SOCIAL MEDIA

Enrich Discord repliers and draft a personalized DM

Takes each engaged Discord replier, searches the web for who they are, drafts a tailored opener with an LLM.

CategorySocial Media
Enginesim
Difficultyintermediate
Triggerevent
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerNew reply in watched Discord channelDiscordDiscord
  • LogicFilter substantive replies; extract author identity
  • ActionSearch the web for the replier's profileBraveBrave Search
  • ActionSummarize findings and draft personalized DM openerOpenAI
  • OutputSave enriched profile and draft DM to AirtableAirtableAirtable

What it does

Closes the gap between spotting a warm replier and actually sending a good DM. For each person who engages with your posts, it researches them on the open web, summarizes what it finds, and writes a personalized opening message so your outreach never starts cold.

When to use it

Reach for this when generic "hey, saw your reply" DMs aren't converting and you want every message grounded in something real about the person. Best for small teams doing high-intent, low-volume founder-led outreach where each DM should feel hand-written.

How it works

  1. 1A new reply event arrives from the watched Discord channel.
  2. 2A filter keeps only substantive replies and extracts the author's username and display name.
  3. 3A Brave Search call looks up the person across the public web to find their role, company, or recent work.
  4. 4An LLM summarizes the findings and drafts a two-sentence personalized DM opener referencing their reply.
  5. 5The enriched profile, source links, and draft DM are saved to an Airtable outreach table marked Ready to send.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect DiscordCommunity channels + voice + bots.
  2. 2
    Connect Brave SearchWeb, news, image, video search.
  3. 3
    Connect OpenAIModels, embeddings, files.
  4. 4
    Connect AirtableBases, tables, views, automations.
  5. 5
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  6. 6
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  7. 7
    Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.

Run this workflow in your colony.

14-day trial. No DevOps. No Sales call. Provisioned in under a minute.