Nonprofit / Digital Equity · San Diego, CA · July 2025How C2K Got Their Inbox Under Control Without Losing Human Oversight
Computers 2 Kids runs on a single shared mailbox. Program applications, donation offers, tech support, order confirmations — everything in one place, one small team sorting it all. Hashing AI built an autonomous email agent that classifies, drafts, and triages every message, with a deterministic safety engine that holds veto power over the AI at every step.
One inbox. Thousands of emails. A very small team.
Computers 2 Kids refurbishes donated computers and gets them into the hands of low-income families across the country. Their lifeline to the community is a single shared mailbox — and it was drowning them.
When we audited the inbox, the pattern was stark. The majority of daily volume wasn't customer email at all: system notifications, order confirmations, voicemail alerts, newsletters, and internal mail buried the real inquiries. The real inquiries were highly repetitive — how do I apply, what does it cost, when can I pick up, how do I activate Office — but each one still needed a warm, accurate, personal answer.
Every answer had to be right. Prices, hours, program rules — a wrong answer to a low-income family isn't a typo, it's a broken promise. And some topics, like refunds, damaged devices, and legal requests, should never be answered by a machine. Off-the-shelf auto-responders were a non-starter.
The AI recommends. The safety engine decides.
We designed the agent around one uncompromising principle: the language model never has the last word. Every email flows through a pipeline where a deterministic, fully-tested safety engine — not the AI — makes the final routing decision.
A pre-filter silently sets aside vendor mail, system notices, voicemails, and marketing before any AI is invoked. A language model then reads each genuine inquiry, identifies intent, detects language, and recommends a response — as a suggestion only. The safety engine holds veto power: refunds, damage claims, legal requests, anything with personal risk — hard-routed to a human, always.
For safe topics, the AI writes a natural, personalized reply, but it can only state facts from a closed, human-approved knowledge base. Every URL, price, and phone number is verified against that set, then a second AI acts as an independent judge before anything is queued. Any doubt falls back to a human-approved template. Nothing is ever sent automatically — every reply lands as a ready-to-review draft with the customer's original message embedded below it.
- Smart pre-triage — Heuristics and a client-curated sender list silently filter vendor mail, confirmations, and newsletters before any AI runs.
- Intent classification — Identifies what the customer actually needs — including multiple intents in a single email — and flags language for bilingual drafting.
- Deterministic safety engine — A rules engine with 100% branch test coverage holds veto power. Sensitive topics are hard-routed to humans, no exceptions.
- Fact-grounded AI writing — Drafts are written naturally and personally, but every fact is verified against an approved knowledge base. A second AI acts as independent judge before anything is queued.
- Full-thread awareness — Tracks whole conversations, reopens threads when customers write back, and marks conversations complete when the customer has been helped.
- Shadow mode deployment — Zero sends, ever. Every reply lands as a ready-to-review draft — staff review, adjust, and click send.
Staff review and click send. The rest is handled.
Since going live, roughly 70% of inbox volume is triaged away before it reaches a human's to-do list — vendor mail, confirmations, and notifications that previously created noise. Not one genuine customer inquiry was mis-filtered during live verification.
Every real inquiry gets a personalized draft in under five minutes. By the time staff open the mailbox, warm, accurate replies are already waiting — with the customer's question embedded right below each one. Replies quote exact prices, hours, and program links from the approved knowledge base, greet customers by name, and handle multi-question emails in a single coherent answer, in English and Spanish.
Zero unauthorized sends across the entire engagement. Thousands of emails processed in development and production, and the send counter reads exactly zero. The safety architecture didn't just work — it was never even tested by accident.
~70%
of inbox noise auto-triaged away
< 5 min
to a ready-to-send draft
0
unauthorized sends across the entire deployment
2,100+
automated tests covering every decision path
From the team at C2K
“Thank you — I just noticed the drafts 😊 I'll start working on them today.”