# Meeting Summary

When a meeting your employee attended ends, it writes a summary and drops it in chat automatically: what got decided, who owns what, and the action items. No need to ask for a recap, it is already waiting when you check in.

After every meeting an AI employee attends, a structured summary is generated automatically: the decisions that were made, the action items that were assigned, and who was in the room. It is ready moments after the call ends.

A transcript tells you everything that was said. The summary tells you what mattered. It is built from the actual transcript, so decisions are stated plainly, owners are attached to action items, and the noise of small talk and tangents is filtered out.

The difference from a note-taking app is that the summary lands on the same private thread you already chat with the employee on, not a separate notes tool. It writes the recap into its own memory too, so asking "what did we decide on the launch date" three weeks later still works, the same way it would with a colleague who was actually in the room.

## What Should a Meeting Summary Actually Contain?

Most meeting notes fail because they transcribe activity instead of extracting outcomes. The automatic summary is organized around the three things people actually look for afterward: what was decided, what was assigned, and who was there.

Each summary keeps the link back to its source. If a decision looks surprising, the full transcript is right there in Drive, so trust never depends on the summary alone.

## When It Fires, and When It Does Not

The summary is not on a timer. It fires the moment the call provider reports the transcript is finished processing after everyone hangs up, and it fires exactly once per meeting, a dedup guard skips any retried webhook so you never get the same recap twice.

A genuinely silent meeting, nobody spoke, produces no summary at all. The employee does not spend a turn writing up silence. If the call drops the employee's connection mid-meeting, there is no automatic reconnect, so the summary covers only what was captured up to that point, a partial recap rather than a failure.

## From Forty Minutes to Two

The summary turns meeting attendance from mandatory to optional for anyone who only needs the outcome. Skip the call, read the summary, and you know what changed and what is expected of you.

Across a week of standups, reviews, and client calls, that compounds into hours returned to every person on the team, while the level of shared awareness goes up rather than down.

## Action Items That Become Action

An action item trapped in a notes doc is a wish. Because the summary is produced by an AI employee inside your workspace, assigned work can move onto the task board on request, ask it to "create tasks from the action items" and they land on the kanban board, with the employee itself picking up anything delegated to it.

It does not push items to the board on its own the moment the summary is written. That step stays a request, so the board only fills with tasks you actually meant to track.

## Meeting Summary vs. the Live Transcript vs. Meeting Notes

Meeting Summary and the live transcript are two different outputs of the same call: the transcript is the verbatim, speaker-tagged record saved to Drive under /documents/meetings/, the summary is the curated read of that record, decisions, action items, attendees, with the small talk stripped out.

Meeting Notes is a separate, on-demand skill for a call the employee was never on, hand it a recording or rough notes after the fact and it produces the same kind of write-up. Because that version is often meant to go out to people beyond you, it stops and waits for your go-ahead before naming anyone's action items or deadlines. The automatic summary skips that gate, it stays inside your own private chat with the employee, nobody else sees it unless you share it.

## How It Works

**From transcript to decisions, action items, and attendees, automatically.**

When a meeting ends, the employee processes the full transcript and produces a structured summary: the decisions made, the action items with owners, and who attended. It lands in Drive next to the transcript moments after the call.

Because the summary is produced by a working agent rather than a note-taking app, it connects to action: items delegated to the employee go onto its board, and the summary becomes part of team knowledge that any teammate or employee can query later.

## Use Cases

### Executives skim a week of meetings in minutes

Five summaries replace five hours of recordings when catching up after travel.

### Teams stop re-litigating decisions

What was decided is written, dated, and linked to the transcript that proves it.

### Project leads track commitments

Action items with owners are extracted automatically, so nothing depends on memory.

### Skipped meetings stop being information gaps

Anyone who misses a call reads the outcome in two minutes.

## Comparison

| Before | After |
|---|---|
| Outcomes depend on someone writing good notes. | Every meeting yields the same structured summary. |
| Action items scatter across notes and chat. | Items are extracted with owners and become tasks. |
| Catching up means watching a recording. | Catching up is a two-minute read. |
| Summaries live in a separate notes app. | Summaries live with your workforce and feed its memory. |

## FAQ

### What does the AI include in a meeting summary?

Decisions made, action items with their owners, and the attendee list, extracted from the full transcript of the meeting.

### How soon after the meeting is the summary ready?

Moments after the meeting ends, once the platform finishes processing the transcript. The summary is generated automatically with no manual step, and only once per meeting.

### What happens if nobody spoke, or the employee got disconnected mid-call?

A silent meeting produces no summary at all, there is nothing to write up. A dropped connection produces a partial summary covering only what was captured before the disconnect, there is no automatic reconnect.

### Can action items from the summary become tasks?

Yes, on request. Ask the employee to create tasks from the action items and they land on the kanban board; it does not file them there automatically the moment the summary is written.

### Where are meeting summaries stored?

The recap is written into the employee's own memory on your private chat thread, so it can answer questions about the meeting later. The full transcript it was built from lives separately in the employee's Drive, under /documents/meetings/.

### How is this different from asking for meeting notes on a call the employee did not attend?

Meeting Summary only covers calls the employee actually joined, and it is automatic and private to your own chat. The separate Meeting Notes skill can turn a recording or rough notes from any call into the same kind of write-up, but because that version is usually meant to circulate, it holds for your sign-off before it names anyone's action items or deadlines.

## Where Meeting Summary fits

Meeting Summary is part of Things they can do out of the box.

Every AI employee ships with built-in abilities that work out of the box. Search the live web for real-time information, scrape and crawl any website for structured data, and generate images directly in conversation. No plugins to install, no APIs to configure.

- [Things they can do out of the box](/en/features/capabilities): Research, create, and extract without plugins.

## Read the guide

- [Guide: Meeting Summary](/en/guide/capabilities/meeting-attender)

## More in Capabilities

- [Web Search](/en/features/capabilities/web_search): Every AI employee can search the live internet for current information and answer with sources, no setup required. It runs automatically whenever the employee needs something it does not already know, such as a competitor update, a price, or a recent news item. Results are cited titles, snippets, and URLs, synthesized into a plain answer inside the chat.
- [Web Scraping](/en/features/capabilities/web_scraping): Give any employee a URL and they read the full page: article, blog post, documentation, competitor page, pricing table, whatever is public. They return clean text with the ads, navigation, and boilerplate stripped out, ready to summarize, compare, or act on. It is enabled for every employee at hire, costs no credits, and works on JavaScript-heavy pages without any setup on your side.
- [Image Generation](/en/features/capabilities/image_generation): Ask any employee to create an image and it builds a detailed prompt, generates it with an OpenAI image model, and saves the result to Drive with a persistent link. Use it for logos, social graphics, illustrations, diagrams, or landing page visuals, described in plain language. No setup required: every employee can generate images at hire, with a Model, Quality, and Shape default you can adjust per tool.
- [Code Interpreter](/en/features/capabilities/code_interpreter): Code Interpreter is on our roadmap: a sandboxed Python environment your AI employee will use to run scripts, crunch numbers, and transform data files on request. Instead of describing a calculation in words, you'll be able to ask for the actual computation and get back a checked result, not a guess. It is not available yet.
- [Video](/en/features/capabilities/video_generation): Hand your employee a prompt and get back a short, ready-to-post video clip, filed straight into your Drive. Built for social cuts, ad concepts, and quick product demos. Editing your own footage is coming next.
- [B2B Marketplace](/en/features/capabilities/b2b_marketplace): A network of real, vetted businesses living inside Sistava. Ask any AI employee to find a vendor, a partner, or a service provider, and it checks this network first, before it ever touches the open internet. Get listed yourself and the same network works the other way: visitors, customers, and other businesses' AI employees can discover and recommend you.
- [Document Editor](/en/features/capabilities/document_editor): Ask an employee for a spreadsheet, a report, a slide deck, or a data export, and get back a real .xlsx, .docx, .pptx, .csv, or .pdf file, not a wall of text pasted into chat. It can also revise a file you already gave it through the same chat-and-Drive workflow, keeping the work you did not ask to change intact whenever the format supports it. For PowerPoint, it can turn a brief into native slides with layouts, charts, images, shapes, tables, and speaker notes. PDFs can be polished reports or colorful, fully designed pages with professional print typography. Included with every employee on every plan, nothing extra to connect or unlock.
- [Premium Prospect Database](/en/features/capabilities/pdl_prospect_database): Find real people to sell to and reveal their verified work email and phone, pulled from a premium database of over a billion professionals worldwide. Filter by role, seniority, industry, company size, and location to build a targeted list, then have your employee save the best prospects straight into your CRM. A premium add-on on paid plans; on the free plan your employee researches prospects on the open web.
- [Send an Employee to Your Meeting](/en/features/capabilities/meeting_attender): Share a Google Meet, Zoom, or Microsoft Teams link and your employee joins the call as a named participant. It listens, keeps a full speaker-tagged transcript, and speaks up out loud when you address it by name. When the call ends, the transcript lands in Drive and a summary shows up in chat.
- [Get a Live Meeting Transcript](/en/features/capabilities/meeting_live_transcript): Your AI employee joins a Google Meet, Zoom, or Microsoft Teams call and captures a full transcript as people speak, tagged by speaker and timestamped. Ask for it mid-call, ask for it after, or just ask what someone said ten minutes ago. When the meeting ends the transcript is saved to your employee's Drive automatically.
- [Document Text Extraction](/en/features/capabilities/text_extraction): When you attach a document to a chat message or upload it for training, your employee turns it into readable text on its own. PDFs, Word, Excel, and PowerPoint files, OpenDocument files, RTF, and plain text or data files all come through automatically, tables included, with no conversion step for you to run first.
- [Import a Skill from GitHub or a URL](/en/features/capabilities/skill_import_from_repo): Paste a link to a GitHub repository or a URL that hosts an Anthropic-style Skill package, and your employee will import the whole thing directly instead of you rebuilding it by hand in the Create Skill drawer. This is on our roadmap and is not active yet: the option appears in the Skills toolbar and in the Create Skill drawer today, but importing does not run until we ship it.

## Explore

- [Every feature](/en/features)
- [Hire an AI employee](/en/market)
- [Pricing](/en/pricing)