Automation library · Scheduling

Automate Microsoft Teams meeting analysis with Outlook

Started by someone submitting a form, and works across Outlook and Postgres. It hands the judgement calls to OpenAI. 51 steps, 2 branches, 1 loop or waits: large, and worth reading before you trust it with anything live.

LargeCalls a model: OpenAI

51 stepsLarge: read it before trusting it with anything live
2Branches: places the flow splits
1Loop or waits
2Services it connects to

The flow

Starts it 7Model 4Logic 25Service 15

The steps in the order they run, from what starts it.

  1. 1Schedule TriggerSchedule triggerStarts it
  2. 2OpenAI Chat ModelLm Chat Open AiModel
  3. 3Web PageWebhookStarts it
  4. 4Next ActionWebhookStarts it
  5. 5OpenAI Chat Model1Lm Chat Open AiModel
  6. 6On form submissionForm triggerStarts it
  7. 7Merge1MergeLogic
  8. 8AI Agent Create SummaryAgentModel
  9. 9Get Meeting Row1PostgresService
  10. 10Get Meeting RowPostgresService
  11. 11AI Agent Draft Follow UpAgentModel
  12. 12Code2CodeLogic
  13. 13Get Microsoft 365 ProfileHttp RequestService
  14. 14Set JSONSetLogic
  15. 15Respond With WebApp HTMLRespond To WebhookStarts it
  16. 16MarkdownMarkdownLogic
  17. 17Set Email JSONSetLogic
  18. 18If2IfLogic
  19. 19Email HTMLHtmlLogic
  20. 20Summary HTMLHtmlLogic
  21. 21SwitchSwitchLogic
  22. 22Send Follow UpMicrosoft OutlookService
  23. 23Set Transcription & Subject2SetLogic
  24. 24Set Time RangeSetLogic
  25. 25End Analysis NotificationMicrosoft OutlookService
  26. 26Save DataPostgresService
  27. 27Mem NoteHttp RequestService
  28. 28Respond With Code 200Respond To WebhookStarts it
  29. 29MergeMergeLogic
  30. 30Get Call RecordsHttp RequestService
  31. 31Loop Over ItemsSplit In BatchesLogic
  32. 32Respond to Webhook1Respond To WebhookStarts it
  33. 33Code1CodeLogic
  34. 34Filter for Join Url1FilterLogic
  35. 35Get Online Meeting Details1Http RequestService
  36. 36Split Out Meetings1Split OutLogic
  37. 37Remove DuplicatesRemove DuplicatesLogic
  38. 38Sort1SortLogic
  39. 39Check if ProcessedPostgresService
  40. 40Filter No ItemsFilterLogic
  41. 41Keep MatchesMergeLogic
  42. 42Get ItemsCodeLogic
  43. 43Get Transcript DataHttp RequestService
  44. 44Split Out TranscriptionsSplit OutLogic
  45. 45Search OneDrive for MeetingHttp RequestService
  46. 46Get TranscriptHttp RequestService
  47. 47Split Out3Split OutLogic
  48. 48Set Transcription & SubjectSetLogic
  49. 49List Transcripts2Http RequestService
  50. 50Get Transcript1Http RequestService
  51. 51Set Transcription & Subject1SetLogic

How it's built

Starts on
Someone submitting a form
Steps
51, with 2 branches, 1 loop or waits
Size
Large: read it before trusting it with anything live
Connects to
Outlook, Postgres
Model
OpenAI

Questions

What does it need to run?

An n8n account, plus your own Outlook and Postgres accounts, and a key for OpenAI. You connect your own accounts after importing it; none are included.

What starts it?

It starts on someone submitting a form.

Does it use AI?

Yes. It calls OpenAI. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Take your time. At 51 steps it is large: read it before trusting it with anything live.

How do I import it?

Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts.

Before you run it

Nothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 51 steps before you point it at anything that matters.