// KNOWLEDGE BASE

Knowledge base

Manage the chatbot's knowledge corpus. Active chunks live in Cloudflare Vectorize and surface in real-time chat responses.

38 of 38 chunks
  • blogThe 7-specialist review pipeline that keeps AI features from breaking in production/ The seven specialists

    [The 7-specialist review pipeline that keeps AI features from breaking in production — The seven specialists] Each specialist is a focused review prompt with a checklist. I run them as Claude subagents from the main session — each gets the diff plus the relevant context (schema,

    288 tokens/blog/seven-specialist-review/id: c_7441d24fbeeade22
  • blogThe 7-specialist review pipeline that keeps AI features from breaking in production/ The seven specialists

    [The 7-specialist review pipeline that keeps AI features from breaking in production — The seven specialists] The trap this catches: AI features that work in dev because the dev DB has 50 rows and collapse in prod because they introduced an unindexed full-table scan. ### 3. AI

    289 tokens/blog/seven-specialist-review/id: c_1c43caf6b8531a3d
  • blogThe 7-specialist review pipeline that keeps AI features from breaking in production/ The seven specialists

    [The 7-specialist review pipeline that keeps AI features from breaking in production — The seven specialists] What's the worst-case latency? What's the request budget per user action? Are model calls in a critical render path, or async? Are there caches, and are they invalidated

    296 tokens/blog/seven-specialist-review/id: c_8638561f27644cc4
  • blogThe 7-specialist review pipeline that keeps AI features from breaking in production/ How does the seven-specialist pass actually work?

    [The 7-specialist review pipeline that keeps AI features from breaking in production — How does the seven-specialist pass actually work?] Concretely, in the workflow: 1. PR is opened with the AI feature changes. 2. Pre-commit hook runs the unit tests and type-checks. 3. Author

    193 tokens/blog/seven-specialist-review/id: c_87543928f4e5fa95
  • blogThe 7-specialist review pipeline that keeps AI features from breaking in production/ How does the seven-specialist pass actually work?

    [The 7-specialist review pipeline that keeps AI features from breaking in production — How does the seven-specialist pass actually work?] The whole pass takes 4–8 minutes wall-clock for a typical feature PR<sup class="sidenote-mark">①</sup>. Author wait-time is roughly the time

    162 tokens/blog/seven-specialist-review/id: c_920d418f2924ee36
  • blogThe 7-specialist review pipeline that keeps AI features from breaking in production/ Why seven specialists, not three or fifteen?

    [The 7-specialist review pipeline that keeps AI features from breaking in production — Why seven specialists, not three or fifteen?] Three is too few — the lenses overlap enough that you miss whole categories. Fifteen is too many — diminishing returns and review fatigue set in.

    176 tokens/blog/seven-specialist-review/id: c_f8b78c4ca1cb6162
  • blogThe 7-specialist review pipeline that keeps AI features from breaking in production/ What it has caught for me

    [The 7-specialist review pipeline that keeps AI features from breaking in production — What it has caught for me] A non-exhaustive list from the last twelve months: - A voice agent that quoted stale eligibility caps because its tool was reading from a 12-minute cache (perf +

    236 tokens/blog/seven-specialist-review/id: c_7030b27b0cf941cb
  • blogThe 7-specialist review pipeline that keeps AI features from breaking in production/ How do you get started with this review pipeline?

    [The 7-specialist review pipeline that keeps AI features from breaking in production — How do you get started with this review pipeline?] Copy the seven names. Write a one-page checklist for each one yourself — what does "architecture" mean in your stack, what does "observabilit

    195 tokens/blog/seven-specialist-review/id: c_7e1ddd6b5af1535f
  • blogAnatomy of an HEI eligibility engine: four investor overlays, zero LLMs in the decision/ What this means for HEI operators evaluating vendors

    [Anatomy of an HEI eligibility engine: four investor overlays, zero LLMs in the decision — What this means for HEI operators evaluating vendors] The HEI market in 2026 sits at the inflection the consumer-mortgage-tech market hit around 2018: a wave of "AI" tools that look impres

    286 tokens/blog/hei-eligibility-engine-anatomy/id: c_9a7e697a672868be
  • blogHow we cut a home equity platform's lead-to-close cycle in half

    [How we cut a home equity platform's lead-to-close cycle in half] This is a field report. Names are abstracted; the work is real. The company runs a multi-program home equity portfolio — HEI, HEA, SLB, shared-equity, plus an alt-finance product. Series Seed–B. Twelve people. Wh

    103 tokens/blog/lead-to-close-half/id: c_5fd4c88a42f5b1f6
  • blogHow we cut a home equity platform's lead-to-close cycle in half/ What did the funnel look like before we started?

    [How we cut a home equity platform's lead-to-close cycle in half — What did the funnel look like before we started?] The funnel had four problem areas, in priority order: **1. Inbound response.** Leads were calling the main line. The main line was a human SDR. After 5 p.m. or b

    258 tokens/blog/lead-to-close-half/id: c_cc1ca879d63f9217
  • blogHow we cut a home equity platform's lead-to-close cycle in half/ What did the funnel look like before we started?

    [How we cut a home equity platform's lead-to-close cycle in half — What did the funnel look like before we started?] **3. Enrichment gap.** Lead intake captured name, email, phone, property address, and self-reported home value. Underwriting needed all of that plus county tax re

    175 tokens/blog/lead-to-close-half/id: c_d810d32b6702adc7
  • blogHow we cut a home equity platform's lead-to-close cycle in half/ Component 1 — Voice intake

    [How we cut a home equity platform's lead-to-close cycle in half — Component 1 — Voice intake] We wired Retell + Claude + Deepgram into the existing phone number. The agent picks up inside 1.5 rings, qualifies on six fields (state, age, property type, estimated home value, estim

    261 tokens/blog/lead-to-close-half/id: c_40ce614e04de997a
  • blogHow we cut a home equity platform's lead-to-close cycle in half/ Component 1 — Voice intake

    [How we cut a home equity platform's lead-to-close cycle in half — Component 1 — Voice intake] **Impact:** Time-to-first-response on inbounds dropped from a median of 17 minutes (during business hours) to 22 seconds. Off-hours response went from "next-day callback" to "in-call q

    89 tokens/blog/lead-to-close-half/id: c_b8918b78b8ccd88c
  • blogHow we cut a home equity platform's lead-to-close cycle in half/ Component 2 — Eligibility config

    [How we cut a home equity platform's lead-to-close cycle in half — Component 2 — Eligibility config] We pulled all the eligibility logic out of the calculators and into an admin-driven settings table. State whitelists, LTV caps, CLTV caps, ownership rules, minimum equity, FICO f

    231 tokens/blog/lead-to-close-half/id: c_0cdbd16dec1042df
  • blogHow we cut a home equity platform's lead-to-close cycle in half/ Component 3 — Agentic enrichment

    [How we cut a home equity platform's lead-to-close cycle in half — Component 3 — Agentic enrichment] We built a Claude agent with web-search tools that takes a lead's address and fills out the underwriting profile. County tax record, lien status, AVM (we use three different sour

    231 tokens/blog/lead-to-close-half/id: c_968f9009ca5a8f76
  • blogHow we cut a home equity platform's lead-to-close cycle in half/ Component 4 — Post-acceptance contract gen

    [How we cut a home equity platform's lead-to-close cycle in half — Component 4 — Post-acceptance contract gen] Replaced the Word-template DocuSign flow with a templating system reading from the same admin config. Program names, terms, jurisdictional language all live in one plac

    98 tokens/blog/lead-to-close-half/id: c_219f3d1c3559261a
  • blogHow we cut a home equity platform's lead-to-close cycle in half/ What broke during rollout, and how did we fix it?

    [How we cut a home equity platform's lead-to-close cycle in half — What broke during rollout, and how did we fix it?] The voice agent confidently quoted a wrong CLTV cap on one call in week three. The cap had been updated in the admin config; the voice agent's eligibility-check

    211 tokens/blog/lead-to-close-half/id: c_c2c2db0e57ccdb54
  • blogHow we cut a home equity platform's lead-to-close cycle in half/ What stuck six months in?

    [How we cut a home equity platform's lead-to-close cycle in half — What stuck six months in?] All four components are live, six months in. The lead-to-close median is at 7 days, down from 14. The same team — twelve people, no new headcount — is processing roughly 2.2× the lead v

    226 tokens/blog/lead-to-close-half/id: c_51df9d9bc899cd02
  • blogYou can't hire a senior AI engineer fast enough — here's the math

    [You can't hire a senior AI engineer fast enough — here's the math] If you're running a $2–10M revenue company in real-estate finance, you already know you need AI infrastructure. Not a chatbot. Voice intake. Lead enrichment. CRM consolidation. Sequence orchestration. The work s

    97 tokens/blog/senior-ai-engineer-math/id: c_41e9b6c8ee6428ba
  • blogYou can't hire a senior AI engineer fast enough — here's the math/ What does a senior AI engineer actually cost in 2026?

    [You can't hire a senior AI engineer fast enough — here's the math — What does a senior AI engineer actually cost in 2026?] [Base salary for a senior AI engineer in the US sits around $220K](https://www.glassdoor.com/Salaries/senior-ai-engineer-salary-SRCH_KO0,18.htm). Add 25–35

    242 tokens/blog/senior-ai-engineer-math/id: c_ad71de2b97f3b730
  • blogYou can't hire a senior AI engineer fast enough — here's the math/ How long is the senior AI engineer hiring cycle?

    [You can't hire a senior AI engineer fast enough — here's the math — How long is the senior AI engineer hiring cycle?] [The 2025 surveys put senior AI engineer search at 4.5–6 months](https://www.acceler8talent.com/resources/blog/ai-engineer--salary---market-rates-2025-2026/) fr

    190 tokens/blog/senior-ai-engineer-math/id: c_9d5ed407f80ea094
  • blogYou can't hire a senior AI engineer fast enough — here's the math/ Where are the senior AI engineers who can actually ship?

    [You can't hire a senior AI engineer fast enough — here's the math — Where are the senior AI engineers who can actually ship?] The senior AI engineers who can ship production systems end-to-end — voice agents wired into dialers with drift detection, Claude-powered enrichment wit

    227 tokens/blog/senior-ai-engineer-math/id: c_50770e99cc38bf61
  • blogYou can't hire a senior AI engineer fast enough — here's the math/ The alternative

    [You can't hire a senior AI engineer fast enough — here's the math — The alternative] Fractional senior engineering. $7,500–$15,000 per month. Six-month minimum so the work has time to compound, but no equity, no recruiting cycle, no FTE conversion drag. You get the same stack

    202 tokens/blog/senior-ai-engineer-math/id: c_74a2eb8f9d34711b
  • blogYou can't hire a senior AI engineer fast enough — here's the math/ The order of operations

    [You can't hire a senior AI engineer fast enough — here's the math — The order of operations] If you're certain you'll need a full-time senior AI engineer eventually, the fractional path isn't a substitute — it's a head start. You ship the production stack now, with a partner wh

    231 tokens/blog/senior-ai-engineer-math/id: c_ca1386d417621cf6
  • blogThe 7-specialist review pipeline that keeps AI features from breaking in production

    [The 7-specialist review pipeline that keeps AI features from breaking in production] The most common failure mode I see in shipped AI features is not "the model is wrong." It's "the model was right in the demo, and then something around the model failed in production." [Researc

    190 tokens/blog/seven-specialist-review/id: c_cf3f77d8ed5f0077
  • blogAnatomy of an HEI eligibility engine: four investor overlays, zero LLMs in the decision

    [Anatomy of an HEI eligibility engine: four investor overlays, zero LLMs in the decision] This is a field report. Names are abstracted; the work is real. The same multi-program home equity operator covered in the [previous field report](/blog/lead-to-close-half/) runs four HEI

    294 tokens/blog/hei-eligibility-engine-anatomy/id: c_4a987bf04da7ce07
  • blogAnatomy of an HEI eligibility engine: four investor overlays, zero LLMs in the decision/ What does the architecture look like?

    [Anatomy of an HEI eligibility engine: four investor overlays, zero LLMs in the decision — What does the architecture look like?] The current state of the engine, in one sentence: per-program eligibility rules live in an admin-editable settings table, the calculators are determi

    230 tokens/blog/hei-eligibility-engine-anatomy/id: c_b9c388f8581f52c8
  • blogAnatomy of an HEI eligibility engine: four investor overlays, zero LLMs in the decision/ What does the architecture look like?

    [Anatomy of an HEI eligibility engine: four investor overlays, zero LLMs in the decision — What does the architecture look like?] This took a deliberate choice early. The pull toward "just throw it in a JSONB column" is strong at every Seed-stage shop. The pull is also wrong. JS

    233 tokens/blog/hei-eligibility-engine-anatomy/id: c_0ee3a63c8310d27a
  • blogAnatomy of an HEI eligibility engine: four investor overlays, zero LLMs in the decision/ How do four investor overlays run on one decision graph?

    [Anatomy of an HEI eligibility engine: four investor overlays, zero LLMs in the decision — How do four investor overlays run on one decision graph?] Each investor overlay evaluates independently against the same applicant snapshot. The engine returns all per-investor verdicts pl

    213 tokens/blog/hei-eligibility-engine-anatomy/id: c_9f309d0e28d41726
  • blogAnatomy of an HEI eligibility engine: four investor overlays, zero LLMs in the decision/ How do four investor overlays run on one decision graph?

    [Anatomy of an HEI eligibility engine: four investor overlays, zero LLMs in the decision — How do four investor overlays run on one decision graph?] The same engine runs the proprietary sale-leaseback product, with one wrinkle: a state-specific LTV override. The national cap is

    236 tokens/blog/hei-eligibility-engine-anatomy/id: c_d21a84de17b02a01
  • blogAnatomy of an HEI eligibility engine: four investor overlays, zero LLMs in the decision/ Why is there no LLM in the decision graph?

    [Anatomy of an HEI eligibility engine: four investor overlays, zero LLMs in the decision — Why is there no LLM in the decision graph?] LLMs are great at parsing unstructured documents. They are great at normalizing inbound data: a lead form that arrived as a free-text email, a v

    263 tokens/blog/hei-eligibility-engine-anatomy/id: c_81fcd8ee11e8a5aa
  • blogAnatomy of an HEI eligibility engine: four investor overlays, zero LLMs in the decision/ Why is there no LLM in the decision graph?

    [Anatomy of an HEI eligibility engine: four investor overlays, zero LLMs in the decision — Why is there no LLM in the decision graph?] A deterministic engine reading from a versioned settings table gives you all three for free. An LLM-in-the-loop gives you none of them. You can

    295 tokens/blog/hei-eligibility-engine-anatomy/id: c_9da8c849a08a4e55
  • blogAnatomy of an HEI eligibility engine: four investor overlays, zero LLMs in the decision/ What broke

    [Anatomy of an HEI eligibility engine: four investor overlays, zero LLMs in the decision — What broke] Four production fixes hit the eligibility layer in a twelve-day window after the per-investor admin tabs went live in mid-May. All four were caught by the architecture's loggin

    253 tokens/blog/hei-eligibility-engine-anatomy/id: c_8c07d2393d237889
  • blogAnatomy of an HEI eligibility engine: four investor overlays, zero LLMs in the decision/ What broke

    [Anatomy of an HEI eligibility engine: four investor overlays, zero LLMs in the decision — What broke] **Admin LTV cap wasn't actually the source of truth.** The admin Settings UI exposed an LTV cap as an editable knob. Three different code paths (a primary calculator, a shared

    158 tokens/blog/hei-eligibility-engine-anatomy/id: c_66bd59cf4eaaf52e
  • blogAnatomy of an HEI eligibility engine: four investor overlays, zero LLMs in the decision/ What broke

    [Anatomy of an HEI eligibility engine: four investor overlays, zero LLMs in the decision — What broke] **Investor proceeds cap silently bypassed in the partner wizard.** The admin-editable per-investor proceeds cap wasn't being applied in the partner-facing proceeds-range formul

    172 tokens/blog/hei-eligibility-engine-anatomy/id: c_b8ffab623222960f
  • blogAnatomy of an HEI eligibility engine: four investor overlays, zero LLMs in the decision/ What broke

    [Anatomy of an HEI eligibility engine: four investor overlays, zero LLMs in the decision — What broke] **Empty admin array crashed every request.** Production had one program's `ineligible_ownership_types` set to an empty array — an intentional admin choice to allow LLC ownershi

    237 tokens/blog/hei-eligibility-engine-anatomy/id: c_6b23c77b783f3256
  • blogAnatomy of an HEI eligibility engine: four investor overlays, zero LLMs in the decision/ What this means for HEI operators evaluating vendors

    [Anatomy of an HEI eligibility engine: four investor overlays, zero LLMs in the decision — What this means for HEI operators evaluating vendors] Three questions to ask any vendor selling you an "AI eligibility engine": First: show me the audit row for a decision made 90 days ag

    269 tokens/blog/hei-eligibility-engine-anatomy/id: c_a7ffc7f7efff474c