BUILD

Rebuilt a SaaS support stack from scratch in 3 weeks

Mid-market B2B SaaS, 80K active users. Replaced a Zendesk + Zapier + human-triage stack with a Claude-Sonnet-driven router plus three purpose-built agents. Live for 60 days, on-call paged once.

SHIPPED · 2026-02-14 SCOPE · 3 WEEKS STACK · CLAUDE SONNET 4.6 · POSTGRES · DENO DEPLOY

TIER-1 DEFLECTION

31% → 67%

AVG RESOLUTION TIME

4.2× faster

NET COST CHANGE

flat

ON-CALL PAGES (60d)

1

The problem

Client ran a B2B SaaS platform for ~80K active users. Support volume had grown 3x in 18 months while headcount had grown 1.4x. The existing stack — Zendesk routing, Zapier-driven escalations, manual tier-1 triage by human agents — was burning the team out and tier-1 deflection was stuck at 31% despite a comprehensive help centre.

The brief: rebuild support so most tier-1 issues resolve without a human, escalations land on the right agent without re-routing, and response quality matches or exceeds the human baseline. Three-week ship, no headcount cut on day one — they wanted to redeploy capacity to higher-tier work.

The diagnosis

We spent the first three days reading the last 6 months of tickets and the team's response patterns. Two things stood out:

  1. Most tier-1 tickets were product questions answerable from existing docs — but the docs lived in three places and the help-centre search was bad.
  2. The escalation routing was lossy — about 22% of escalations got bounced between two teams before landing right.

What we shipped

One router + three specialist agents, all on Claude Sonnet 4.6.

All four use the same prompt-cached system prompt (~5K tokens of product context + behavioural guardrails). Cache hit rate stays above 92% in production. Deployed on Deno Deploy for the API surface, Postgres for the eval and conversation logs, Sentry for errors, Datadog for cost dashboards.

What we evaluated continuously

What we'd do differently

  1. Start with the eval set. We built it in week 2; it should have been week 1, day 1. Without it we couldn't have caught two regressions during the build.
  2. Right-size more aggressively. The router agent could probably run on Haiku 4.5 (it's a classification task at heart). Would save another ~25% on its cost line.
  3. Ship the cost dashboard before shipping the agents. Same lesson as our LLM bill case study: visibility before deployment, not after.

Stack

Need a similar rebuild? We do these end-to-end.

SCOPE A BUILD → SEE SERVICES →