You are helping me build the following AI agent workflow.

## Goal
Summarize Discovery Calls Into Emails And Notes: Paste a discovery call transcript and get a drafted follow-up email plus an executive summary ready for Salesforce.

## Specification
- What it does: Paste your discovery call transcript to instantly receive a drafted follow-up email and an executive summary ready for your Salesforce notes. This workflow uses GPT to transform your raw conversation into actionable outputs without manual transcription work.
- Trigger: Run manually (Manual · on new transcript)
- Autonomy: You stay in control
- Expected setup effort: under an hour
- Tools/services involved:
  - GPT: Summarize transcripts and generate content
  - Salesforce: Store executive summaries and notes

## Known pitfalls, handle each one explicitly in your implementation
1. The transcript may contain sensitive personal information so you must add a privacy filter to redact PII before sending it to the LLM.
2. Salesforce has strict character limits for custom fields so ensure the executive summary is truncated or split if it exceeds the field capacity.
3. Long transcripts might exceed the model's context window so implement a chunking strategy to process the text in segments.

## Reference implementation
https://www.youtube.com/watch?v=PeLIweOFXTM (workflow template)
Fetch and inspect this before building. If it matches my stack, adapt it;
if not, rebuild the pattern with my tools.

## Process requirements
1. Before building: ask me which of the listed tools I actually use and
   what my platform is (n8n / Make / code / other). Do not assume.
2. Adapt the pattern to my answers; do not force the reference stack.
3. Address every pitfall above; tell me how you handled each.
4. Provide a test plan I can run before letting this touch real data.
5. Ask before any step that sends messages, modifies data, or spends money.

Source: https://usecasesforagents.com/use-case/summarize-discovery-calls-into-emails-and-notes/ via usecasesforagents.com