<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:wfw="http://wellformedweb.org/CommentAPI/"
	xmlns:dc="http://purl.org/dc/elements/1.1/"
	xmlns:atom="http://www.w3.org/2005/Atom"
	xmlns:sy="http://purl.org/rss/1.0/modules/syndication/"
	xmlns:slash="http://purl.org/rss/1.0/modules/slash/"
	>

<channel>
	<title>firefliesai &#8211; iAIFeed</title>
	<atom:link href="https://www.iaifeed.com/tag/firefliesai/feed" rel="self" type="application/rss+xml" />
	<link>https://www.iaifeed.com</link>
	<description>iAIFeed</description>
	<lastBuildDate>Mon, 16 Nov 2026 12:45:35 +0000</lastBuildDate>
	<language>en-US</language>
	<sy:updatePeriod>
	hourly	</sy:updatePeriod>
	<sy:updateFrequency>
	1	</sy:updateFrequency>
	<generator>https://wordpress.org/?v=7.1.5</generator>

<image>
	<url>https://www.iaifeed.com/wp-content/uploads/2026/07/cropped-iaifeed1-80x80.png</url>
	<title>firefliesai &#8211; iAIFeed</title>
	<link>https://www.iaifeed.com</link>
	<width>32</width>
	<height>32</height>
</image> 
	<item>
		<title>How to Automate Fireflies Transcripts with the GraphQL API</title>
		<link>https://www.iaifeed.com/how-to-automate-fireflies-transcripts-with-the-api</link>
					<comments>https://www.iaifeed.com/how-to-automate-fireflies-transcripts-with-the-api#respond</comments>
		
		<dc:creator><![CDATA[iamltlb]]></dc:creator>
		<pubDate>Mon, 16 Nov 2026 12:45:35 +0000</pubDate>
				<category><![CDATA[Blog]]></category>
		<category><![CDATA[firefliesai]]></category>
		<guid isPermaLink="false">https://www.iaifeed.com/how-to-automate-fireflies-transcripts-with-the-api</guid>

					<description><![CDATA[Pull transcripts by ID, generate summaries in the API, and feed meeting data into your CRM with a small scheduled job.]]></description>
										<content:encoded><![CDATA[<p>The <a href="https://www.iaifeed.com/ai-tool/firefliesai">Fireflies</a> API is GraphQL at <code>https://api.fireflies.ai/graphql</code>. You authenticate with a 32-character API key from Settings, and every query costs credits against your plan, so a scheduled job needs some care about volume.</p>
<p>This is for teams whose meeting data needs to live somewhere else — a CRM record, a support ticket, a weekly digest — not just in the Fireflies app.</p>
<h2 id="how-do-you-authenticate-and-test-the-connection">How do you authenticate and test the connection?</h2>
<p>Generate the key under <strong>Settings → Developer Settings → API Key</strong>. Store it as a bearer token in your environment.</p>
<p>Start with a small query in the API playground:</p>
<pre><code class="language-graphql">query { transcripts(limit: 3) { id title date duration } }
</code></pre>
<p>If you get an error about rate limits or permissions, check that the key belongs to a user on a plan with API access. Free plans have narrower limits and slower response windows, and the 404-vs-403 distinction is not always clear in the error message.</p>
<p>Rate limits are documented per plan and applied per minute. For any job that touches more than a handful of meetings, add a 1-second sleep between requests and handle 429 by backing off, not retrying immediately.</p>
<h2 id="how-do-you-pull-a-transcript-with-speakers-and-timestamps">How do you pull a transcript with speakers and timestamps?</h2>
<p>The <code>transcripts</code> query supports a <code>transcript</code> subfield returning sentences. Request more than <code>id</code> and <code>title</code> — the sentence-level data is what makes the transcript useful:</p>
<pre><code class="language-graphql">query($id: String!) {
  transcript(id: $id) {
    title date duration
    participants
    sentences { speaker_name text start_time end_time }
  }
}
</code></pre>
<p>Request only the fields you need. GraphQL lets you ask for everything, and asking for everything noticeably slows large responses.</p>
<p>For enumerating recent meetings, use the <code>fromDate</code> and <code>toDate</code> arguments on <code>transcripts</code> with ISO timestamps. Paginate with <code>limit</code> at 50 and <code>skip</code>, and stop when a page returns fewer rows than the limit — do not assume a total count field exists on all plans.</p>
<h2 id="how-do-you-generate-a-summary-through-the-api">How do you generate a summary through the API?</h2>
<p>Fireflies has a summary generation mutation. It returns a structure rather than one string, typically covering an overview, action items, and per-topic notes.</p>
<p>Call it on transcripts that lack a summary rather than regenerating everything — repeat generation spends credits and can produce different text for the same meeting, which is confusing when someone compares two versions of a client call.</p>
<p>If you need a custom summary format, generate it yourself: pull the sentences, concatenate with speaker labels, and send to a model you control. That gives you a stable structure and a cost you can predict. The trade-off is that you now own the summarisation quality.</p>
<h2 id="how-do-you-sync-meetings-into-a-crm">How do you sync meetings into a CRM?</h2>
<p>The pattern that works:</p>
<ol>
<li>Schedule a daily job that lists transcripts from the last 48 hours.</li>
<li>Filter to meetings whose participants include an email on your customer domain.</li>
<li>Match the external participant&#8217;s email to a CRM contact.</li>
<li>Write the summary and a link to the Fireflies recording onto a note or activity record.</li>
<li>Log the transcript ID in your own store so the job is idempotent and does not write duplicates.</li>
</ol>
<p>Point 5 is not optional. Without a dedupe table, a re-run after a partial failure writes the same note twice and the CRM record looks careless to whoever reads it.</p>
<p>Keep summaries out of CRM fields that sync to email tools. Nobody wants an auto-generated call summary landing in a nurture sequence.</p>
<h2 id="what-are-the-real-constraints">What are the real constraints?</h2>
<p>Credits. Transcription and storage are metered, and API-generated summaries consume them too. A 500-meeting-per-month team on a mid-tier plan will hit limits faster than expected if the job regenerates summaries on every sync.</p>
<p>Speaker attribution remains imperfect. <code>speaker_name</code> comes from the join metadata, so a phone-only attendee often shows as an email address or a generic label.</p>
<p>And recordings expire depending on plan and settings. If your company has a retention policy that deletes transcripts after 90 days, your job must copy anything it wants to keep. Do not treat Fireflies as the archive.</p>
<h2 id="quick-summary">Quick Summary</h2>
<ul>
<li>Fireflies exposes a GraphQL API at <code>api.fireflies.ai/graphql</code>, authenticated by a 32-character key.</li>
<li>Request sentence-level data with speaker labels; it is the part that makes transcripts useful.</li>
<li>Paginate with limit and skip, and back off on 429 rather than retrying hard.</li>
<li>Make CRM sync idempotent with a local dedupe table keyed by transcript ID.</li>
<li>Plan for retention: recordings expire, so copy what you need to keep.</li>
</ul>
]]></content:encoded>
					
					<wfw:commentRss>https://www.iaifeed.com/how-to-automate-fireflies-transcripts-with-the-api/feed</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
			</item>
		<item>
		<title>How to Get Fireflies to Join and Summarize Your Meetings</title>
		<link>https://www.iaifeed.com/how-to-get-fireflies-to-summarize-your-meetings</link>
					<comments>https://www.iaifeed.com/how-to-get-fireflies-to-summarize-your-meetings#respond</comments>
		
		<dc:creator><![CDATA[iamltlb]]></dc:creator>
		<pubDate>Mon, 16 Nov 2026 12:45:14 +0000</pubDate>
				<category><![CDATA[Blog]]></category>
		<category><![CDATA[firefliesai]]></category>
		<guid isPermaLink="false">https://www.iaifeed.com/how-to-get-fireflies-to-summarize-your-meetings</guid>

					<description><![CDATA[Connect a calendar, set the recording rules, and tune the summary format so Fireflies output is usable the same day.]]></description>
										<content:encoded><![CDATA[<p><a href="https://www.iaifeed.com/ai-tool/firefliesai">Fireflies</a> is a meeting notetaker that joins your calls, transcribes them, and writes a summary with action items. You connect a calendar, it joins meetings automatically, and you read the transcript afterwards.</p>
<p>Setup takes ten minutes. Getting output you actually use takes a bit more, because the default summary is written for scanning, not for follow-up.</p>
<h2 id="how-do-fireflies-and-your-calendar-connect">How do Fireflies and your calendar connect?</h2>
<p>Sign in with Google or Microsoft, authorise calendar read access, and Fireflies watches for events with a conferencing link. Zoom, Google Meet, and Teams links all trigger it.</p>
<p>The free plan covers a limited number of transcription credits per month, which for one person is roughly a handful of hour-long calls. Paid tiers raise storage from 800 minutes to thousands and add team features like shared search.</p>
<p>Two behaviours to set on day one: which calendars it watches, and whether it joins by default. If you leave the default on across a shared team calendar, it will join calls where nobody expected a bot in the room.</p>
<h2 id="how-do-you-control-which-meetings-get-recorded">How do you control which meetings get recorded?</h2>
<p>Use the dashboard&#8217;s calendar rules. You can scope by calendar, exclude events with a keyword in the title, and require an invitee from a specific domain.</p>
<p>A workable policy for a small team:</p>
<ul>
<li>Record internal standups and client calls.</li>
<li>Exclude anything with &#8220;1:1&#8221; or &#8220;HR&#8221; in the title.</li>
<li>Exclude events where the organiser is outside your domain, then add the bot manually when needed.</li>
</ul>
<p>That last rule saves you the awkward moment where a prospect notices a recording notice. Not every company is fine with it, and consent requirements vary by region — two-party consent states in the US require telling participants.</p>
<h2 id="what-does-the-default-summary-contain">What does the default summary contain?</h2>
<p>The template covers an overview, key topics, and a bulleted action items list with owners when names are clear enough for the model to attribute them.</p>
<p>Attribution is the weak link. If three people say &#8220;I&#8217;ll take care of that,&#8221; the summary picks one or writes &#8220;the team.&#8221; You can improve this by using the transcript view and editing, but the automatic version is only reliable with two or three speakers who address each other by name.</p>
<p>For calls with heavy crosstalk, the transcript is worth more than the summary. Fireflies timestamps each line and labels the speaker, so you can search for a phrase and jump to the audio.</p>
<h2 id="how-do-you-customise-the-summary-format">How do you customise the summary format?</h2>
<p>In settings, there is a summary template you can rewrite. Three changes that make output far more useful:</p>
<ul>
<li>Replace the &#8220;topics&#8221; section with &#8220;decisions made&#8221; — topics are easy to generate and rarely what you need later.</li>
<li>Force the action items list to include a due date field, even if the model writes &#8220;unassigned.&#8221; Gaps are visible that way.</li>
<li>Ask for a one-sentence &#8220;what changed&#8221; line at the top, for anyone catching up.</li>
</ul>
<p>After editing, run it on an old recording and compare. The difference between a generic summary and one with decisions plus owners is the difference between a document people read and one they ignore.</p>
<h2 id="how-do-you-push-summaries-where-people-will-see-them">How do you push summaries where people will see them?</h2>
<p>Fireflies integrates with Slack, Notion, HubSpot, and via Zapier or its API for anything else. The useful pattern is narrow: post only to the channel that owns the account, and only when the meeting title contains a client name.</p>
<p>A blanket integration that posts every summary to one channel produces noise. Turn on selective sharing, or send summaries to email and let people opt in.</p>
<h2 id="what-are-the-honest-downsides">What are the honest downsides?</h2>
<p>Accuracy on accented English and on technical jargon drops noticeably. Add your product&#8217;s terms to the vocabulary list in settings if it offers one; unrecognised names appear as plausible but wrong words throughout the transcript.</p>
<p>It also cannot read slides. If a decision was made in a shared screen, the transcript may miss the context entirely. For those calls, keep the notes.</p>
<p>And the bot joining is visible. Some prospects ask about it. Decide your answer in advance.</p>
<h2 id="quick-summary">Quick Summary</h2>
<ul>
<li>Fireflies joins calendar meetings, transcribes them, and writes summaries with action items.</li>
<li>Set calendar rules first so the bot does not join sensitive calls by default.</li>
<li>Default action-item attribution is unreliable with more than three speakers; the transcript is more trustworthy.</li>
<li>Rewrite the summary template around decisions and owners, not topics.</li>
<li>Two-party consent rules mean you must tell participants you are recording in some regions.</li>
</ul>
]]></content:encoded>
					
					<wfw:commentRss>https://www.iaifeed.com/how-to-get-fireflies-to-summarize-your-meetings/feed</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
			</item>
		<item>
		<title>How to Search Fireflies Transcripts to Find Decisions</title>
		<link>https://www.iaifeed.com/how-to-search-fireflies-transcripts-to-find-decisions</link>
					<comments>https://www.iaifeed.com/how-to-search-fireflies-transcripts-to-find-decisions#respond</comments>
		
		<dc:creator><![CDATA[iamltlb]]></dc:creator>
		<pubDate>Thu, 12 Nov 2026 12:46:16 +0000</pubDate>
				<category><![CDATA[Blog]]></category>
		<category><![CDATA[firefliesai]]></category>
		<guid isPermaLink="false">https://www.iaifeed.com/how-to-search-fireflies-transcripts-to-find-decisions</guid>

					<description><![CDATA[A year of Fireflies recordings is useless if nobody can find the decision. Keyword habits, AskFred prompts, CRM sync and retention planning.]]></description>
										<content:encoded><![CDATA[<p><a href="https://www.iaifeed.com/ai-tool/firefliesai">Fireflies</a> accumulates transcripts faster than anyone reads them. Six months in, a team of ten has hundreds of hours of searchable meetings and no idea how to query them. The fix is three habits: keyword queries phrased as decisions, AskFred prompts scoped to a date range, and a weekly export of durable decisions.</p>
<p>This guide is about making the archive earn its storage cost. If you have not set up recording yet, start with the basic setup guide first.</p>
<h2 id="why-is-keyword-search-usually-disappointing">Why is keyword search usually disappointing?</h2>
<p>Because transcribers write what people said, and people say &#8220;we&#8217;ll go with the second option&#8221; rather than &#8220;we decided to use Postgres.&#8221; Searching &#8220;Postgres&#8221; finds the slide discussion, not the decision.</p>
<p>Search better by querying for verbal signatures of commitment:</p>
<ul>
<li>&#8220;let&#8217;s go with&#8221;</li>
<li>&#8220;final answer&#8221;</li>
<li>&#8220;ship it&#8221;</li>
<li>&#8220;we&#8217;ll do&#8221;</li>
<li>&#8220;I&#8217;ll own that&#8221;</li>
</ul>
<p>Combine one commitment phrase with a project name. Searching &#8220;billing migration&#8221; plus &#8220;let&#8217;s go with&#8221; finds the moment someone chose, not every mention of the word billing.</p>
<h2 id="how-does-askfred-answer-questions-across-meetings">How does AskFred answer questions across meetings?</h2>
<p>AskFred is Fireflies&#8217; conversational layer over your transcripts. You ask a question and it answers with references to specific meetings.</p>
<p>Prompts that return useful answers name a time window and an output shape:</p>
<ul>
<li>&#8220;What did we decide about the pricing page between May and August 2026?&#8221;</li>
<li>&#8220;List every action item assigned to me in the last 30 days that was not marked done.&#8221;</li>
<li>&#8220;Which customers raised objections about onboarding time? Quote the objection.&#8221;</li>
</ul>
<p>Prompts that fail: &#8220;summarise our meetings.&#8221; Too broad, and the answer becomes a generic paragraph that could describe any company.</p>
<p>One caveat: AskFred is confident. It will produce a plausible answer from two loosely related meetings. Always click through to the cited meeting before you act on it.</p>
<h2 id="how-do-you-get-decisions-out-of-the-archive-permanently">How do you get decisions out of the archive permanently?</h2>
<p>Search is reactive. Decisions need to be proactive, or they get re-litigated every quarter.</p>
<p>A lightweight ritual that works:</p>
<ol>
<li>Every Friday, search the week&#8217;s meetings for the commitment phrases above.</li>
<li>Copy each confirmed decision into a decision log (a doc, a Notion database, anything durable).</li>
<li>Include the meeting date and a link to the Fireflies recording.</li>
<li>Note who owned it.</li>
</ol>
<p>Twenty minutes a week. Twelve months later you have a decision trail that survives people leaving, and the recordings become evidence rather than the record itself.</p>
<h2 id="does-the-crm-sync-help-sales-teams">Does the CRM sync help sales teams?</h2>
<p>Yes, when it is configured narrowly. Fireflies can push call summaries to Salesforce or HubSpot records, giving reps the transcript on the deal instead of in a separate tool.</p>
<p>Configure it per pipeline, not globally. A rep who sees every internal recording attached to a deal record will start distrusting the integration, and cleanup takes longer than setup.</p>
<p>What it does well: attaching external call summaries and next steps to the deal timeline. What it does badly: extracting structured fields for reporting. Do not expect it to fill in a MEDDIC scorecard reliably.</p>
<h2 id="what-are-the-storage-and-retention-tradeoffs">What are the storage and retention tradeoffs?</h2>
<p>Free tiers cap storage minutes; paid plans raise the cap and retention window. If you record everything, you will hit the cap within a couple of months on a busy team.</p>
<p>The cost-aware setup: record external calls always, internal meetings only when they produce decisions, and exclude recurring standups. That typically cuts archive volume by 40-60% while keeping every recording anyone would search for.</p>
<h2 id="where-this-approach-falls-apart">Where this approach falls apart</h2>
<p>If your team never writes anything down, nobody will run the weekly ritual, and the archive stays dead weight. That is a process problem the tool cannot solve.</p>
<p>Also, if you change meeting tools or lose calendar access mid-year, older recordings stay searchable but lose attendee context, which makes AskFred answers less reliable.</p>
<h2 id="quick-summary">Quick Summary</h2>
<ul>
<li>Search transcripts for commitment phrases like &#8220;let&#8217;s go with&#8221; combined with a project name.</li>
<li>Scope AskFred prompts with a date range and an output shape, and always open the cited meeting.</li>
<li>Export decisions weekly to a durable log with date, owner and recording link.</li>
<li>Sync to a CRM per pipeline only; do not expect reliable structured field extraction.</li>
<li>Record external calls and decision meetings, exclude standups, and you cut storage use by 40-60%.</li>
</ul>
]]></content:encoded>
					
					<wfw:commentRss>https://www.iaifeed.com/how-to-search-fireflies-transcripts-to-find-decisions/feed</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
			</item>
		<item>
		<title>How to Auto-Record and Summarize Meetings in Fireflies</title>
		<link>https://www.iaifeed.com/how-to-auto-record-and-summarize-meetings-in-fireflies</link>
					<comments>https://www.iaifeed.com/how-to-auto-record-and-summarize-meetings-in-fireflies#respond</comments>
		
		<dc:creator><![CDATA[iamltlb]]></dc:creator>
		<pubDate>Thu, 12 Nov 2026 12:45:51 +0000</pubDate>
				<category><![CDATA[Blog]]></category>
		<category><![CDATA[firefliesai]]></category>
		<guid isPermaLink="false">https://www.iaifeed.com/how-to-auto-record-and-summarize-meetings-in-fireflies</guid>

					<description><![CDATA[Fireflies joins your calendar calls, records, transcribes in 30+ languages and emails a summary. Setup, bot defaults, storage limits, and consent rules.]]></description>
										<content:encoded><![CDATA[<p><a href="https://www.iaifeed.com/ai-tool/firefliesai">Fireflies</a> joins your Zoom, Google Meet, and Teams calls automatically, transcribes them, and emails a summary with action items when the call ends. Connect one calendar and one conferencing account, and the first recording happens on your next meeting.</p>
<p>The valuable part is not the transcript. It is having searchable minutes for every call without anyone taking notes. The risky part is that it records by default, which is a consent problem in more places than people expect.</p>
<h2 id="what-is-fireflies-and-how-does-it-connect">What is Fireflies and how does it connect?</h2>
<p>Fireflies is a meeting assistant. Its bot joins as a participant (visible in the attendee list), records audio, transcribes speech, and runs language-model summarisation on the transcript.</p>
<p>What you connect:</p>
<ul>
<li>A calendar (Google or Outlook) to know which meetings exist.</li>
<li>A conferencing account (Zoom, Google Meet, Microsoft Teams, Webex) to allow the bot to join.</li>
<li>Optionally a CRM (Salesforce, HubSpot) to push summaries to deal records.</li>
</ul>
<p>Free plan covers a limited amount of transcription storage per user, with paid tiers raising the minutes cap and adding CRM integrations, team analytics, and longer retention.</p>
<h2 id="how-do-you-set-it-up-without-recording-the-wrong-meetings">How do you set it up without recording the wrong meetings?</h2>
<ol>
<li>Sign in and connect Google Calendar or Outlook. Grant read access to event details.</li>
<li>Connect your conferencing tool. Zoom needs the installed-app consent, not just OAuth.</li>
<li>Open Settings, then Recording, and set the default to &#8220;record only meetings with external attendees&#8221; if you run internal standups you never want transcribed.</li>
<li>Add your internal domains to the exclusion list so 1:1s with colleagues are skipped by default.</li>
<li>Set the summary template and turn on email delivery.</li>
<li>Run one test meeting with a colleague before rolling out to a team.</li>
</ol>
<p>Step three is the one people skip. Then their daily standup ends up in a shared team folder with everyone&#8217;s task lists.</p>
<h2 id="what-does-the-fireflies-summary-contain">What does the Fireflies summary contain?</h2>
<p>After a call ends, processing takes a few minutes. You get:</p>
<ul>
<li>An overview paragraph of what the meeting covered.</li>
<li>Bulleted action items with the speaker attributed.</li>
<li>Chapters with timestamps so you can jump to a topic.</li>
<li>The full transcript, searchable across all meetings by keyword.</li>
<li>A shareable link or a PDF export.</li>
</ul>
<p>Accuracy is good on clean audio and mediocre on crosstalk. In a five-person call with people talking over each other, expect some action items attributed to the wrong person. Skim the action list before forwarding it; one wrong owner undermines the whole summary.</p>
<h2 id="how-good-is-the-transcription-in-non-english-calls">How good is the transcription in non-English calls?</h2>
<p>Fireflies supports transcribing in a long list of languages, and summaries can be produced in a language different from the spoken one. That combination is the real win for distributed teams: record a Spanish call, get English minutes.</p>
<p>Quality drops when languages mix inside one call. Code-switching between English and another language produces garbled segments, and speaker labels get scrambled. For mixed-language meetings, keep the summary language English and review the transcript manually rather than trusting the auto-summary.</p>
<h2 id="what-are-the-free-plan-limits">What are the free plan limits?</h2>
<p>The free tier gives a limited pool of transcription storage minutes per seat and keeps summaries for a set retention window. Paid plans are per seat per month and raise the storage, add CRM sync, and extend retention.</p>
<p>Practical implication: on free, you cannot keep a year of calls. Export the meetings that matter as PDFs and accept that older transcripts expire.</p>
<h2 id="consent-and-where-fireflies-does-not-fit">Consent and where Fireflies does not fit</h2>
<p>Recording laws vary. Some jurisdictions require all-party consent, and the bot announcing itself is not always sufficient. Add a spoken notice at the start of external calls, or set the bot to only join on invitation.</p>
<p>Skip Fireflies for:</p>
<ul>
<li>confidential HR, legal, or medical conversations;</li>
<li>calls with prospects who have not agreed to recording;</li>
<li>rooms where a visible bot is unwelcome, like some client pitches.</li>
</ul>
<p>For those, take manual notes. A searchable archive is not worth a trust problem.</p>
<h2 id="quick-summary">Quick Summary</h2>
<ul>
<li>Fireflies joins calendar meetings, records, transcribes and emails summaries with action items.</li>
<li>Set recording defaults and domain exclusions before rolling out, or internal standups get captured.</li>
<li>Summaries include overview, attributed action items, timestamped chapters and a searchable transcript.</li>
<li>Translate-while-summarising works well; mixed-language calls produce garbled speaker labels.</li>
<li>Free tier has limited storage minutes and retention; recording consent rules differ by jurisdiction.</li>
</ul>
]]></content:encoded>
					
					<wfw:commentRss>https://www.iaifeed.com/how-to-auto-record-and-summarize-meetings-in-fireflies/feed</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
			</item>
		<item>
		<title>How to Track Competitor Mentions Across Sales Calls in Fireflies</title>
		<link>https://www.iaifeed.com/how-to-track-competitor-mentions-across-sales-calls-in-fireflies</link>
					<comments>https://www.iaifeed.com/how-to-track-competitor-mentions-across-sales-calls-in-fireflies#respond</comments>
		
		<dc:creator><![CDATA[iamltlb]]></dc:creator>
		<pubDate>Sat, 07 Nov 2026 12:46:34 +0000</pubDate>
				<category><![CDATA[Blog]]></category>
		<category><![CDATA[firefliesai]]></category>
		<guid isPermaLink="false">https://www.iaifeed.com/how-to-track-competitor-mentions-across-sales-calls-in-fireflies</guid>

					<description><![CDATA[A topic tracker built well turns scattered call recordings into a competitor map. Exact setup, keyword hygiene, and the reports worth building each month.]]></description>
										<content:encoded><![CDATA[<p>Fireflies topic trackers count how often a phrase appears across every recorded call and flag the moment it was said. Built properly, five trackers give you a monthly competitor map without anyone listening back to calls.</p>
<p>Built sloppily, they count &#8220;Notion&#8221; every time someone says &#8220;notion of a deadline&#8221; and you get garbage. Keyword hygiene is the whole game with <a href="https://www.iaifeed.com/ai-tool/firefliesai">Fireflies</a>.</p>
<h2 id="what-is-a-topic-tracker-and-where-do-you-find-it">What is a topic tracker and where do you find it?</h2>
<p>A topic tracker is a named group of keywords that Fireflies scans for across your call library. Each hit is stored with the call, speaker, and timestamp. You see totals in the Analytics tab and per-call mentions in the transcript view.</p>
<p>You need a Business plan or above to create trackers. Pro includes summaries and CRM sync but not the tracker analytics, which is a frustrating paywall if trackers are your main reason for buying.</p>
<h2 id="how-do-you-build-a-competitor-tracker-that-works">How do you build a competitor tracker that works?</h2>
<ol>
<li>Start from a list of every competitor mentioned in the last quarter of calls. Pull from CRM closed-lost reasons if you have them; otherwise sample 20 transcripts.</li>
<li>For each competitor, add the exact product name plus one or two common pronunciation variants. &#8220;Snowflake&#8221; and &#8220;Snowflake Data Cloud&#8221; are one tracker; &#8220;Snow&#8221; alone is not.</li>
<li>Exclude generic words. Fireflies matches substrings loosely, so a tracker on &#8220;Linear&#8221; will fire on &#8220;linearly.&#8221; Add the full name and accept some noise rather than tracking a common word.</li>
<li>Group by category, not by individual company. &#8220;Competitor — CRM&#8221; catches six vendors; six separate trackers produce six charts nobody combines.</li>
<li>Set the reporting window to 30 days and review before you present anything.</li>
</ol>
<p>Add a second tracker for objections — pricing, security, integration, timeline. Competitor mentions explain who you lose to; objection tracking explains why.</p>
<h2 id="how-do-you-read-the-numbers-honestly">How do you read the numbers honestly?</h2>
<p>Three traps.</p>
<p><strong>Mentions are not losses.</strong> A competitor mentioned in a discovery call is often the incumbent being replaced. Filter by deal outcome before you claim a competitive trend.</p>
<p><strong>Call volume skews everything.</strong> A month where one enterprise prospect called six times triples your &#8220;competitive pressure&#8221; numbers. Normalize per call, not per month.</p>
<p><strong>Small samples.</strong> Under about 30 calls, mention rates bounce around by 10 points for no reason. Wait for volume before building a narrative.</p>
<table>
<thead>
<tr>
<th>Metric</th>
<th>Useful when</th>
<th>Misleading when</th>
</tr>
</thead>
<tbody>
<tr>
<td>Total mentions</td>
<td>Sizing awareness</td>
<td>Call volume changed</td>
</tr>
<tr>
<td>Mentions per 100 calls</td>
<td>Comparing months</td>
<td>Fewer than 30 calls</td>
</tr>
<tr>
<td>Win rate vs competitor</td>
<td>Deal analysis</td>
<td>Outcomes not tracked</td>
</tr>
<tr>
<td>Objection frequency</td>
<td>Product planning</td>
<td>Reps word it differently</td>
</tr>
</tbody>
</table>
<h2 id="what-reports-are-worth-building-monthly">What reports are worth building monthly?</h2>
<p>Three, and no more.</p>
<p><strong>Competitor mention rate per 100 calls.</strong> One line per competitor, trailing three months. Shows who is showing up more often in buyer conversations.</p>
<p><strong>Objection frequency by category.</strong> Pricing objections rising while security objections fall tells product where to invest in collateral.</p>
<p><strong>Mentions tied to closed-lost deals.</strong> The only report that connects mentions to money. Requires CRM outcome sync, which Fireflies does on Business tier.</p>
<p>Everything else — sentiment averages, talk-time distributions — is available and rarely acted on.</p>
<h2 id="how-accurate-are-keyword-matches-on-messy-transcripts">How accurate are keyword matches on messy transcripts?</h2>
<p>Fireflies transcription runs about 85–93% word accuracy. That generally catches product names but misses them when speakers compress syllables. &#8220;Snowflake&#8221; is reliable. &#8220;Databricks&#8221; occasionally comes out as &#8220;data bricks&#8221; — add both forms as separate keywords in the same tracker.</p>
<p>Non-English calls degrade badly. If your sales calls happen in Spanish or German, test 10 transcripts before trusting the counts.</p>
<p>One more limit: trackers scan from creation forward. They do not retroactively index your existing library, so a new tracker starts at zero and takes 4–6 weeks to produce a comparable sample.</p>
<h2 id="who-should-run-trackers-and-who-should-skip-them">Who should run trackers and who should skip them?</h2>
<p><strong>Worth the setup:</strong> sales teams with 50+ recorded calls a month, product marketers who need competitive evidence, and anyone preparing a win/loss review with real numbers.</p>
<p><strong>Skip:</strong> small teams with three calls a week (you will know your competitors better than the tracker does), and anyone on Pro who would have to upgrade just for trackers — use transcript search instead, which is slower but free.</p>
<p>Budget note: Business runs about $19/seat/month. A five-person team is roughly $1,140 a year for analytics that need a monthly human review to be worth anything.</p>
<h2 id="quick-summary">Quick Summary</h2>
<ul>
<li>Topic trackers in Fireflies count keyword mentions across all recorded calls with timestamps.</li>
<li>Trackers need Business tier (~$19/seat/month); Pro has summaries but not tracker analytics.</li>
<li>Group by category, use full product names, and avoid generic words that match loosely.</li>
<li>Normalize mentions per 100 calls; raw totals move with call volume.</li>
<li>Trackers do not backfill — a new tracker needs 4–6 weeks before comparisons are fair.</li>
</ul>
]]></content:encoded>
					
					<wfw:commentRss>https://www.iaifeed.com/how-to-track-competitor-mentions-across-sales-calls-in-fireflies/feed</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
			</item>
		<item>
		<title>How to Set Up Fireflies.ai for a Sales Team</title>
		<link>https://www.iaifeed.com/how-to-set-up-fireflies-ai-for-a-sales-team</link>
					<comments>https://www.iaifeed.com/how-to-set-up-fireflies-ai-for-a-sales-team#respond</comments>
		
		<dc:creator><![CDATA[iamltlb]]></dc:creator>
		<pubDate>Sat, 07 Nov 2026 12:46:10 +0000</pubDate>
				<category><![CDATA[Blog]]></category>
		<category><![CDATA[firefliesai]]></category>
		<guid isPermaLink="false">https://www.iaifeed.com/how-to-set-up-fireflies-ai-for-a-sales-team</guid>

					<description><![CDATA[Fireflies scores calls, writes CRM notes, and joins meetings automatically. A realistic two-week rollout plan, the per-seat math, and what it gets wrong.]]></description>
										<content:encoded><![CDATA[<p>Setting up Fireflies for a sales team takes about a week: connect the calendar, set the auto-join rule, connect the CRM, then build one shared topic tracker before you turn the team loose. Teams that skip the tracker step end up with hundreds of transcripts nobody reads.</p>
<p>The rollout matters more than the settings. <a href="https://www.iaifeed.com/ai-tool/firefliesai">Fireflies</a> will record everything whether or not your process is ready.</p>
<h2 id="what-does-fireflies-do-during-a-sales-call">What does Fireflies do during a sales call?</h2>
<p>It joins the meeting as a bot, records it, transcribes with speaker labels, and then produces four things: a summary, action items, a topic tracker, and a call score based on talk-time ratio and sentiment.</p>
<p>The CRM sync is the feature sales leaders actually buy it for. Notes and action items push to Salesforce or HubSpot fields on the contact or deal record, on the paid tiers.</p>
<p>Automatic join is configurable by calendar rule, so you can exclude internal meetings. Turn that on early — a bot that joins every standup is the fastest way to get the tool banned.</p>
<h2 id="how-do-you-roll-it-out-without-annoying-everyone">How do you roll it out without annoying everyone?</h2>
<p><strong>Day 1 — connect and restrict.</strong> Link Google or Microsoft calendar. Set auto-join to external attendees only. Add a whitelist of domains so customer calls get recorded and internal ones do not.</p>
<p><strong>Day 2 — build one tracker.</strong> Create a topic tracker with 5–8 real topics from your sales calls: pricing objection, competitor mention, implementation timeline, budget approval, procurement. Fireflies tracks mention frequency across all calls from that point.</p>
<p><strong>Day 3 — wire the CRM.</strong> Map the summary field and the next-steps field in Salesforce or HubSpot. Test with one call end to end before enabling for the team.</p>
<p><strong>Day 4–5 — pilot with two reps.</strong> Pick your best and worst listeners. Compare their call scores and read the summaries. If both summaries need heavy editing, your tracker is too narrow.</p>
<p><strong>Week 2 — open to the team</strong> with a 20-minute walkthrough covering the ask-first rule and how to stop the bot.</p>
<p>The ask-first rule is not optional in most jurisdictions. Two-party consent states in the US and GDPR in Europe both require it. Fireflies can play a pre-recorded consent message at the start of the call.</p>
<h2 id="how-much-does-it-cost-per-seat">How much does it cost per seat?</h2>
<ul>
<li><strong>Free</strong> — limited transcription credits, roughly 800 minutes of storage, basic AI summary.</li>
<li><strong>Pro</strong> — around $10/seat/month billed yearly ($18 monthly), unlimited transcription, unlimited storage, AI summaries and action items, CRM integrations on select plans.</li>
<li><strong>Business</strong> — around $19/seat/month, conversation intelligence, topic trackers, team analytics.</li>
<li><strong>Enterprise</strong> — custom, adds SSO, data residency, and retention rules.</li>
</ul>
<p>For a 12-person sales team, Business lands around $230/month. That is roughly the cost of one extra long-distance call, which is the pitch — as long as the reps actually read the summaries.</p>
<h2 id="what-does-the-call-score-actually-measure">What does the call score actually measure?</h2>
<p>Talk-time ratio, longest monologue, sentiment, and question rate. Four metrics, computed automatically.</p>
<p>Useful as a coaching flag, useless as a performance metric. A rep who talks 55% of the time and asks zero questions may still be closing well. Score correlates with listener behavior, not with revenue.</p>
<p>Fireflies will also score calls that are 10 minutes long and 90 minutes long the same way, which distorts averages. Filter by call length before drawing conclusions.</p>
<h2 id="where-does-fireflies-get-things-wrong">Where does Fireflies get things wrong?</h2>
<p>Transcript accuracy lands around 85–93% depending on audio quality. Names are the recurring failure — spelling drifts within a single transcript.</p>
<p>Summaries are structured but shallow. Expect &#8220;Customer raised concerns about implementation timeline&#8221; rather than the specifics of the concern. For deal-critical calls, someone should read the transcript, not the summary.</p>
<p>The CRM sync can create duplicate notes when two bots join the same call, which happens when a customer&#8217;s own recorder is also running. Audit the first two weeks of notes.</p>
<p><strong>Good fit:</strong> sales teams of 5–50 doing 10+ customer calls a day, managers who need call review without sitting in on calls, and anyone tracking objection patterns over time.</p>
<p><strong>Poor fit:</strong> teams of one or two (the per-seat cost outweighs the analytics), regulated industries where cloud recording is barred, and anyone expecting the CRM notes to be copy-ready.</p>
<h2 id="quick-summary">Quick Summary</h2>
<ul>
<li>Fireflies joins calls automatically, transcribes, scores, and pushes notes to CRM.</li>
<li>Restrict auto-join to external attendees on day one — the bot joining every standup kills adoption.</li>
<li>Build 5–8 topic trackers before the team rollout; trackers are the durable value.</li>
<li>Pro is around $10/seat/month yearly; Business around $19/seat/month for conversation intelligence.</li>
<li>Scores measure listening behavior, not revenue — use them for coaching, not ranking.</li>
</ul>
]]></content:encoded>
					
					<wfw:commentRss>https://www.iaifeed.com/how-to-set-up-fireflies-ai-for-a-sales-team/feed</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
			</item>
		<item>
		<title>How to Use Fireflies Conversation Analytics to Coach Reps</title>
		<link>https://www.iaifeed.com/how-to-use-fireflies-analytics-to-coach-reps</link>
					<comments>https://www.iaifeed.com/how-to-use-fireflies-analytics-to-coach-reps#respond</comments>
		
		<dc:creator><![CDATA[iamltlb]]></dc:creator>
		<pubDate>Wed, 28 Oct 2026 12:49:21 +0000</pubDate>
				<category><![CDATA[Blog]]></category>
		<category><![CDATA[firefliesai]]></category>
		<guid isPermaLink="false">https://www.iaifeed.com/how-to-use-fireflies-analytics-to-coach-reps</guid>

					<description><![CDATA[Track talk ratio, objection frequency and competitor mentions across calls, then turn those metrics into a coaching loop that survives more than one quarter.]]></description>
										<content:encoded><![CDATA[<p>Most teams install <a href="https://www.iaifeed.com/ai-tool/firefliesai">Fireflies</a>, get transcripts, and never open the analytics tab. The analytics are the part that changes rep behaviour — a talk-ratio number on a dashboard does more than the 40-page transcript nobody reads.</p>
<p>The catch: conversation metrics are easy to measure and easy to misread. Talk ratio below 50% isn&#8217;t automatically good. Here&#8217;s how the numbers work and which ones deserve a weekly review.</p>
<h2 id="what-does-fireflies-analytics-actually-measure">What does Fireflies analytics actually measure?</h2>
<p>Fireflies computes per-meeting metrics from the transcript and speaker labels. The ones that hold up:</p>
<ul>
<li><strong>Talk ratio</strong> — percentage of speaking time per participant. Derived from transcript timestamps, so it&#8217;s reliable if speaker labels are right.</li>
<li><strong>Sentiment</strong> — positive/neutral/negative per speaker, per sentence. Crude, but trend direction is informative.</li>
<li><strong>Monologue detection</strong> — the longest uninterrupted stretch from one speaker. Anything over 3 minutes in a discovery call is a signal.</li>
<li><strong>Keyword tracking</strong> — custom phrases such as competitor names or &#8220;budget&#8221;, counted across calls.</li>
<li><strong>Question rate</strong> — questions per 10 minutes from each speaker.</li>
</ul>
<p>The ones to be sceptical of: overall sentiment scores (they drift with transcript quality), and anything derived from topic detection without your custom vocabulary configured.</p>
<p>Set up keyword tracking first. It&#8217;s under <strong>Settings → Conversation Intelligence</strong>, where you add a list of phrases. Put in your competitors, and &#8220;pricing&#8221;, &#8220;contract&#8221;, &#8220;security review&#8221;, &#8220;integration&#8221;. Three weeks later you have a real answer to &#8220;how often do we hear about Competitor X&#8221;, which nobody has.</p>
<h2 id="how-should-you-read-talk-ratio">How should you read talk ratio?</h2>
<p>The common advice is &#8220;talk less than 50%&#8221;. It&#8217;s directionally right and too blunt.</p>
<p>Discovery calls: a rep above 60% is pitching instead of asking. That&#8217;s a coaching conversation.</p>
<p>Demo calls: 50-65% is normal. Someone has to drive the screen.</p>
<p>Pricing negotiation: reps typically talk 70%+ and that&#8217;s fine — you&#8217;re stating terms.</p>
<p>So compare within call type, not globally. Fireflies doesn&#8217;t segment by call type automatically, but you can tag meetings (<strong>Meeting → Add to channel</strong>) or filter by meeting title pattern, and read the metric per channel.</p>
<p>The much more useful metric is <strong>longest monologue</strong>. A rep who talks 45% overall but delivers a 6-minute uninterrupted pitch has the same problem as one at 65% overall, and it&#8217;s far easier to point at in a 1:1. &#8220;Here are 40 seconds where you answered a question the buyer hadn&#8217;t asked yet&#8221; lands better than a percentage.</p>
<h2 id="how-do-you-turn-metrics-into-a-coaching-loop">How do you turn metrics into a coaching loop?</h2>
<p>A weekly loop that survives: 20 minutes, one rep, one metric, one clip.</p>
<ol>
<li><strong>Pick a metric for the week</strong> — not all of them. Question rate, or monologue length.</li>
<li><strong>Pull the outlier call.</strong> Sort the rep&#8217;s calls by the metric. Pick the worst one that isn&#8217;t already known-bad.</li>
<li><strong>Send a 60-second clip, not a transcript.</strong> Fireflies lets you share a timestamped link; a shared link to 14:32-15:40 of the actual call outperforms 2,000 words of summary.</li>
<li><strong>Agree one change.</strong> &#8220;Ask about timeline before showing pricing.&#8221; One thing.</li>
<li><strong>Check next week</strong> whether the metric moved.</li>
</ol>
<p>The failure mode is doing this monthly with a spreadsheet of 12 metrics. Reps disengage because it reads as surveillance. One metric, one clip, one change, every week, is a different message.</p>
<h2 id="whats-the-fastest-way-to-compare-competitors">What&#8217;s the fastest way to compare competitors?</h2>
<p>Keyword tracking gives counts. To get context, use the search on the stored transcripts: search a competitor name and you get every mention across the org with a timestamp and a link.</p>
<p>Build a quarterly competitor sheet from it:</p>
<table>
<thead>
<tr>
<th>Competitor</th>
<th>Mentions</th>
<th>Meetings</th>
<th>Common objection</th>
<th>Where we lose</th>
</tr>
</thead>
<tbody>
<tr>
<td>Competitor A</td>
<td>34</td>
<td>22</td>
<td>&#8220;already have a contract&#8221;</td>
<td>Renewal timing</td>
</tr>
<tr>
<td>Competitor B</td>
<td>19</td>
<td>15</td>
<td>&#8220;cheaper for small teams&#8221;</td>
<td>Seat pricing</td>
</tr>
<tr>
<td>Competitor C</td>
<td>8</td>
<td>6</td>
<td>&#8220;no one&#8217;s heard of you&#8221;</td>
<td>Social proof</td>
</tr>
</tbody>
</table>
<p>The &#8220;where we lose&#8221; column can&#8217;t be extracted automatically — it comes from reading the flagged mentions. But filtering to 34 mentions instead of 400 calls is the difference between doing the analysis and not.</p>
<p>Practical warning: keyword matching is literal. &#8220;Competitor B&#8221; won&#8217;t match &#8220;B&#8217;s pricing&#8221; or a mis-transcribed variant. Add 2-3 spelling variants per competitor, and check the tokenisation by searching a phrase you know appears.</p>
<h2 id="what-should-you-not-do-with-these-metrics">What should you not do with these metrics?</h2>
<p><strong>Don&#8217;t rank reps by sentiment.</strong> It measures transcript quality and speaking style more than deal outcomes. A rep with a flat delivery on a happy call scores worse than a warm-sounding rep losing the deal.</p>
<p><strong>Don&#8217;t put talk ratio on a leaderboard.</strong> It gets gamed instantly — reps go quiet, buyers fill the silence with less information, and calls get worse.</p>
<p><strong>Don&#8217;t benchmark against Fireflies&#8217; suggested averages.</strong> They&#8217;re aggregated across all customers and skew toward high-volume inside sales. Your enterprise deals will look wrong against them.</p>
<p><strong>Don&#8217;t review analytics without watching a call.</strong> The number tells you where to look. It never tells you why.</p>
<h2 id="whats-the-actual-adoption-problem">What&#8217;s the actual adoption problem?</h2>
<p>Transcript tools get abandoned when nobody&#8217;s job includes reading them. Two things fix that:</p>
<p>Assign an owner. One person (sales manager or enablement) whose job includes a weekly pass. Without a named owner, analytics rot.</p>
<p>Tie it to something already reviewed. If there&#8217;s a pipeline review on Mondays, add one slide of conversation data to it. Tools survive when they attach to an existing ritual, not when they create a new one.</p>
<p>Also check <strong>Settings → Team → Permissions</strong>. By default, reps can see each other&#8217;s transcripts. Some teams thrive on that; others have a quiet mutiny. Decide deliberately before someone finds out by accident.</p>
<h2 id="quick-summary">Quick Summary</h2>
<ul>
<li>Fireflies analytics track talk ratio, monologue length, question rate, sentiment and custom keywords.</li>
<li>Configure keyword tracking with competitor names first — it answers a question nobody can currently answer.</li>
<li>Read talk ratio within call type; the longest monologue is a better coaching target than the average.</li>
<li>Coach with one metric, one 60-second clip and one change per week.</li>
<li>Don&#8217;t rank reps on sentiment or put talk ratio on a leaderboard — both get gamed.</li>
<li>Analytics get abandoned without a named owner and an existing meeting to attach to.</li>
</ul>
]]></content:encoded>
					
					<wfw:commentRss>https://www.iaifeed.com/how-to-use-fireflies-analytics-to-coach-reps/feed</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
			</item>
		<item>
		<title>How to Set Up Fireflies Meeting Notes for a Sales Team</title>
		<link>https://www.iaifeed.com/how-to-set-up-fireflies-meeting-notes-for-a-sales-team</link>
					<comments>https://www.iaifeed.com/how-to-set-up-fireflies-meeting-notes-for-a-sales-team#respond</comments>
		
		<dc:creator><![CDATA[iamltlb]]></dc:creator>
		<pubDate>Wed, 28 Oct 2026 12:48:53 +0000</pubDate>
				<category><![CDATA[Blog]]></category>
		<category><![CDATA[firefliesai]]></category>
		<guid isPermaLink="false">https://www.iaifeed.com/how-to-set-up-fireflies-meeting-notes-for-a-sales-team</guid>

					<description><![CDATA[Connect Fireflies to your calendar and CRM, tune the AskFred summaries, and push notes into HubSpot or Salesforce — plus what to configure before the first demo call.]]></description>
										<content:encoded><![CDATA[<p><a href="https://www.iaifeed.com/ai-tool/firefliesai">Fireflies</a> is an AI meeting notetaker that joins calls, transcribes them, and writes summaries. It has one feature that matters for sales teams and that most competitors charge more for: writing the meeting notes into HubSpot or Salesforce automatically.</p>
<p>The free plan gives 800 minutes of storage with limited AI summaries. Pro is $10/user/month billed annually for 8,000 minutes. Business, at $19, adds admin controls and a limited-API allowance.</p>
<h2 id="how-do-you-connect-fireflies-to-a-calendar">How do you connect Fireflies to a calendar?</h2>
<p>Sign up at fireflies.ai, then <strong>Settings → Integrations → Calendar</strong>. Connect Google or Microsoft.</p>
<p>Two decisions to make immediately:</p>
<p><strong>Which calendars.</strong> Fireflies auto-joins meetings it finds on your calendar. If your sales team shares a team calendar, every rep&#8217;s bot will join every meeting. Set auto-join to only the rep&#8217;s personal calendar, and configure a keyword rule (see below) so it doesn&#8217;t join internal 1:1s.</p>
<p><strong>Who&#8217;s the notetaker.</strong> Fireflies joins as a participant called &#8220;Fireflies&#8221;. For external demos, some prospects find a bot on the call off-putting. The alternative is the <strong>Fireflies Chrome extension</strong>, which records from your browser without a visible bot — less intrusive, but it depends on your tab staying open, and if Chrome crashes mid-call you lose the recording.</p>
<p>For sales calls with prospects, I&#8217;d use the extension. For internal pipeline reviews, use the bot.</p>
<h2 id="how-do-you-stop-it-joining-the-wrong-meetings">How do you stop it joining the wrong meetings?</h2>
<p>Auto-join rules live under <strong>Settings → Notetaker → Auto-join rules</strong>. Three levers:</p>
<ul>
<li><strong>Only join events with video conferencing links</strong> — kills most noise.</li>
<li><strong>Exclude by keyword in the title</strong> — add &#8220;1:1&#8221;, &#8220;sync&#8221;, &#8220;lunch&#8221;, &#8220;internal&#8221;. Wildcard matching is on the title only.</li>
<li><strong>Include by domain</strong> — for external meetings, only join when a participant&#8217;s email isn&#8217;t on your domain.</li>
</ul>
<p>The third rule does most of the work for a sales team: join external calls, skip internal ones. Set it once and the team stops getting transcripts of their own standups.</p>
<p>There&#8217;s also a per-event override: forward a calendar invite to <code>fred@fireflies.ai</code> to force a join. Useful for the one-off call on someone else&#8217;s calendar.</p>
<h2 id="how-do-you-get-useful-sales-summaries">How do you get useful sales summaries?</h2>
<p>Fireflies&#8217; default summary is a generic bullet list. For sales calls you want a specific structure, and the product supports it two ways.</p>
<p><strong>Custom summary templates</strong> (Business plan and above): define sections like <code>Pain points</code>, <code>Budget discussed</code>, <code>Timeline</code>, <code>Next step</code>, <code>Competitors mentioned</code>. Fireflies fills them from the transcript. This is the single highest-value configuration on the platform for a sales team — a generic summary answers &#8220;what happened&#8221;, a templated one answers &#8220;what do I do next&#8221;.</p>
<p><strong>AskFred</strong> (the chat interface) works on Pro too. Ask &#8220;what did the buyer say about budget?&#8221; across one meeting or all meetings with a contact. Quality depends on transcript quality, which depends on audio — push your team to use headsets; it&#8217;s the difference between 90% and 65% accuracy.</p>
<p>The prompt-based approach has a limit worth internalising: Fireflies doesn&#8217;t know your product. If a prospect says &#8220;this is too expensive compared to X&#8221;, the summary will report it, but it won&#8217;t tell you whether that&#8217;s a real objection or negotiating. Templates give structure; judgement is still yours.</p>
<h2 id="how-do-you-push-notes-to-the-crm">How do you push notes to the CRM?</h2>
<p>This is the reason to pick Fireflies over Otter for a sales team. Connect HubSpot or Salesforce under <strong>Integrations → CRM</strong>, authorise OAuth, then choose what gets written.</p>
<p>For HubSpot: notes attach to the contact and company, with the transcript as a separate engagement. For Salesforce: notes attach to the opportunity or lead depending on matching.</p>
<p>Three things to configure before you turn it on, because retrofitting is painful:</p>
<ol>
<li><strong>Matching rules.</strong> Fireflies matches attendees by email. If your reps use personal email addresses for prospects, matching fails silently and notes vanish into an unattached queue. Verify with one test call.</li>
<li><strong>Field mapping.</strong> Map the summary to a CRM field rather than dumping everything into the activity feed. Activity feeds are searchable in theory and unsearchable in practice.</li>
<li><strong>Team-level vs user-level.</strong> A single admin can connect the CRM org-wide (Business) so notes flow consistently. If each rep connects their own account, expect 40% adoption.</li>
</ol>
<p>The Business tier also adds <strong>Sounds good</strong> — a feature that suggests objection-handling responses during calls by searching your team&#8217;s past transcripts. Gimmicky-sounding, genuinely useful for a new rep who hasn&#8217;t heard the top five objections yet. Not a substitute for training.</p>
<h2 id="what-are-the-actual-plan-limits">What are the actual plan limits?</h2>
<table>
<thead>
<tr>
<th>Plan</th>
<th>Price</th>
<th>Storage</th>
<th>AI summaries</th>
</tr>
</thead>
<tbody>
<tr>
<td>Free</td>
<td>$0</td>
<td>800 min total</td>
<td>Limited</td>
</tr>
<tr>
<td>Pro</td>
<td>$10/user/mo</td>
<td>8,000 min/user</td>
<td>Unlimited</td>
</tr>
<tr>
<td>Business</td>
<td>$19/user/mo</td>
<td>Unlimited</td>
<td>Unlimited + templates</td>
</tr>
</tbody>
</table>
<p>&#8220;800 minutes total&#8221; on free is a trap for evaluation — that&#8217;s about 12 one-hour calls, after which recordings age out. Enough to test, not enough to run a team on.</p>
<p>Business&#8217;s unlimited storage matters more than it sounds. Sales teams generate 20-40 hours of recording per rep per quarter. At 8,000 minutes (133 hours) Pro is fine for a year, but teams that keep recordings indefinitely need Business.</p>
<p>Note that Fireflies prices per seat but transcripts are organisation-wide by default. That&#8217;s good for a team (shared context) and bad for anything confidential — check permissions under <strong>Settings → Team</strong>.</p>
<h2 id="where-it-falls-short">Where it falls short</h2>
<p>Speaker attribution is by voice, same as Otter, and it&#8217;s worse on calls with more than five people. Rename speakers once and Fireflies learns, but a rotating panel of prospects defeats it.</p>
<p>Language coverage is narrower than Otter&#8217;s — around 20 languages for transcription against Otter&#8217;s ~100. If your team sells in three languages, test the quality in each before committing.</p>
<p>And the bot in the call: some enterprise procurement teams block unidentified bots. If your prospects are enterprises with strict vendor review, the browser extension or a manual upload path is what you&#8217;ll actually use.</p>
<h2 id="quick-summary">Quick Summary</h2>
<ul>
<li>Fireflies joins calls from your calendar; Pro is $10/user/month annually, Business $19.</li>
<li>Auto-join rules by external domain stop it recording internal meetings.</li>
<li>Custom summary templates (Business) are the biggest win for sales — generic summaries don&#8217;t drive next steps.</li>
<li>CRM sync to HubSpot/Salesforce is the main reason to pick Fireflies over Otter.</li>
<li>Verify email matching with one test call before relying on CRM sync.</li>
<li>Free plan&#8217;s 800 total minutes is an evaluation allowance, not a working plan.</li>
</ul>
]]></content:encoded>
					
					<wfw:commentRss>https://www.iaifeed.com/how-to-set-up-fireflies-meeting-notes-for-a-sales-team/feed</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
			</item>
	</channel>
</rss>
