Ad-hoc Q&A

Every team that uses Earmark accumulates a substantial archive of recorded conversations. The transcripts exist. The structured artifacts exist. The knowledge is captured. Captured is not the same as askable. The gap between “we have it” and “I can retrieve it” is wider than most teams admit — until someone asks “did we ever talk about pricing for the SMB tier?” and the only honest answer is “probably, somewhere.” This guide is about how to close that gap. It is unlike the other workflow guides in this set: there is no template, no recurring cadence, no destination per artifact. It is about the capability itself, what works today, and how to use it well. For the templated patterns this capability supports, see Workflows.

​

What works today and what doesn’t

Worth being precise about up front. Cross-meeting Q&A is Chat. Open Chat from the sidebar and ask in plain language: “What did this customer say across our last three calls?”, “What objections came up most often in sales calls this quarter?”, “When did we first discuss the SSO requirement?” Chat searches your meetings, shows its research as it works (Searching Earmark, reading transcripts), and answers with source chips that point back to the meetings it drew from. Every answer about your meetings ends with a Coverage line: the date range it searched and how many meetings it reviewed. Say how far back to look. Most questions are about recent work. For anything older, ask for it: “across all my meetings”, “ever”, or name the period (“in Q1”, “since January”). If an answer looks thin, read the Coverage line before you conclude the topic never came up. Single-meeting Q&A starts from the meeting. Open a live or finished meeting and click Chat in its header to ask about that call — “what did Adi say about prep agent settings?”, “did I commit to anything?”, “what was the customer’s main objection?” — or reach back with “Did this come up in the previous meeting?” During a live meeting, it reads the conversation so far. When you want the answer kept on the meeting, ask meeting chat for “an artifact”, or write the question as a task in the Composer. Projects narrow the corpus. Put a customer’s calls, a hiring loop, or a launch’s meetings in a project and ask from the project page. Chat focuses on that project’s meetings, including ones teammates shared with it, and follows the project’s Instructions. This is the cleanest way to ask “what’s the latest status?” of one account without other calls leaking in. Search is still search. The command menu (Cmd+K / Ctrl+K) finds a meeting, artifact, or task by title or keyword. Use it when you know what you’re looking for and want to open it. Use Chat when you want an answer. What Chat can’t do:

• See meetings nobody shared with you. Chat uses meetings you recorded, plus meetings shared with you through projects. A teammate’s unshared calls stay private to them.
• Use temporary meetings. They aren’t saved, so there’s nothing to search later.
• Always know who said what. On desktop recordings your mic is kept separate from everyone else, so “what did I say?” works well. Other speakers aren’t identified by name with certainty, and Chat says when it’s guessing.

The rest of this guide is about using this well: asking good questions, and checking the answers.

​

Verification matters more here than anywhere else

Every other workflow has a template-driven cleanup step where the human reviews the artifact before it goes anywhere. Ad-hoc Q&A does not. The user often acts on the answer immediately. The model is good. It is not infallible. It can:

• Fabricate a quote that sounds plausible
• Conflate two speakers
• Get a date or detail wrong while getting the substance right
• Confidently answer a question the transcript does not actually support
• Answer from fewer meetings than you assumed, and read as complete when it isn’t

For low-stakes questions (“what was that thing Adi said about settings?”), the cost of an occasional wrong answer is low. For high-stakes questions — legal, HR, contractual, commitments to customers, board-level reporting — always verify against the source. The verification habit:

1. Check the source chips. Hover a chip to read the excerpt behind the claim. For meetings you recorded, click it to jump to that moment and hear it in context.
2. Read the Coverage line. “Never came up” across four meetings last month is a different answer from “never came up” across sixty meetings over a year. If the range or count is smaller than you expected, widen the question and ask again.
3. Ask for the verbatim moment when a claim has no source, or when you’re asking in a Composer task. If the model cannot produce a quote, treat the answer as unverified.

Thirty seconds. Not optional for anything you’ll act on or share.

​

Question patterns

Q&A does not have templates. It has patterns — shapes of questions that work well, with good and bad versions.

​

Catch-up

For when you missed a meeting or want to refresh on one. Why the good versions work: scoped output length, told what to prioritize.

​

”Did we” verification

For checking whether something specific happened. For these especially: check the source chip, or ask for the verbatim quote. If there’s no source, the answer is unverified.

​

Person-specific recall

Name a person and a topic. People misremember who said what; the model occasionally does too, and Chat tells you when it’s guessing at a speaker. Ask for the moment.

​

Open questions

For finding what was not resolved. Especially useful as input to the next meeting’s agenda. These ask for absence of resolution, which is harder for the model to fabricate — there is no positive thing to invent.

​

Pre-meeting prep

For the next call with a customer or person you’ve met before. Ask these in Chat and name the customer, and it draws on every prior call it can find, not only the last one. With your calendar connected, “Help me prepare for tomorrow using my past meetings” pairs each upcoming event with related past meetings. For the templated version, see the pre-meeting prep workflow.

​

Self-coaching

For reviewing your own performance on a call. Especially valuable for sales reps and managers reviewing their own conversations. The model can flag things you didn’t catch in the moment.

​

Comparison

For comparing two meetings or two people — when both are in the corpus. Ask these in Chat and name both meetings, or ask from meeting chat on the newer one. Before you trust the comparison, check that both meetings show up as sources.

​

Across many meetings

For rollups: recurring themes, frequency, first mentions, how a position shifted over time. Name the set of meetings (a customer, a series, a period), the dimension you care about, and the shape you want back. Ask for frequency, and for what’s missing as well as what’s there.

​

Running single-call Q&A

​

Asking across meetings

The patterns from the previous section still apply: be specific about scope, name dimensions precisely, ask for citations, ask for frequency, ask for what’s missing as well as what’s there. If you want to run your own analysis. Some jobs call for a method you control end-to-end, like a custom scoring pass over a year of interviews, or output that feeds another system on a schedule. For those, export the transcripts and run an external agent across them. The agent you use is your call.

​

Graduating an answer into a durable artifact

Most ad-hoc answers are ephemeral — you wanted the answer, you got it, you moved on. Some are worth keeping. An answer is worth graduating when any of these are true:

• Others will need it. “When did we decide X?” belongs in the decision log.
• It will be relitigated. If it’ll be asked again, the answer should live somewhere durable.
• It’s evidence. Customer pain, feature requests, verbatim quotes — belong in the research repo.
• It changes the playbook. Patterns of objections, repeated questions — feed enablement and sales.

The “ask then write” loop is the right shape: ask the model the question, get the answer, write the durable version of the answer in your own words, paste it into the destination. The Q&A surfaces substance; the writing forces ownership of the claim. The combination produces better artifacts than either pure model output or pure manual writing. When the answer comes from Chat, Copy keeps its formatting but drops the source chips. Wherever the claim has to hold up later, name the meeting and date yourself. Copy as image captures the response, including its visible research steps and source chips, with your name and the available meeting context. It leaves out your question. Match the graduated answer to its destination: Verification answers usually don’t need a destination at all. “Did I commit to that?” — the answer is for you, in the moment. If the answer is yes and you need to act on it, push the action to your task system; the Q&A itself does not need to be preserved.

​

Privacy

Q&A inherits the privacy model of the meetings themselves. Earmark’s workspace isolation keeps each user’s meetings private by default — see Security and privacy. Your chats are private to you. Chat only draws on meetings you recorded and meetings shared with you through projects. The line that matters is the project. Once you add a meeting to a shared project, everyone in that project can ask Chat about it and see short excerpts as sources, even though they can’t open the meeting. Keep sensitive meetings out of shared projects. Some categories worth handling deliberately:

• 1:1s — queryable only by the two participants, or with explicit consent. See the people and team meetings workflow.
• Candidate interviews — within the hiring loop, fine. Outside, no.
• Skip-levels — confidential to the participants.
• Comp, performance, termination conversations — should not be in the corpus at all. Use temporary meetings for sensitive sessions you want captured without keeping.

If you’re not sure whether you should be querying something, you shouldn’t.

​

Common pitfalls

• Vague questions, vague answers. Specificity of the question controls quality of the answer. Always tell the model the desired length, audience, and what to prioritize.
• Acting on unverified high-stakes answers. The verification habit is not optional for anything you’ll act on. Build it from day one.
• Treating Cmd+K as Q&A. It is search. It finds the meeting; Chat answers the question.
• Scope mismatch across meetings. Too narrow misses context; too broad produces mush. Pick the smallest corpus that could plausibly contain the answer — name the customer, series, or period, or ask from a project.
• Skipping the Coverage line. An answer drawn from three meetings when you expected thirty usually means the date range was too short. Widen it before you trust “it never came up.”
• Querying meetings you shouldn’t. 1:1s, skip-levels, candidate interviews outside the loop, comp conversations. Know the lines and respect them.
• Treating ephemeral answers as durable. Not every answer needs a destination. Capture the ones that matter; let the rest go.
• Letting answers replace conversation. “What does Sam think about X?” is a fine question to ask the model. It is a better question to ask Sam.
• Skipping iteration. The first answer is rarely the final answer. Push back, refine scope, ask for sources.
• Asking the model to judge sensitive things about people. “Is Sam disengaged?” is the kind of question the model can help you investigate. It is not the kind it should answer outright. Use it to surface patterns; interpret the patterns yourself, in conversation with Sam.
• Confirmation bias. You’ll occasionally ask questions where you already think you know the answer. The model will sometimes confirm what you wanted to hear. This is the easiest moment to skip verification.
• Over-reliance for memory tasks. Some recall is your job. If you outsource every verification to the model, your engagement with your own meetings degrades.

​

Where to go next

• Chat — asking across your meetings, sources, and the Coverage line
• Projects — grouping meetings so Chat answers from a focused set
• Composer — for single-call Q&A you want saved as an artifact
• Command menu — for finding a meeting by title or keyword
• Local transcripts — if you want to run your own analysis
• Temporary meetings — for sensitive sessions you want captured without keeping
• Workflows — the templated patterns this capability supports
• Customer research workflow — for the systematic version of “what did customers say”
• Sales calls workflow — for the systematic version of “what’s the state of this deal”
• People and team meetings workflow — for the privacy discipline around 1:1s and interviews