The review work that checks itself first
ASK Consulting builds AI systems that hold up under hostile review. This one passed the most hostile review there is: the client's own engineers merging it into production.
The situation
A market research platform had the fraud problem every survey platform has: bad actors polluting the data buyers pay for. Their quality-enforcement team investigated flagged tickets by hand, an analyst digging through MongoDB queries per ticket. Their verdict on early tooling attempts was blunt: exploratory analysis where they needed deep-dives on the flagged question.
What we did
We built an AI quality-enforcement agent that sits on their own data. It reads a flagged ticket, pulls the evidence rows before any AI judgment happens, and walks a 5-step human-in-the-loop flow to a buyer-facing report card.
The part that made it trustworthy is not the AI. It is the gates around it:
- Missing evidence cannot render a "clear" verdict.
- Numeric claims are validated against the actual query counts.
- Contradictory device evidence blocks the report instead of shipping inside it.
Alongside it: a weekly threat intelligence pipeline monitoring 24 fraud-community channels, a corpus of over 181,000 messages, feeding detection rules and an executive brief their leadership reads.
The number
The first working version shipped within one week of the design call. The finished delivery was reviewed and merged into their production codebase by their own engineers: 369 files applied with zero merge conflicts, 2,498 tests passing at handoff. The engagement is monthly and has run six months and counting.
Anonymized at the founder's direction. Published with the client's approval on file; every number is from the engagement record.
If your AI feature is doing something like this, the same kind of thing can be running in your business in a week. Start with one thing: $1,000 fixed, one week, running by Friday.
Start with one thing: $1,000, one weekMore work: the pipeline that failed 95 times silently · the investigations OS · the research desk that runs itself