ENGINEERING
Private transcription ADR drafting agent
Downloads the recorded design-sync audio, transcribes it with a self-hosted Hugging Face speech model to keep sensitive architecture talk off third-party APIs.
How it runs
The automated pipeline, trigger to output.
- TriggerZoom recording completed for reviewZoom
- ActionDownload recording audio from ZoomZoom
- ActionTranscribe via self-hosted Hugging Face modelHugging Face
- LogicConfirm a decision was reached
- OutputPublish Proposed ADR draft to ConfluenceConfluence
What it does
Generates ADR drafts from recorded architecture reviews while keeping the audio inside your own infrastructure. Rather than relying on Zoom's cloud transcript, it downloads the recording and runs a self-hosted Hugging Face speech-to-text model, then extracts the decision and writes a Confluence ADR - suitable for teams under strict data-handling rules.
When to use it
Use it when compliance forbids sending meeting audio to external transcription or LLM vendors, but you still want automated ADR drafting. Best for regulated orgs running their own model endpoints.
How it works
- 1A Zoom recording-completed event triggers for the review.
- 2Download the recording's audio file via the Zoom API.
- 3Send the audio to a self-hosted Hugging Face inference endpoint for transcription.
- 4An agent step extracts the decision, context, and consequences from the transcript.
- 5A logic check confirms a decision exists before writing anything.
- 6Publish the structured ADR draft to the Confluence space, marked Proposed.
Set it up
What you configure once, before turning it on.
- 1Connect ZoomMeetings, recordings, transcripts.
- 2Connect Hugging FaceModels, datasets, spaces — the open-source hub.
- 3Connect ConfluenceSpaces, pages, blueprints.
- 4Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 5Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 6Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More Engineering workflows
Gate breaking API PRs behind downstream consumer acknowledgement
When a PR introduces a breaking contract change, comments the impact summary back on the PR, applies a blocking label.
Publish a versioned API changelog to Confluence on each release tag
On a new semver release tag, gathers the contract changes since the last release and writes a clean.
Agent reviews model-license fit and suggests compliant swaps on the PR
When a PR adds a Hugging Face model, an agent reads the model card and license, judges fit against your commercial-use policy.
Upgrade Impact Router to Module Code Owners
Maps a dependency-bump PR's affected modules to their CODEOWNERS, then DMs each owner on Slack with only the changelog slice that touches code they own.
Re-Voice IVR Prompts on Phone-Tree Config Merge
When a phone-tree config change merges in GitHub, regenerates the ElevenLabs audio for any prompt whose script changed in the diff and opens a follow-up PR adding the new audio…
Upstream Release to Notion Upgrade Brief
When a watched package publishes a new release, fetches the release notes, maps them to the internal modules that depend on it.
Run it inside a business
This workflow drops into a full company template. Import the org, and this is one of the playbooks its agents run.
Run this workflow in your colony.
14-day trial. No DevOps. No Sales call. Provisioned in under a minute.