DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to have an agent fill contact gaps from your own email threads with CRM

Run the research agent so it reads your CRM's threads, meetings and signature blocks and records strong facts.

Who it is forA sales rep or RevOps lead with many contacts that have missing job titles or companies after email and meetings have already happened.

The problemContact records go stale or stay blank because nobody updates them after each conversation.

The outcomeThe agent records facts it can support from CRM history, and weak evidence appears as suggestions for a person to settle.

What you need first

  • Bun and Docker installed
  • A Google or Microsoft OAuth client, or your own identity provider set up later under Settings → SSO
  • A value for BETTER_AUTH_SECRET and an ALLOWED_SIGN_IN domain or address
  • Optional: a Context API key for company brand data and LinkedIn lookups, and a PERPLEXITY_API_KEY for web research

Steps

  1. Deploy apps/agent next to the CRM and set AGENT_BRIDGE_SECRET to the same value in both processes
  2. Open a contact and select the Agent tab to see the steps the agent takes
  3. Review the startup list that shows which sources are on (for example, Web research with PERPLEXITY_API_KEY)
  4. Check the facts it recorded on the contact and resolve any suggestions it could not decide

Prompt for your agent

In the trycompai/crm repo, use the apps/agent research agent to run read_crm_history and record_fact for the contact <contact-name>, with no outside API keys set. Report the facts recorded and any suggestions left for a human. Verify that every recorded fact cites an observed source such as a signature block or thread.

Caveat. The README says the agent is designed to run with no outside keys, but it still needs a deployed apps/agent and a running CRM, and the README does not give the exact command to start the agent.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page