Outbound-to-CRM pipeline
A GTM system that turns cold-email events into CRM contacts, deals and team alerts, and keeps opt-outs, lead rotation and follow-up enrolment in sync without manual work.
- 1The problem
Replies, opt-outs and interested leads from outbound campaigns had to be copied into the CRM by hand, so deals were missed, opted-out contacts risked being emailed again and nobody trusted the pipeline view.
- 2Our contribution
Designed and built by Kumar Sahil.
- 3What we built
One container image with 10 run modes on serverless jobs: a webhook receiver for campaign events, opt-out sync, lead rotation, follow-up enrolment, a reconciler, monitoring and credit alerts. A 5-layer reply classifier (platform flag → keywords → LLM → statistical model → keyword safety net) decides which replies become deals, and secrets live in a managed secret store.
- 4The result
In production. Results shared on request.
Other systems we’ve built
Reply Classifier Cascade
A cost-ordered classifier for English and Dutch cold-email replies that decides which replies become CRM deals, built so a false “hot deal” needs several layers to agree.Read the case studyLLM Gateway
A provider-neutral LLM gateway: code asks for a job, the gateway routes it through a chain of models with safe failover, a deadline per call, and the cost of every call written to a ledger.Read the case studyLLM Eval Gauntlet
Invariant-checked evaluation suites for tool-calling agents that run in CI and fail the build when an agent invents a number, leaks its prompt or obeys an injection.Read the case studyFind the workflow worth automating first.
Tell us about one process that costs your team hours every week. We will tell you honestly whether AI or automation is the right fix, and what a first build would take.