project or walkthrough in your workspace, and send it by email, instead of only the person who made it being able to. Being invited to the parent project by email address counts too. A recipient gets the same view you already have.

Failed generations give your credits back. When an image or video generation fails, the credits it used return to your balance. The failed tile tells you so.

Quick images cost less. Generating an image from the workshop or with the deck assistant now starts at 10 credits instead of 80.

Revising an outline costs less. A chat edit to a deck outline is charged as a revision now, not as a new deck.

The price you see is the price you pay. The picker shows each option's price at your current settings. The estimate beside Send counts every reference image you've attached.

Coverage checks run when you ask. An outline drafted from an RFP no longer checks coverage on its own. Use Check coverage on the outline card when you're ready.

Confirmation when you share by email. Sending from the Share window now confirms the send once it's queued, and notes that the email takes a minute or two to arrive. If the send can't be recorded, the window says so and asks you to try again, instead of looking like it worked.

A history of every email you've shared. Send History now lists each email you've sent for a deck, form, previs, or project: who it went to, its subject, and when. Earlier sends are included. Until now it covered only walkthroughs.

Open any image to study it. Click an image in a chat's side panel and it opens large beside its analysis. Zoom with the slider, your scroll wheel, or a double-click. Drag to look around a detail. Step through every image from the same document with the arrow keys. Download it, or save it to your Library or project.

Filter and sort a chat's side panel. A new menu shows just Documents, Text, Images, Videos, Links, or Outputs, sorted by oldest, newest, or name. Images gathers every picture in the chat in one place. Links lists what your documents and your research turned up. If a document hasn't been scanned yet, the panel offers to scan it.

Drawings in your RFPs, ready to study. A PDF in a chat now has a Drawings tab. It finds the plans, sections, elevations, and diagrams drawn as linework, which the Images tab can't pick out. Each becomes its own picture with its labels. Open one full size, save it, or analyze it like any image. SVG and Illustrator uploads work the same way.

Send or paste a picture to have it read. Paste a screenshot straight into the message box, or attach a drawing, and send it. What you type becomes a question about it. Send it on its own for the full analysis. If a file is still uploading, the chat asks you to wait rather than sending without it.

Ask about an image, or read it again. Type a question in the viewer, such as "what does the red boundary cover?". The answer appears beside the image and in the chat. The viewer lists every read of that image and what was asked.

Reads that use your RFP. An image is read against the documents in the chat and the work your pursuit has already done. A site plan is tied to the requirements it relates to, and answers cite the passages they rely on.

A quick, relevant read. Analysis gives a short read rather than a long report, so it comes back faster. It says what the image is, and the three to five things it means for the work in this chat. Each point says whether it's visible, inferred, or still needs checking.

Small labels read more reliably. Images pulled from an RFP are often small. They're enlarged before analysis, so tiny building numbers and street names come back right far more often.

Clearer attachments. An attached PDF shows its first page. Every document shows its name and whether it's still uploading. Once you analyze an image from a PDF, the PDF leaves the message box — it's already in the side panel.

Slimmer scrollbars. The thin scrollbars in chats, side panels, and menus no longer show arrow buttons or widen in Chrome and Edge.