Home About Experience Projects Case studies Resources Articles Briefs Playbook Tools FAQ How we start Security Get in touch

AI automation

Meeting Notes to Action Items, With a Human Gate

This is the automation most likely to be built badly, because it is the one where people hand a language model more authority than it should have. Here is where the model earns its place, and where a rule is simply correct.

If you are writing during a meeting, you are not fully in it. That is the case for automating meeting notes, and it is a good one.

It is also the automation most likely to be built badly, because it is the one where people hand a language model more authority than it should have.

THE GATE IS THE WHOLE DESIGN Recordingand transcript Model extractstask, owner, date A human reviews two minutes, before anything is created Taskscreated Remove the gate and you have automated the creation of confident, plausible, wrong tasks. The model will assign an owner who was only mentioned in passing. It will turn "we should probably look at that" into a task with a due date nobody agreed to.
Figure 1: extraction is genuinely good. Judgment about what was actually decided is not, and it never has to be.

What the model is genuinely good at

Three things, and they are real: summarising a long transcript into something readable, extracting structure from loose speech into task, owner and date, and drafting the follow-up message.

Language models are unusually well suited to this because meeting speech is exactly the sort of unstructured input that deterministic parsing handles badly. Nobody says "action item, owner Sarah, due Friday." They say "yeah I'll pick that up before the end of the week probably."

What it is not good at, and never needs to be

Deciding what was actually agreed. A transcript contains firm commitments, tentative suggestions and thinking out loud, and they sound similar. A model asked to extract action items will confidently produce tasks from all three.

The characteristic failures are consistent: assigning an owner who was mentioned rather than volunteered, and converting "we should probably look at that" into a task with a due date nobody agreed to. Both are plausible enough that nobody catches them until the task is late.

Automate the extraction. Never automate the acceptance. The two-minute review is not overhead, it is the design.

WHERE THE MODEL BELONGS, AND WHERE IT DOES NOT Use a model summarising a long transcript pulling structure out of loose speech drafting the follow-up email classifying topic or urgency spotting what was never assigned Use a rule calculating a due date routing by project or client deciding who is notified anything with one correct answer anything that must be auditable
Figure 2: the common failure is using a model where a rule would be right one hundred percent of the time.

How to build it

1. Record and transcribe first, and only that

Get reliable transcripts working before adding any extraction. If transcription is patchy, everything downstream inherits the problem and you will blame the model for it.

2. Extract into a structured format, not prose

Ask for JSON with explicit fields: task, owner, due date, and a confidence flag. Prose output cannot be validated or routed, and it invites the model to editorialise.

3. Instruct it to leave gaps rather than guess

The single most valuable line in the prompt is an instruction to return null for any owner or date that was not explicitly stated, rather than inferring one. A blank you can fill beats a plausible wrong answer you will not notice.

4. Route it to a human before anything is created

Post the extracted list somewhere a person confirms, edits or deletes items. Two minutes after the meeting, while it is fresh. Nothing enters the tracker without passing this gate.

5. Use rules for everything with a correct answer

Due date calculation, project routing, who gets notified, formatting. These have one right answer and a rule will get it right every time. Handing them to a model introduces non-determinism for no benefit.

6. Sample the output monthly

Pick three meetings, compare the extracted list against the transcript yourself. You are checking whether the model has started drifting or whether people have started rubber-stamping the review. Both happen.

Tools and what they cost

OptionWhat it costsHonest trade-off
Meeting assistants (Fathom, Otter, Fireflies, Granola)Free tiers exist; paid plans typically $10 to $30 per user per month.Least work by far, with transcription and summary handled. Task extraction quality varies and the review gate is often weak or absent.
Built-in recording in your meeting platformIncluded in most business tiers.No extra subscription and no extra vendor holding your recordings. Summaries are usually more basic.
Transcript into your own model call, then a review stepAPI pricing is usage-based and small at meeting volumes.Full control over the prompt, the null-rather-than-guess instruction, and the gate. You build and maintain the pipeline.
Fully autonomous meeting-to-task agentsVaries; often bundled into AI platform pricing.Impressive in a demo. This is precisely where the gate gets removed, and it is the pattern I would avoid.

What it is actually worth, and the caution that belongs here

The time saving is real and modest: the note-taking itself, plus the follow-up that would otherwise be written by hand. The larger gain is attention, because the person who was transcribing can now read the room.

The caution is worth more than the saving. Gartner predicted in June 2025 that over 40 percent of agentic AI projects will be cancelled by the end of 2027, citing escalating costs, unclear business value and inadequate risk controls. That is a forecast rather than a measurement, and Gartner sells research rather than automation, which is why I am willing to quote it. Gartner has also estimated that only around 130 of the thousands of vendors marketing agentic capability genuinely have it.

Read alongside that, MIT's Project NANDA reported in 2025 that roughly 95 percent of enterprise generative AI pilots produced no measurable profit and loss impact. Those findings are preliminary and not peer reviewed, and the report has been publicly criticised since publication, which I state rather than leave you to discover.

The pattern across both: AI projects fail on governance and scope, not on model capability. A narrow, well-gated meeting-notes automation is on the right side of that line precisely because it is narrow and gated.

How it breaks

The review becomes a rubber stamp. After a month of accurate output people stop reading and start approving. This is the most likely failure and the hardest to detect. Monthly sampling is the countermeasure.

Tasks are created for things nobody committed to. Team members start finding work assigned to them from meetings where they said "maybe." Trust in the whole system goes quickly, and it does not come back easily.

Confidential meetings get recorded by default. Decide explicitly which meeting types are never recorded, and make it easy to turn off. A tool that records a difficult personnel conversation because nobody remembered to disable it is a serious problem.

How to tell whether it worked

Two measures. The share of decisions that become tracked items with an owner, which should rise. And the edit rate at the review gate, which is the health check: if it is near zero, either the extraction is excellent or nobody is actually reviewing, and you need to find out which.

Sources and honesty note. The agentic AI cancellation forecast is from a Gartner press release dated 25 June 2025 and is a prediction rather than an observed outcome; it is frequently re-dated in secondary coverage to imply more recency. The 95 percent figure is from MIT Project NANDA's 2025 State of AI in Business report, which describes itself as preliminary findings and is not peer reviewed, and which has attracted public criticism. Pricing is list price at time of writing. I have not quoted any vendor claim about hours saved by meeting automation, because those come from companies selling meeting automation.

Paul Prado Pacardo is a Senior Executive Assistant and Operations professional with over ten years supporting C-level leaders, and the solo founder of a multi-product software studio. Available for remote Chief of Staff, Operations, Senior Executive Assistant and Project Manager roles.