Overwise — WritingBuild-in-public posts from Overwise: agentic outreach decisions, deliverability, and lead-discovery research from a trust-first AI sales agent.https://overwise.ai/enMulti-source lead discovery vs. a contact databasehttps://overwise.ai/blog/multi-source-discovery-vs-contact-database/https://overwise.ai/blog/multi-source-discovery-vs-contact-database/A contact database sells you a static list everyone else also bought. Multi-source discovery routes your ICP across many live sources and finds the B2B companies you actually sell to — including the long tail one database misses. Here's the difference, and why it changes who you can reach.Wed, 24 Jun 2026 00:00:00 GMTlead-discoverytrustDeliverability for founders: warmup, bounce-pause, and SPF/DKIM/DMARChttps://overwise.ai/blog/deliverability-for-founders/https://overwise.ai/blog/deliverability-for-founders/Cold email lands in spam for boring, fixable reasons: unauthenticated domains, cold mailboxes sending too fast, and bounce rates that torch your reputation. Here's the founder's version of deliverability — what actually protects your domain, and what Overwise enforces by default so you can't shoot yourself in the foot.Sat, 20 Jun 2026 00:00:00 GMTdeliverabilitytrustHow AI qualifies a B2B lead: absence signals and buying triggershttps://overwise.ai/blog/how-ai-qualifies-a-b2b-lead/https://overwise.ai/blog/how-ai-qualifies-a-b2b-lead/Finding companies is the easy half. Qualification is what turns a list into leads worth emailing. Here's how configurable absence signals — what a company doesn't have — plus hiring and funding triggers score each lead 0–100 against your product, not a generic firmographic filter.Tue, 16 Jun 2026 00:00:00 GMTlead-discoveryqualificationCite-or-discard as a product primitive: how the MessageVerifier earns its keephttps://overwise.ai/blog/cite-or-discard/https://overwise.ai/blog/cite-or-discard/The MessageVerifier is a binary cite-or-discard gate on every draft the agent produces. Every factual claim has to point at evidence from the lead's context — or the draft is discarded and re-drafted. Why we built it as a primitive instead of a score, and what it costs.Thu, 14 May 2026 00:00:00 GMTtrustdeliverabilityengineeringCross-tenant cooldown: 7 days because we'd want it ourselveshttps://overwise.ai/blog/cross-tenant-cooldown/https://overwise.ai/blog/cross-tenant-cooldown/When two of our customers independently find the same lead, the second one to send is silently held for seven days. Thirty days if the lead already replied. Neither customer sees the other. Here's why we built it that way, what it costs each tenant, and why the alternative — both customers firing in the same week — is the failure mode we refuse to ship.Thu, 14 May 2026 00:00:00 GMTdeliverabilityarchitecturetrustThe reply-rate trap: why we don't promote A/B winners by reply ratehttps://overwise.ai/blog/reply-rate-trap/https://overwise.ai/blog/reply-rate-trap/Every other outbound tool ships an A/B winner-picker that promotes the variant with the higher reply rate. The trap: reply rate collapses positive replies, negative replies, and unsubscribes into one number. The 'winning' variant is often the one with more 'stop emailing me'. Here's what we built instead.Tue, 12 May 2026 00:00:00 GMTmetricstrustengineeringReplacing a fixed sequence with an agentic loophttps://overwise.ai/blog/agentic-loop-decisions/https://overwise.ai/blog/agentic-loop-decisions/Notes from rebuilding Overwise's outreach pipeline as an agentic system: a Sonnet executor that decides per-lead what to send, an Opus advisor for edge cases, and a MessageVerifier that discards drafts whose claims can't be cited. What we threw away, what we replaced it with, and why.Fri, 01 May 2026 00:00:00 GMTagentic-outreachtrustengineering