When does an AI agent use this pattern?

When the trigger described above matches the situation the agent is handling. The agent queries FusedFrames at runtime, this pattern is returned and the agent follows the recorded reasoning and steps to reach the recorded outcome.

How were the steps captured?

By the desktop app on the machine of someone who actually does this work. It records clicks, keystrokes, copy and paste, drag and drop, selected text and screen regions across Outreach and Salesforce, then groups them into the meaningful steps shown above.

Where does the reasoning come from?

From the operator. When the desktop app sees a decision the action alone cannot explain, it asks why in the moment. The operator's answer is recorded and becomes the reasoning attached to the pattern, so the AI agent gets the thinking and not just the steps.

What if my team handles this differently?

Capture how your team actually does it. The desktop app records what your operator does on your tools and the web app distills that into a pattern shaped by your team. Each team's library reflects their own approach rather than the example shown here.

What happens when a case looks like this pattern but does not quite fit?

The connections shown on this page link to related patterns that may match the case better. The agent can follow those edges to find a closer fit.

How does my AI agent actually call this pattern?

Through the read-only REST API or the npm CLI. Create an API key in the dashboard, choose whether it accesses all libraries or specific ones and have your agent query at runtime. The response is structured JSON ready for tool use.

Is the data shown on this page from a live customer?

No. Example libraries on this site are illustrative. Patterns in your own account are built from your team's captured actions and stay private to your workspace.

How do I build a pattern like this for my team?

Install the desktop app on the machine of the person who already does this work, ask them to handle a real case end to end, then distill the captured action into a pattern in the web app. The pattern you end up with mirrors how your team actually operates.

Booking a demo from a positive email reply

When a prospect replies positively to an Outreach step, the SDR pauses the sequence first and then offers three concrete slots from the AE's calendar. Once the prospect picks one, the demo invite is created from Salesforce with the AE attached as Lead Co-owner and the lead status set to 'Working - Demo Scheduled'.

Tags

outreachsalesforcecalendardemobookingae-handoff

Lets your agent filter to the right pattern

Categories and tags scope the retrieval set, so your agent receives only the patterns relevant to the task instead of scanning the full library.

What and why

The observed behaviour and the reasoning behind it.

Behaviour

When a prospect replies positively to an Outreach sequence step, the SDR pauses the sequence inside Outreach as the very first action, never afterwards. They then open the AE's shared calendar, find three concrete thirty-minute slots in the next seven calendar days that work for the AE and the prospect's likely working hours and reply from inside Outreach offering those three options. Once the prospect picks a slot, the SDR creates the demo invite from Salesforce's Schedule Demo quick action, attaches the AE as Lead Co-owner and updates the lead status to 'Working - Demo Scheduled'.

Reasoning

Pausing the sequence first stops the next templated email landing the moment the prospect agrees to a meeting, that mistake makes the team look automated and prospects mention it on demo calls. Three concrete time slots convert at almost double the rate of a Calendly link as a first response, the link suggests low effort and prospects often forget to click it. Thirty-minute slots first attend twenty percent better than sixty-minute first demos, the bigger commitment scares people. The Schedule Demo quick action populates the description with the BANT brief from the activity timeline, the AE walks into the demo with the prospect's pain quote in front of them.

Gives your agent an operator's reasoning

Behaviour records the action; reasoning records the rationale. Your agent applies both to handle cases that diverge from the captured examples.

Cause and effect

What initiates this pattern and what it produces.

Trigger

A prospect replies to any step of an Outreach sequence with clearly positive intent to meet (e.g. 'happy to chat', 'send me some times', 'this is interesting').

Outcome

A demo meeting is on the prospect's calendar, the right Account Executive is attached and notified, the Outreach sequence is paused and the Salesforce lead reads 'Working - Demo Scheduled' with the AE assigned as a co-owner.

Tells your agent when to act and what to verify

Your agent stays within the scope set by the trigger and outcome, so it doesn't extend beyond the work or finish before the outcome is met.

Standard operating procedure

Step-by-step instructions to reproduce this pattern.

Outreach

Open the prospect's reply in the Outreach Inbox and click Pause Sequence as the first action.

Pause comes before any reply or meeting work. Replying first leaves a window where the next sequence step can fire if the SDR is interrupted, the team has been called out by prospects for that exact failure mode three times this year.

Expected: The sequence is paused and no further automated emails will fire.

Salesforce

Open the prospect's Salesforce lead and check the AE territory mapping for the right Account Executive.

Territory is mapped by country and ICP segment, never assume by company size alone. The same company can map to a different AE depending on whether it falls in mid-market or enterprise on the head-count band. If the territory mapping is ambiguous, ask in the rev-ops Slack channel before scheduling, double-booking AEs is one of the team's recurring incidents.

Expected: The correct AE for this prospect is identified.

Outreach

Open the AE's shared calendar in a second tab and find three concrete thirty-minute slots over the next seven calendar days that work for the AE and the prospect's likely time-zone.

Always offer thirty-minute slots first, never sixty. Sixty-minute first demos under-attend by twenty percent, prospects feel the commitment is too high for an unknown product. If the prospect explicitly asked for a longer slot, escalate to the AE in their DMs before offering, the AE may want to swap to a more senior demo lead.

Expected: Three concrete slot options are ready to paste into the reply.

Outreach

Reply from the Outreach Inbox view with the three concrete slot options in the prospect's local time-zone.

Always reply from inside Outreach, never from the SDR's personal inbox. Replies from the personal inbox break the activity timeline on Salesforce and the AE loses sight of the conversation history. Always include the prospect's local time-zone in brackets after each slot, e.g. 'Wed 6 May, 10:30 (PT)'.

Expected: The reply is sent and the conversation is logged on the Salesforce lead via the Outreach sync.

Salesforce

When the prospect picks a slot, create a calendar invite from inside Salesforce using the Schedule Demo quick action on the lead.

Schedule Demo populates the description with the BANT-plus-Pain brief from the Salesforce Activity timeline. Going through Schedule Demo not a fresh calendar invite means the AE accepting the invite sees the prospect's pain quote, BANT signals and SDR notes by default, no prep call required.

Expected: A calendar invite is on the prospect's calendar with the AE attached and the discovery brief in the description.

Salesforce

Add the AE as Lead Co-owner with role 'Demo Owner' so they get notification of the prospect's responses.

Co-ownership splits the Salesforce notification rules so both SDR and AE receive replies. Without this, the AE only sees the conversation when they log in to Salesforce manually and prospect replies between booking and demo can sit unread for days.

Expected: The AE is on the lead and will be notified of any further replies.

Salesforce

Update Lead Status to 'Working - Demo Scheduled' and tag the lead with the AE's name.

The status field drives the bookings dashboard the team reviews on Friday. The AE name in the tag drives the per-AE pipeline dashboard. Both are needed, neither one is sufficient on its own and skipping either silently drops the demo from the wrong report.

Expected: Lead Status is updated and the lead is in the right reporting bucket.

Hands your agent your team's exact steps

Your agent executes the documented procedure in order, against the applications named at each step, producing consistent output across human and agent runs.

Book a demo

Related patterns

How this pattern connects to other patterns in the library.

Often previous

Adding a prospect to a personalised cold email sequence Logging a discovery call outcome Moving an unresponsive prospect to a break-up sequence

Often next

Converting a qualified lead and handing off to the AE

Lets your agent confirm the match and its scope

Alternative patterns let your agent compare candidates and select the closest match. Previous and next patterns define position in the workflow, so the agent operates within the scope of this one.

Supporting actions

Actions that provide evidence for this pattern.

Paused 'rev-ops-mid-market' sequence after positive reply from Director Ops at Brava Health

Offered 3 thirty-minute demo slots in prospect's Pacific time-zone

Booked demo with AE Maya Chen for Heliograph Labs, attached BANT brief via Schedule Demo

Updated Salesforce Lead Status to 'Working - Demo Scheduled' and tagged AE name

Added AE as Lead Co-owner with role 'Demo Owner' on Marlowe Capital lead

Shows your agent the evidence behind the pattern

Each pattern is derived from captured action sequences. Your agent can reference the source actions to verify any field, so nothing it acts on is authored by hand or hallucinated.

Metadata

Timestamps and identifiers.

Evidence	Observed 81 times across 5 connections
Applications	Outreach, Salesforce
First seen	29 Jan 2026, 11:32
Last seen	7 May 2026, 11:14

Helps your agent rank patterns by confidence

Action count and last-seen timestamp weight each pattern by frequency and recency, so your agent selects the highest-scoring match rather than the first returned.

Questions

Frequently asked questions

Book a demo View all examples

Speak to the founder

Get a demo. Watch a live capture, then an AI agent query the result.

Ask anything. Pricing, security or integrating with your stack.

No purchase obligation

Book a call

Start capturing

Record in minutes. Install once and work as normal.

Plug AI agents in. One API call from any AI agent stack.

Refund on unused credits if you cancel